Best Image Generation Skills for Claude Code in 2026

⚡

The best Image Generation Skills for Claude Code in 2026 depends on the visual style you want (259 of 265 rated SAFE on Agent Skills Hub): We had 130 image skills make the same six pictures on the newest models. Claude Code with no skill got every line of text right, 66 skills matched it and none did better, so install one for its look: the 7 below each have one of their own and still kept every rule of the brief. See the test →

Image generation skills and MCP servers for Claude Code, Codex and other agents, security-graded: GPT Image, Nano Banana, Flux, image editing and design assets. Vet before you install.

What is an image generation skill for Claude Code?

An image generation skill is an installable package (a folder with a SKILL.md file, or an MCP server) that lets a coding agent such as Claude Code or Codex call an image model, such as Google's Nano Banana (Gemini), FLUX or GPT Image, to create or edit pictures and save them into your project. The skill supplies the connection to the model and the know-how for prompting it. Most bill you through your own account or API key with the model's provider; ComfyUI-based ones can run open models on your own machine instead.

Which model gets the text right: 17 models, one poster

Each model drew the test's poster once, with no skill, through the same provider; the text was read by OCR and checked by hand. One picture each, and a second try can differ: Nano Banana 2.1 misspelt a Chinese line in an earlier try. The skill test on this page sent every image call to GPT Image 2.6, Nano Banana 2.1 or FLUX 3.

ModelLines right (of 6)Per imageTimePoster
Muse6/6 $0.00553 sThe poster Muse drew
GPT Image 26/6 $0.00936 sThe poster GPT Image 2 drew
GPT Image 2.66/6 $0.00936 sThe poster GPT Image 2.6 drew
Nano Banana 26/6 $0.01214 sThe poster Nano Banana 2 drew
Nano Banana 2.16/6 $0.01243 sThe poster Nano Banana 2.1 drew
Hunyuan Image 3.56/6 $0.01924 sThe poster Hunyuan Image 3.5 drew
Qwen-Image 3 Pro6/6 $0.02910 sThe poster Qwen-Image 3 Pro drew
Seedream 5 Pro6/6 $0.02966 sThe poster Seedream 5 Pro drew
FLUX 36/6 $0.03831 sThe poster FLUX 3 drew
Grok Imagine 2
Only at its own default size
6/6 $0.04866 sThe poster Grok Imagine 2 drew
Wan 2.7 Image Pro
All six right, plus a line of its own (Est. 2024)
6/6 $0.05433 sThe poster Wan 2.7 Image Pro drew
Z-Image Turbo
Bristol as Bristel
5/6 $0.0107 sThe poster Z-Image Turbo drew
MAI Image 2.6
可颂 as 可谅
5/6 $0.03031 sThe poster MAI Image 2.6 drew
Nano Banana
Both Chinese lines garbled
4/6 $0.00814 sThe poster Nano Banana drew
Nano Banana Pro
Changed the Chinese date and put the last line in English
4/6 $0.02033 sThe poster Nano Banana Pro drew
FLUX 2 Pro
Both Chinese lines wrong (周六 as 周云)
4/6 $0.024154 sThe poster FLUX 2 Pro drew
GPT Image 1
The price line and the last Chinese line wrong; the dearest per image here
4/6 $0.20052 sThe poster GPT Image 1 drew
Midjourney
Not offered by the provider we used
- --
Imagen 4
Failed on the day
- -18 s

7 image generation skills with a look of their own (tested 2026)

What Claude Code drew with no skill: the poster, a mascot and the bag
For comparison, what Claude Code made with no skill: the poster, a mascot and the bag. See the six Claude Code made with no skill →

mono-color-skill ★ 3.6k

For a one-colour print look. Every picture came out in blue halftone on cream with oversized type, like a risograph poster, and every rule of the brief held. It drew 28 times to get there, the most of any skill that followed the brief (10.8 minutes, $0.17).

mono-color-skill: the poster, a mascot and the bag from our test
See the six pictures →

illo-skill ★ 421

For warm, hand-drawn illustration. It drew the mascot in a cartoon line style and put it on the poster and the bag too, so the six read as one set (9.5 minutes, $0.09).

illo-skill: the poster, a mascot and the bag from our test
See the six pictures →

voxel-icon ★ 105

For a voxel (3D pixel-block) look. The loaf, the mascot and even the bag came out as clean voxel art on white, with the text set plainly below (4.7 minutes, $0.07).

voxel-icon: the poster, a mascot and the bag from our test
See the six pictures →

sci-figure-workflow ★ 41

For flat vector graphics. Built for research-paper figures, it drew a sun-and-loaf poster in clean shapes and a line-drawn mascot, closer to an infographic than a photo (7.8 minutes, $0.05).

sci-figure-workflow: the poster, a mascot and the bag from our test
See the six pictures →

regional-culture-poster ★ 69

For posters built on Chinese lettering. It set a giant calligraphic 晨 (morning) behind the loaf; its mascot and bag stay close to the default photo look (3.6 minutes, $0.05).

regional-culture-poster: the poster, a mascot and the bag from our test
See the six pictures →

xxd-panel-028 ★ 72

For little isometric scenes. Built to turn photos into paper miniatures, from the brief alone it stood the mascot in a tiny bakery stall, with props from the same scene on the poster and the bag (4.6 minutes, $0.10).

xxd-panel-028: the poster, a mascot and the bag from our test
See the six pictures →

photo-revival ★ 607

For a quiet, minimal look. Built to turn your photos into airy hand-drawn pictures, from the brief alone it drew small subjects in a lot of white space with light type, the opposite of the busy default (6.7 minutes, $0.05).

photo-revival: the poster, a mascot and the bag from our test
See the six pictures →

From our 2026-11-08 test of 130 skills: each of these made all six pictures, wrote every line of text right, kept the formats asked for, added no text and drew one consistent mascot, and its set looks different from what Claude Code made with no skill (top). Not ranked; every result is in the test section below.

Image generation skills tested: the same six pictures from 130 skills

On 7 and 8 November 2026 we had 130 image generation skills make the same six pictures in a throwaway sandbox, driven by Claude Code (Claude Opus 5.5): a 3:4 poster for a made-up bakery with six exact lines of English and Chinese text, a square photo of a kraft-paper bag printed with the shop's name, and four square pictures of one mascot in four poses. Every image call went to the newest model of the family the skill asked for (GPT Image 2.6, Nano Banana 2.1 or FLUX 3) through one provider, so the skills compare on their prompts and workflow, not on the model they default to. Claude Code with no skill made the set too. The text was read by OCR, and by hand where OCR stumbled; the formats were measured; a vision model judged whether the four mascots are one character; the look was judged by eye. Each skill ran once, with 20 minutes.

All 98 posters side by side, the one Claude Code made with no skill outlined in red: most are the same warm photo of a loaf.
All 98 posters side by side, the one Claude Code made with no skill outlined in red: most are the same warm photo of a loaf.

What we found: On the newest models the text is not where skills differ. Claude Code with no skill wrote all six lines and the bag's name correctly, in 5.1 minutes for $0.07 of image calls. 66 skills did as well and none did better. 30 more made all six pictures but broke a rule, most often the format (26 drew the poster square, landscape or 2:3, or the square pictures some other shape) or text on the mascots (8). 31 made no picture: 20 work only with their own service or account, 7 do another job, 2 wait for a person and 2 drew nothing in 20 minutes. By eye, 77 of the 96 complete sets look close to the no-skill set and 19 have a look of their own. See the six Claude Code made with no skill →

Skill and what it drewResultTextFormatLook, by eyeTimeImage calls
regional-culture-poster ★ 69regional-culture-poster: the pictures from our test Followed the brief6/6 · bag ✓As askedA look of its own3.6 min6 · $0.05
xxd-panel-028 ★ 72Built to turn photos into isometric paper miniatures; from the brief alone it staged the mascot in a tiny bakery stall.xxd-panel-028: the pictures from our test Followed the brief6/6 · bag ✓As askedA look of its own4.6 min12 · $0.10
voxel-icon ★ 103voxel-icon: the pictures from our test Followed the brief6/6 · bag ✓As askedA look of its own4.7 min8 · $0.07
photo-revival ★ 607Built to turn your photos into airy hand-drawn pictures; from the brief alone it drew small subjects in a lot of white space.photo-revival: the pictures from our test Followed the brief6/6 · bag ✓As askedA look of its own6.7 min6 · $0.05
sci-figure-workflow ★ 41sci-figure-workflow: the pictures from our test Followed the brief6/6 · bag ✓As askedA look of its own7.8 min6 · $0.05
illo-skill ★ 418illo-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedA look of its own9.5 min10 · $0.09
mono-color-skill ★ 3,620Drew 28 times to get its one-colour look, the most of any skill that followed the brief.mono-color-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedA look of its own10.8 min28 · $0.17
ai-pixel-art-image-generation ★ 26Despite the name, the same photo and 3D look as Claude Code with no skill; the fastest here at 1.6 minutes.ai-pixel-art-image-generation: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set1.6 min6 · $0.05
Wangnov/gpt-image-2-skill ★ 146Wangnov/gpt-image-2-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.0 min6 · $0.05
gpt-image2-layered-psd ★ 17gpt-image2-layered-psd: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.0 min6 · $0.05
MeiGen-AI-Design-MCP ★ 1,800MeiGen-AI-Design-MCP: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.1 min6 · $0.05
gpt-image-2-prompting-skill ★ 56gpt-image-2-prompting-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.2 min7 · $0.06
zven-imagegen ★ 9zven-imagegen: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.2 min6 · $0.05
dshark3y/gpt-image-2-skill ★ 19dshark3y/gpt-image-2-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.4 min6 · $0.05
claude-image ★ 88claude-image: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.5 min6 · $0.05
gpt-image-skills ★ 6gpt-image-skills: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.6 min6 · $0.05
nanobanana ★ 8nanobanana: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.8 min7 · $0.10
ecom-details-image ★ 1,615ecom-details-image: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.9 min6 · $0.05
codex-image2-skill ★ 155codex-image2-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.9 min6 · $0.05
codex-bridge ★ 244codex-bridge: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set2.9 min6 · $0.05
openai-image-prompt-writer ★ 13openai-image-prompt-writer: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.0 min6 · $0.05
claude-skill-codex-imagegen ★ 22claude-skill-codex-imagegen: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.2 min7 · $0.06
hermes-codex-image-skill ★ 6hermes-codex-image-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.2 min7 · $0.06
deepseek-imagegen ★ 7deepseek-imagegen: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.2 min6 · $0.05
qiaomu-codex-imagegen ★ 136qiaomu-codex-imagegen: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.3 min6 · $0.05
biorender-mechanism-figures-skill ★ 41biorender-mechanism-figures-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.3 min7 · $0.06
sub2api-gpt-image-2 ★ 13sub2api-gpt-image-2: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.3 min7 · $0.06
codex-gpt-image-mcp ★ 5codex-gpt-image-mcp: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.3 min7 · $0.06
api-image ★ 109api-image: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.4 min7 · $0.06
remote-imagegen ★ 24remote-imagegen: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.4 min7 · $0.06
design-bridge ★ 8design-bridge: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.4 min8 · $0.07
UzenUPoZiTiV4ik/gpt-image-2-skill ★ 439UzenUPoZiTiV4ik/gpt-image-2-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.5 min6 · $0.05
codex-image ★ 32codex-image: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.5 min7 · $0.06
nano-banana-pro-mcp ★ 18nano-banana-pro-mcp: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.5 min6 · $0.08
ccskill-nanobanana ★ 29ccskill-nanobanana: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.6 min6 · $0.07
nano-banana-claude-plugin ★ 14nano-banana-claude-plugin: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.6 min6 · $0.07
codex-imagegen-free-reference ★ 6codex-imagegen-free-reference: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.7 min7 · $0.06
claude-image-gen ★ 80claude-image-gen: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set3.8 min9 · $0.11
creating-social-media-visuals ★ 9creating-social-media-visuals: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.0 min9 · $0.08
eterna-image2image-skill ★ 185eterna-image2image-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.1 min8 · $0.07
codex-canvas ★ 160codex-canvas: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.2 min8 · $0.07
paper-signal ★ 109paper-signal: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.3 min7 · $0.06
gpt-image-2-5-agent-kit ★ 25gpt-image-2-5-agent-kit: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.4 min6 · $0.05
gpt-image-2-ecommerce-skill ★ 13gpt-image-2-ecommerce-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.4 min7 · $0.06
nano-banana-2-skill ★ 417nano-banana-2-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.5 min7 · $0.09
ecommerce-image-skills ★ 155ecommerce-image-skills: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.5 min8 · $0.07
image-inspirer ★ 41image-inspirer: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.5 min7 · $0.06
huashu-gpt-image ★ 29huashu-gpt-image: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.5 min7 · $0.06
hermes-daily-image-training ★ 5hermes-daily-image-training: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.5 min7 · $0.06
codex-gpt-image-2-subscription ★ 9codex-gpt-image-2-subscription: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.6 min7 · $0.06
fantasy-dongfang-jianyuehaibao ★ 126fantasy-dongfang-jianyuehaibao: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.7 min7 · $0.06
scientific-visual-skills ★ 21scientific-visual-skills: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set4.7 min7 · $0.06
image-first-frontend ★ 6image-first-frontend: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set5.1 min6 · $0.05
sub2api-4k-image-generator-ts ★ 12sub2api-4k-image-generator-ts: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set5.2 min10 · $0.09
ultimate-image-gen-mcp ★ 14ultimate-image-gen-mcp: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set5.5 min7 · $0.10
nano-banana-2-promptor-skill ★ 8nano-banana-2-promptor-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set5.9 min8 · $0.14
banana-claude ★ 1,192banana-claude: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set6.0 min6 · $0.07
codexQIYU-image-workflow ★ 107codexQIYU-image-workflow: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set6.1 min6 · $0.05
nanobanana-mcp-server ★ 403nanobanana-mcp-server: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set6.4 min6 · $0.07
gpt-image2-ecommerce ★ 442gpt-image2-ecommerce: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set6.5 min7 · $0.06
gen-images-skill ★ 32gen-images-skill: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set6.8 min7 · $0.09
micu-image-mcp ★ 318micu-image-mcp: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set7.0 min6 · $0.05
nanobanana-mcp ★ 32nanobanana-mcp: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set7.8 min6 · $0.07
Nano-Banana-MCP ★ 235Nano-Banana-MCP: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set8.5 min7 · $0.08
flyreq-image-studio ★ 169flyreq-image-studio: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set8.9 min7 · $0.06
huashu-slide-codex ★ 25huashu-slide-codex: the pictures from our test Followed the brief6/6 · bag ✓As askedClose to the no-skill set10.1 min8 · $0.07
ip-as-logo-skill ★ 6,456Makes the mascot-as-logo only, as its README says: no text on the poster or the bag.ip-as-logo-skill: the pictures from our test Broke a rule0/6 · bag ✗Poster 1:1A look of its own1.5 min6 · $0.05
tait-crt-interface-skill ★ 541Extra text on the poster; text on the mascot picturesFrames every picture as a retro computer screen, and printed its own name on the poster.tait-crt-interface-skill: the pictures from our test Broke a rule6/6 · bag ✓As askedA look of its own2.6 min6 · $0.05
generate-article-cover-image ★ 16Text on the mascot pictures; the mascots less alike (judge 4/5)generate-article-cover-image: the pictures from our test Broke a rule6/6 · bag ✓All six 5:2A look of its own3.0 min6 · $0.05
awesome-gpt-image2-ppt-skills ★ 191awesome-gpt-image2-ppt-skills: the pictures from our test Broke a rule6/6 · bag ✓All six 16:9A look of its own3.1 min6 · $0.05
muted-zine-poster-v01 ★ 90Text on the mascot picturesA muted zine look on 9:16 pages, with the mascot's name on its pictures.muted-zine-poster-v01: the pictures from our test Broke a rule6/6 · bag ✓All six 9:16A look of its own3.4 min7 · $0.06
bold-contour-ink-portrait ★ 9The mascots less alike (judge 4/5)Black ink line art: the red scarf came out black.bold-contour-ink-portrait: the pictures from our test Broke a rule6/6 · bag ✓As askedA look of its own4.5 min8 · $0.07
xhs-imagen ★ 120Text on the mascot picturesxhs-imagen: the pictures from our test Broke a rule6/6 · bag ✓5 not squareA look of its own5.7 min7 · $0.06
ian-xiaohei-scenes ★ 552Text on the mascot pictures; the mascots less alike (judge 3/5); the hat or scarf missing in someIts Xiaohei character in place of the bun, 16:9, and 2 of the 6 lines.ian-xiaohei-scenes: the pictures from our test Broke a rule2/6 · bag ✓All six 16:9A look of its own6.0 min10 · $0.09
fantasy-qiqiguaiguai-skill ★ 125Extra text on the poster; text on the mascot picturesBig-type posters; added lines of its own on the poster, the bag and the mascots.fantasy-qiqiguaiguai-skill: the pictures from our test Broke a rule6/6 · bag ✓5 not squareA look of its own8.0 min15 · $0.13
skills ★ 97The mascots less alike (judge 4/5)A chalkboard look; the poster carries the shop name and none of the other five lines.skills: the pictures from our test Broke a rule1/6 · bag ✓As askedA look of its own8.1 min15 · $0.13
ian-xiaohei-illustrations ★ 13,125Text on the mascot picturesDraws everything 16:9 in its own style, with its Xiaohei character in place of the bun.ian-xiaohei-illustrations: the pictures from our test Broke a rule6/6 · bag ✓All six 16:9A look of its own12.4 min17 · $0.05
codex-ppt-skill ★ 7,716A slide-deck skill: made all six as 16:9 slides, in 20 minutes.codex-ppt-skill: the pictures from our test Broke a rule6/6 · bag ✓All six 16:9A look of its own20.1 min9 · $0.08
guizang-material-illustration ★ 1,243guizang-material-illustration: the pictures from our test Broke a rule6/6 · bag ✓Poster 1:1Close to the no-skill set2.6 min6 · $0.05
codex-image-context-runtime ★ 97codex-image-context-runtime: the pictures from our test Broke a rule6/6 · bag ✓Poster 2:3Close to the no-skill set3.1 min6 · $0.05
artifex-mcp ★ 9artifex-mcp: the pictures from our test Broke a rule6/6 · bag ✓Poster 9:16Close to the no-skill set3.1 min6 · $0.05
nano-banana-prompting-skill ★ 5Wrote no text on the poster or the bag.nano-banana-prompting-skill: the pictures from our test Broke a rule0/6 · bag ✗As askedClose to the no-skill set3.3 min7 · $0.10
xiaohu-ip-studio ★ 304xiaohu-ip-studio: the pictures from our test Broke a rule6/6 · bag ✓Poster 2:3Close to the no-skill set3.6 min7 · $0.06
claude-custom-skills-demo ★ 7claude-custom-skills-demo: the pictures from our test Broke a rule6/6 · bag ✓Poster 1:1Close to the no-skill set3.7 min13 · $0.16
awesome-ppt-skills ★ 74Text on the mascot picturesawesome-ppt-skills: the pictures from our test Broke a rule6/6 · bag ✓Poster 1:1Close to the no-skill set3.8 min8 · $0.07
codex-skill-academic-slides ★ 8codex-skill-academic-slides: the pictures from our test Broke a rule6/6 · bag ✓All six 16:9Close to the no-skill set4.4 min7 · $0.06
custom-icons-skill ★ 41custom-icons-skill: the pictures from our test Broke a rule6/6 · bag ✓Poster 1:1Close to the no-skill set4.7 min7 · $0.06
image-cockpit-for-codex-workflows ★ 296image-cockpit-for-codex-workflows: the pictures from our test Broke a rule6/6 · bag ✓Poster 2:3Close to the no-skill set4.9 min6 · $0.05
imagegen-mcp ★ 37imagegen-mcp: the pictures from our test Broke a rule6/6 · bag ✓Poster 2:3Close to the no-skill set6.0 min6 · $0.05
NanoBananaASO ★ 61NanoBananaASO: the pictures from our test Broke a rule6/6 · bag ✓5 not squareClose to the no-skill set6.8 min8 · $0.11
gpt-image-1-mcp ★ 18gpt-image-1-mcp: the pictures from our test Broke a rule6/6 · bag ✓Poster 2:3Close to the no-skill set6.8 min6 · $0.05
xhs-writer-skill ★ 190A social-card layout; left out the price line and the last Chinese line.xhs-writer-skill: the pictures from our test Broke a rule4/6 · bag ✓All six 2:3Close to the no-skill set9.0 min21 · $0.18
image-gen-mcp ★ 69image-gen-mcp: the pictures from our test Broke a rule6/6 · bag ✓Poster 2:3Close to the no-skill set9.1 min14 · $0.12
mcp-server-gemini-image-generator ★ 3423 image calls and no text on any picture.mcp-server-gemini-image-generator: the pictures from our test Broke a rule0/6 · bag ✗Poster 1:1Close to the no-skill set10.3 min23 · $0.28
cc-nano-banana ★ 38217.5 minutes, the slowest of the sets with all six; a square poster.cc-nano-banana: the pictures from our test Broke a rule6/6 · bag ✓Poster 1:1Close to the no-skill set17.5 min9 · $0.11
PaperBanana-AIMSLab ★ 848 image calls in 21 minutes, the most here; a 2:3 poster.PaperBanana-AIMSLab: the pictures from our test Broke a rule6/6 · bag ✓Poster 2:3Close to the no-skill set21.2 min48 · $0.41
paperbanana ★ 2,471A pipeline for research-paper figures: 1 picture in 20 minutes.paperbanana: the pictures from our test Part of the set-As asked-20.1 min10 · $0.14
PaperBanana-CN ★ 85A pipeline for research-paper figures: 3 pictures in 20 minutes.PaperBanana-CN: the pictures from our test Part of the set6/6 · bag ✓As asked-20.1 min3 · $0.04
female-portrait-director ★ 1,699Draws portraits of women only, so it got a portrait brief instead of the bakery set.female-portrait-director: the pictures from our test Portrait only---1.9 min1 · $0.01
Made no picture (31)
  • andyluu98/ai-image-gpt-mcp: Works only with its own service or account: needs a ChatGPT sign-in in a browser; it does not read an API key.
  • AndyShaman/gemini-webapi-mcp: Works only with its own service or account: needs a signed-in Gemini web session (browser cookies).
  • awei84/antibanana-mcp: Works only with its own service or account: needs Antigravity credentials.
  • black-forest-labs/flux-mcp: Works only with its own service or account: needs a Black Forest Labs account (the hosted official MCP).
  • BlockRunAI/Claude-Code-GPT-IMAGE2-SeeDance-BlockRun: Works only with its own service or account: needs a funded BlockRun wallet (USDC on Base).
  • boteSu/aiChatGptAgent: Works only with its own service or account: needs ChatGPT web accounts, which it offers to mass-register: against OpenAI's terms, so not done.
  • Bria-AI/bria-skill: Works only with its own service or account: needs a Bria API key.
  • darkamenosa/codex-imagen: Works only with its own service or account: needs a ChatGPT or Codex sign-in; it does not take an API key.
  • jomeswang/agnes-ai-skill: Works only with its own service or account: needs an Agnes API key.
  • kodelyx/flow-agent: Works only with its own service or account: needs a signed-in Google Flow session.
  • koshimazaki/flux-api-control-surface: Works only with its own service or account: needs a Black Forest Labs key in the macOS Keychain.
  • luciferfran/nan-mcp-server: Works only with its own service or account: needs a NaN API key.
  • metavolve-labs/studiomcphub: Works only with its own service or account: needs paid credits on its hosted server.
  • ningzimu/codex-gpt-image: Works only with its own service or account: needs a Codex sign-in and says not to use an API key.
  • nopnor/SCOPE: Works only with its own service or account: needs a JD Cloud account.
  • runapi-ai/mcp: Works only with its own service or account: needs a RunAPI account.
  • SamurAIGPT/Generative-Media-Skills: Works only with its own service or account: needs a MuAPI account and key.
  • scenario-labs/skills: Works only with its own service or account: needs a Scenario account or API key.
  • TamerinTECH/claude-code-generate-images-mcp: Works only with its own service or account: calls a retired Gemini 2.0 endpoint written into its code, or Azure OpenAI; our sandbox's relay did not serve that endpoint.
  • xinvxueyuan/NovelAI-Image-MCP: Works only with its own service or account: needs a NovelAI account.
  • Andy20010101/style-prompt-forger-skill: Does another job, not pictures from a brief: writes reusable style prompts, not pictures.
  • Evianis/travel-photo-abstraction: Does another job, not pictures from a brief: needs a travel photo to start from.
  • karem505/character-animation-skill: Does another job, not pictures from a brief: animates a character picture you give it.
  • LueXxxxxxx/architecture-image2-diagram-skill: Does another job, not pictures from a brief: draws architecture diagrams only.
  • op7418/guizang-yingzao-skill: Does another job, not pictures from a brief: covers its own subject only, not ads, products or mascots.
  • ShinChven/nano-banana-skills: Does another job, not pictures from a brief: needs existing pictures of the character; makes a three-view sheet.
  • Vieeeeeee/wibi-style: Does another job, not pictures from a brief: restyles a photo you give it, and its licence is non-commercial only.
  • Gayaya999/ecommerce-detail-page-generator: Waits for a person first: asks for missing shop details before drawing, and makes text-free product shots only.
  • izscc/cc2image: Waits for a person first: must have a person pick a style in a separate plugin first.
  • helloianneo/ian-handdrawn-ppt: No picture within 20 minutes: a slide-deck workflow: no picture saved in 20 minutes.
  • JuneYaooo/gpt-image2-ppt-skills: No picture within 20 minutes: a slide-deck workflow: no picture saved in 20 minutes.

All results and scripts →

The Complete Guide to Image Generation Skills for Claude Code (2026)

What Are Image Generation Skills for Claude Code?

Image Generation Skills for Claude Code are AI-powered software designed to help developers and teams tackle image generation-related tasks more efficiently. These tools are typically published as open-source projects on GitHub and can be integrated into existing workflows via MCP (Model Context Protocol), Claude Skills, or standalone agent frameworks. On Agent Skills Hub, we index 265 quality-scored Image Generation Skills for Claude Code across languages including Python, JavaScript, TypeScript.

Why Use Image Generation Skills for Claude Code?

In 2026, the AI agent ecosystem is maturing rapidly. Image Generation Skills for Claude Code can significantly boost development efficiency by automating repetitive tasks, reducing human error, and providing intelligent suggestions. The top 3 tools — ian-xiaohei-illustrations, ip-as-logo-skill, mono-color-skill — have earned an average of 7,743 GitHub stars. 194 of the listed tools come with clear open-source licenses, ensuring freedom to use and modify.

How to Choose the Best Image Generation Skills for Claude Code?

When choosing among Image Generation Skills for Claude Code, consider these factors: 1) Community activity — GitHub stars and recent commit frequency indicate reliability; 2) Integration method — check if it supports MCP, Claude, or your preferred agent framework; 3) Language compatibility — the most common language in this list is Python; 4) Quality score — Agent Skills Hub's 9-dimension quality score rates documentation completeness, structure and agent readiness, not the code. Our recommendation: start with ian-xiaohei-illustrations — it has the most GitHub stars on this list.

Top 265 Image Generation Skills for Claude Code

1 ian-xiaohei-illustrations by helloianneo
★ 13.2k GPT Image

Codex Skill for generating illustrations for Chinese “Little Black Grotesque” body text, hand-drawn on white 16:9 backgrounds with sparse red, orange, and blue…

🧪 Image test, 2026-11-08: Draws everything 16:9 in its own style, with its Xiaohei character in place of the bun. · made all six but broke a rule: all six 16:9; text on the mascot pictures · a look of its own · 12.4 min · 17 image calls ($0.05) · See the six pictures →
git clone https://github.com/helloianneo/ian-xiaohei-illustrations.git
2 ip-as-logo-skill by s1dashu
★ 6.4k Design assets

A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.

🧪 Image test, 2026-11-08: Makes the mascot-as-logo only, as its README says: no text on the poster or the bag. · made all six but broke a rule: 0 of 6 poster lines right; the shop name on the bag wrong or missing; poster 1:1 · a look of its own · 1.5 min · 6 image calls ($0.05) · See the six pictures →
npx skills@latest add s1dashu/ip-as-logo-skill
3 mono-color-skill by yanliudesign
★ 3.6k Design assets

One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained typography.

🧪 Image test, 2026-11-08: Drew 28 times to get its one-colour look, the most of any skill that followed the brief. · followed the brief: all six pictures, all text right, formats as asked · a look of its own · 10.8 min · 28 image calls ($0.17) · See the six pictures →
4 skills by scenario-labs
★ 3.8k MCP servers

Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a Scenario account or API key.
npx skills add scenario-labs/skills --skill "*"
5 paperbanana by llmsresearch
★ 2.5k MCP servers

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

🧪 Image test, 2026-11-08: A pipeline for research-paper figures: 1 picture in 20 minutes. · 1 of the 6 pictures in 20 minutes · 20.1 min · 10 image calls ($0.14) · See the six pictures →
pip install paperbanana
6 MeiGen-AI-Design-MCP by jau123
★ 1.8k MCP servers

Discover inspiration and create images and videos with the latest AI models. Works with ChatGPT, Claude, Cursor, and other MCP clients.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.1 min · 6 image calls ($0.05) · See the six pictures →
/plugin marketplace add jau123/MeiGen-AI-Design-MCP
7 female-portrait-director by liyue-aigc
★ 1.7k GPT Image

A modular Codex Skill for directing and expanding detailed AI female portrait prompts.

🧪 Image test, 2026-11-08: Draws portraits of women only, so it got a portrait brief instead of the bakery set. · draws portraits of women only; given a portrait brief, it made one · 1.9 min · 1 image calls ($0.01) · See the six pictures →
npx skills@latest add liyue-aigc/female-portrait-director -g -a codex -y
8 ecom-details-image by liangdabiao
★ 1.7k GPT Image

A skill for workbuddy/Codex agents: generates e-commerce product, detail, social, livestream images from photos and descriptions via GPT-Image-2 API.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.9 min · 6 image calls ($0.05) · See the six pictures →
git clone https://github.com/liangdabiao/ecom-details-image.git
★ 1.3k Design assets

Guizang’s material illustration skill: creates annotated images, improves charts, and makes reference illustrations.

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 1:1 · close to the no-skill set · 2.6 min · 6 image calls ($0.05) · See the six pictures →
npx skills add https://github.com/op7418/guizang-material-illustration --skill guizang-material-illustration
10 banana-claude by AgriciDaniel
★ 1.2k Nano Banana & Gemini

AI image generation skill for Claude Code - Creative Director powered by Gemini

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 6.0 min · 6 image calls ($0.07) · See the six pictures →
/plugin marketplace add AgriciDaniel/banana-claude
11 codex-ppt-skill by ningzimu
★ 7.8k GPT Image

GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

🧪 Image test, 2026-11-08: A slide-deck skill: made all six as 16:9 slides, in 20 minutes. · made all six but broke a rule: all six 16:9 · a look of its own · 20.1 min · 9 image calls ($0.08) · See the six pictures →
12 GPT-Image2-Skill by wuyoscar
★ 6.0k GPT Image

GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

/plugin marketplace add wuyoscar/gpt_image_2_skill
13 NanoBanana-PPT-Skills by op7418
★ 3.4k Nano Banana & Gemini

NanoBanana PPT Skills uses AI to generate PPT images and videos, with smart transitions and interactive playback.

git clone https://github.com/op7418/NanoBanana-PPT-Skills.git
14 hand-drawn-styles by threerocks
★ 2.7k Design assets

Claude Code skill: turns content into copyable image prompts using 5 built-in hand-drawn styles: coloring, line art, crayon, Ghibli, bean-person doodles.

git clone https://github.com/threerocks/hand-drawn-styles.git
15 MiniMax-MCP by MiniMax-AI
★ 1.6k MCP servers

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

16 ian-handdrawn-ppt by helloianneo
★ 1.5k GPT Image

Chinese hand-drawn technical PPT full-page image generation skill, with 21:9 covers, 16:9 content images, and PNG output

🧪 Tried in our test, no picture. No picture within 20 minutes: a slide-deck workflow: no picture saved in 20 minutes.
git clone https://github.com/helloianneo/ian-handdrawn-ppt.git
17 gpt-image2-ppt-skills by JuneYaooo
★ 1.4k GPT Image

Clone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT:gpt-image-2 仿版式、你换内容,另含 10 套精选风格。Claude Code / OpenClaw skill.

🧪 Tried in our test, no picture. No picture within 20 minutes: a slide-deck workflow: no picture saved in 20 minutes.
18 ai-image-prompts-skill by YouMind-OpenLab
★ 1.4k Design assets

AI Image Prompts — 10,000+ curated prompts for any model. Works with Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E, Flux, Stable Diffusion, and more.

npx skills i YouMind-OpenLab/ai-image-prompts-skill
19 comfyui-mcp by artokun
★ 938 MCP servers

Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.

claude plugin install comfyui-mcp
20 ima2-gen by lidge-ai
★ 904 MCP servers

Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.

npm install -g ima2-gen
21 travel-photo-abstraction by Evianis
★ 800 GPT Image

A source-available Codex skill for distilling photographs into sparse editorial abstractions.

🧪 Tried in our test, no picture. Does another job, not pictures from a brief: needs a travel photo to start from.
git clone https://github.com/Evianis/travel-photo-abstraction.git
22 ilab-conjure by kadevin
★ 739 GPT Image

本地优先的多模型 AI 图片生成工作台,支持 GPT Image、Gemini、图像编辑、素材库、模板与并发任务。Local-first AI image workbench for GPT Image & Gemini, with editing, reusable assets, templates and task history.

git clone https://github.com/kadevin/ilab-conjure.git
23 visual-skills by smixs
★ 632 MCP servers

AI film director skills for agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for Seedance 2.5, Kling 3.0 Turbo/Omni, Veo 3.1, Nano Banana 2, GPT Image 2.5.

git clone https://github.com/smixs/visual-skills.git
24 photo-revival by dacnay816y62-hub
★ 607 GPT Image

Codex skill for turning everyday photos into poetic white-paper hand-drawn illustrations.

🧪 Image test, 2026-11-08: Built to turn your photos into airy hand-drawn pictures; from the brief alone it drew small subjects in a lot of white space. · followed the brief: all six pictures, all text right, formats as asked · a look of its own · 6.7 min · 6 image calls ($0.05) · See the six pictures →
25 draw-ui by oil-oil
★ 555 GPT Image

Claude Code skill: generate UI design mockups with GPT Image 2 via ZenMux

npx skills add oil-oil/draw-ui
26 ian-xiaohei-scenes by helloianneo
★ 554 GPT Image

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

🧪 Image test, 2026-11-08: Its Xiaohei character in place of the bun, 16:9, and 2 of the 6 lines. · made all six but broke a rule: 2 of 6 poster lines right; all six 16:9; text on the mascot pictures; the mascots less alike (judge 3/5); the hat or scarf missing in some · a look of its own · 6.0 min · 10 image calls ($0.09) · See the six pictures →
git clone https://github.com/helloianneo/ian-xiaohei-scenes.git
27 tait-crt-interface-skill by TaiT-tt
★ 547 GPT Image

TaiT-CRT-Interface-Skill is a Codex image generation skill that transforms user-uploaded portraits, photographs, or text descriptions into a retro illustration with the feel of an early CRT computer interface.

🧪 Image test, 2026-11-08: Frames every picture as a retro computer screen, and printed its own name on the poster. · made all six but broke a rule: extra text on the poster; text on the mascot pictures · a look of its own · 2.6 min · 6 image calls ($0.05) · See the six pictures →
28 guizang-yingzao-skill by op7418
★ 539 GPT Image

🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报

🧪 Tried in our test, no picture. Does another job, not pictures from a brief: covers its own subject only, not ads, products or mascots.
npx skills add https://github.com/op7418/guizang-yingzao-skill --skill yingzao
29 higgsfield-claude-skills by AKCodez
★ 474 MCP servers

19 Claude Code skills for Higgsfield AI — automate image generation, Seedance 2.0 video creation, and full UGC ad pipelines with Playwright browser automation

30 gpt-image2-ecommerce by buluslan
★ 441 GPT Image

E-commerce product image generator skill — 39 scenario templates, GPT-Image-2/2.5 (Flare/Sunburst) model routing, campaign consistency lock, platform compliance. 电商做图 Skill:39 场景模板×双模型路由×套图一致性×平台合规。

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 6.5 min · 7 image calls ($0.06) · See the six pictures →
git clone https://github.com/buluslan/gpt-image2-ecommerce.git ~/.claude/skills/ecom-image2
31 gpt-image-2-skill by UzenUPoZiTiV4ik
★ 439 GPT Image

A universal skill for generating realistic images

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.5 min · 6 image calls ($0.05) · See the six pictures →
32 kokon by GabrieleLozupone
★ 426 Image editing

Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay on your computer, no daily limit. One installer for Windows, Mac and Linux sets up the best open model (Qwen-Image 2.1). MCP server for AI agents.

claude mcp add --scope user kokon -- "$env:LOCALAPPDATA\Kokon\kokon-mcp.exe"
33 ComfyUI_Skills_OpenClaw by HuangYuChuh
★ 422 Open models

Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Comfy official local MCP.

git clone https://github.com/HuangYuChuh/ComfyUI_Skills_OpenClaw.git comfyui-skill-openclaw
34 image-use by leeguooooo
★ 422 GPT Image

Use your ChatGPT subscription to generate images from the command line — no OPENAI_API_KEY, no gateway, no daemon. Zero-dep Python CLI + AI-agent skill.

npx skills add leeguooooo/image-use -g
35 illo-skill by tmchow
★ 421 MCP servers

illo skill — an AI agent skill that turns ideas and articles into original print-style editorial illustrations, starring a recurring mascot. 30+ characters packs, with ability to create your own.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · a look of its own · 9.5 min · 10 image calls ($0.09) · See the six pictures →
npx skills add tmchow/illo-skill --skill illo
36 nano-banana-2-skill by kingbootoshi
★ 417 Nano Banana & Gemini

AI image generation CLI powered by Gemini 3 Pro. Green screen transparency, reference images, style transfer. Also a Claude Code plugin.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.5 min · 7 image calls ($0.09) · See the six pictures →
git clone https://github.com/kingbootoshi/nano-banana-2-skill.git ~/tools/nano-banana-2
37 comfyui-mcp-server by joenorton
★ 412 Open models

lightweight Python-based MCP (Model Context Protocol) server for local ComfyUI

git clone https://github.com/joenorton/comfyui-mcp-server.git
38 nanobanana-mcp-server by zhongweili
★ 404 MCP servers

AI image generation MCP server powered by Google Gemini, with smart model selection and 4K output

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 6.4 min · 6 image calls ($0.07) · See the six pictures →
uvx nanobanana-mcp-server@latest
39 cc-nano-banana by kkoppenhaver
★ 383 Nano Banana & Gemini

A Claude Code skill to generate images with Nano Banana

🧪 Image test, 2026-11-08: 17.5 minutes, the slowest of the sets with all six; a square poster. · made all six but broke a rule: poster 1:1 · close to the no-skill set · 17.5 min · 9 image calls ($0.11) · See the six pictures →
git clone https://github.com/kkoppenhaver/cc-nano-banana ~/.claude/skills/nano-banana
40 comfy-mcp by Comfy-Org
★ 359 MCP servers

Local MCP server for ComfyUI — run your local ComfyUI from AI agents

pip install comfy-mcp "comfy-cli>=1.14.0" # this server + the engine it wraps
41 micu-image-mcp by Subaru486desuwa
★ 331 MCP servers

MCP server wrapping 米醋 gpt-image-2 / gpt-image-2-pro proxy. One-click install for Claude Code / Codex / Cursor.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 7.0 min · 6 image calls ($0.05) · See the six pictures →
git clone https://github.com/Subaru486desuwa/micu-image-mcp.git
42 gongnyang-prompt-kit by gongnyang
★ 330 GPT Image

Claude Code skill that compiles vague requests into complete gpt-image-2 prompts: no negative prompts, result-based descriptions, validation scripts, C1–C10

git clone https://github.com/gongnyang/gongnyang-prompt-kit
43 ai-game-art-pipeline-skill by ybuild-ai
★ 306 Image editing

Agent skill from Y Build for turning AI images and videos into playable game art assets

npx skills add ybuild-ai/ai-game-art-pipeline-skill --skill ai-game-art-pipeline -g
44 xiaohu-ip-studio by xiaohuailabs
★ 306 GPT Image

Open-source skill and IP character library for illustrating Chinese long-form articles with recurring characters, cognitive anchors, improvised metaphors, and…

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 2:3 · close to the no-skill set · 3.6 min · 7 image calls ($0.06) · See the six pictures →
git clone https://github.com/xiaohuailabs/xiaohu-ip-studio ~/.claude/skills/xiaohu-ip-studio
45 image-cockpit-for-codex-workflows by dreiachse-cyber
★ 296 GPT Image

Local cockpit for Codex imagegen, pixel art, image editing, animation, and sprite-sheet workflows.

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 2:3 · close to the no-skill set · 4.9 min · 6 image calls ($0.05) · See the six pictures →
46 PocketMen-with-you by six-nut
★ 294 Open models

Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.

47 ai-media-generator by Hao0321
★ 274 MCP servers

Zero-skill cinema. Senior-director prompts on autopilot. A Claude Code Skill for high-quality AI image / video / music prompt crafting and browser-based execution across 14+ generative platforms.

48 flow-agent by kodelyx
★ 259 MCP servers

⚡ CLI toolkit for Google Flow — Nano Banana Pro images, Omni Flash videos, MCP v2 & OpenAI API.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a signed-in Google Flow session.
git clone https://github.com/kodelyx/flow-agent.git
49 shots by hypersocialinc
★ 250 GPT Image

Claude Code/Agent Skill for making App Store Screenshot generator with GPT Image 2. Give it your App Store link & screenshots of your app and it will produce beautiful app store screenshots ready to upload to Apple (or Google)

npx skills add hypersocialinc/shots
50 MiniMax-H3-ImageNEW by MiniMax-AI
★ 250 Image editing

MiniMax-H3-Image, an open-weight model for 16-megapixel image generation and editing.

npx skills add https://github.com/MiniMax-AI/MiniMax-H3-Image --skill h3-image-prompt-writing
51 codex-bridge by Sateezg
★ 243 GPT Image

Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.9 min · 6 image calls ($0.05) · See the six pictures →
/plugin marketplace add Sateezg/codex-bridge
52 generative-media-skills by calesthio
★ 242 Open models

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

53 Nano-Banana-MCP by ConechoAI
★ 238 Nano Banana & Gemini

A Nano Banana MCP server, which you can integrate to cursor/claude code and any mcp client

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 8.5 min · 7 image calls ($0.08) · See the six pictures →
npx nano-banana-mcp
54 comfy-pilot by ConstantineB6
★ 232 MCP servers

MCP server + embedded terminal that lets Claude Code see and edit your ComfyUI workflows

55 Plush-for-ComfyUI by glibsonoran
★ 199 MCP servers

Custom node for ComfyUI/Stable Diffustion

git clone https://github.com/glibsonoran/Plush-for-ComfyUI.git.
56 cc2image by izscc
★ 194 Design assets

Codex Chinese-content interactive image generation system skill: cognitive-anchor image breakdown, 49 content styles, 8 logo/icon modes, covers, visuals, and b…

🧪 Tried in our test, no picture. Waits for a person first: must have a person pick a style in a separate plugin first.
git clone https://github.com/izscc/cc2image.git ~/.agents/skills/zscc配图生成器
57 xhs-writer-skill by JuneYaooo
★ 194 GPT Image

Xiaohongshu post generator based on gpt-image-2, with natural-language editing.

🧪 Image test, 2026-11-08: A social-card layout; left out the price line and the last Chinese line. · made all six but broke a rule: 4 of 6 poster lines right; all six 2:3 · close to the no-skill set · 9.0 min · 21 image calls ($0.18) · See the six pictures →
git clone https://github.com/JuneYaooo/xhs-writer-skill.git
★ 193 GPT Image

🧪 Image test, 2026-11-08: made all six but broke a rule: all six 16:9 · a look of its own · 3.1 min · 6 image calls ($0.05) · See the six pictures →
59 mcp-image by shinpr
★ 190 MCP servers

MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.

npx mcp-image skills install --path <target-directory>
60 design-buddy by SpaceZephyr
★ 189 Design assets

Design Buddy: visual production Agent Skills for brand design systems, GPT-image-2 images, diagrams, infographics, logos, slide decks, WeChat layouts and social images

npx skills add SpaceZephyr/design-buddy
61 eterna-image2image-skill by Cuimao777
★ 186 GPT Image

Experimental bilingual Codex skill for ETERNA-inspired image2image cinematic color and composition.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.1 min · 8 image calls ($0.07) · See the six pictures →
62 god-tibo-imagen by NomaDamas
★ 185 GPT Image

Python & Node package to use GPT image 2.0 model via codex subscription

npm install -g god-tibo-imagen
63 workrally by Tencent
★ 184 MCP servers

A full-process toolkit for AI Agent AIGC comic video creation.

npm install -g workrally
64 wibi-style by Vieeeeeee
★ 184 GPT Image

47 installable visual-design skills for Codex, with reusable Python tooling and versioned packages. Turn photos into artwork. Try online: style.abdc.online

🧪 Tried in our test, no picture. Does another job, not pictures from a brief: restyles a photo you give it, and its licence is non-commercial only.
65 gpt-image-skill by GENEXIS-AI
★ 184 MCP servers

Generate GPT images from Codex or Claude Code using a ChatGPT subscription, without the Images API.

66 scumble by DenRakEiw
★ 181 Image editing

Free, open-source desktop editor for AI inpainting: select, prompt, get a colour-matched layer. FLUX 3 Image, FLUX.2, GPT Image, Nano Banana, Seedream and Qwen through your API key or your own ComfyUI. Layers, PSD export, MCP.

67 flyreq-image-studio by doudou770
★ 170 MCP servers

AI image/video workbench: Agent/workbench modes, infinite canvas, assets, prompt reverse search/plaza, PWA, external config, Grok, GPT Image 2, mobile.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 8.9 min · 7 image calls ($0.06) · See the six pictures →
git clone https://github.com/doudou770/flyreq-image-studio.git
68 codex-canvas by Xiangyu-CAS
★ 164 GPT Image

Infinite canvas plugin for codex; Codex无限画布插件,图层分离,涂抹修改

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.2 min · 8 image calls ($0.07) · See the six pictures →
Quick Start: Copy this prompt into Codex: See the full installation guide in . Stable versions ship through GitHub Releases. Settings → Version only installs a rel...
Please install Codex-Canvas according to https://github.com/Xiangyu-CAS/codex-canvas.git and its INSTALL.md.
After installation, tell the user to start a new Codex task and type `@Codex-Canvas open the codex canvas`.
69 ecommerce-image-skills by xianyu110
★ 162 GPT Image

12 电商出图 Agent Skills for Claude Code / Codex / Cursor · GPT Image 2.5 (Flare/Sunburst) · Amazon 白底主图, A+, 场景图, 模特图, 小红书封面, 淘宝详情页

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.5 min · 8 image calls ($0.07) · See the six pictures →
npx skills add xianyu110/ecommerce-image-skills
70 codex-image2-skill by fengfengzhidao
★ 156 GPT Image

A skill for generating images in Codex

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.9 min · 6 image calls ($0.05) · See the six pictures →
git clone https://github.com/fengfengzhidao/codex-image2-skill.git
71 gpt-image-2-skill by Wangnov
★ 147 GPT Image

GPT Image 2 Skill / CLI / Web / Desktop

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.0 min · 6 image calls ($0.05) · See the six pictures →
cargo install gpt-image-2-skill --locked
72 qiaomu-codex-imagegen by joeseesun
★ 140 MCP servers

让任何 Agent 调用 Codex 内置生图(MCP + CLI + Skill),内置小红书、视频封面、Mondo 海报技巧 · Codex image generation for any agent

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.3 min · 6 image calls ($0.05) · See the six pictures →
npx skills add joeseesun/qiaomu-codex-imagegen
73 ComfyUI-AnimaTool by Moeblack
★ 140 MCP servers

AI Tool Use API for Anima anime/illustration image generation. Supports MCP Server, HTTP API, and CLI.

git clone https://github.com/Moeblack/ComfyUI-AnimaTool.git
74 skills by black-forest-labs
★ 137 Open models

Official agent skills from Black Forest Labs for FLUX image and video generation — prompting guides and API integration patterns for Claude Code, Codex, and any agentskills.io-compatible agent.

npx skills add black-forest-labs/skills
75 codex-imagen by darkamenosa
★ 135 GPT Image

Codex/OpenClaw skill for generating images with ChatGPT/Codex OAuth

🧪 Tried in our test, no picture. Works only with its own service or account: needs a ChatGPT or Codex sign-in; it does not take an API key.
76 comfy-colab-kit by FireTable
★ 131 Open models

Zero-GPU-idle gateway for running ComfyUI on ephemeral Google Colab VMs with Zero-Trust Access

77 z-image-studio by iconben
★ 128 MCP servers

A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)

uv tool install git+https://github.com/iconben/z-image-studio.git
78 photo-abstract-editorial by kwhi6693-web
★ 128 MCP servers

Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity composition path.

79 fantasy-dongfang-jianyuehaibao by dacnay816y62-hub
★ 126 GPT Image

Eastern culture editorial poster v2 Codex skill: Image 2 generation, concise Chinese titles, authentic cultural artifacts, A/B/C triptych testing

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.7 min · 7 image calls ($0.06) · See the six pictures →
80 opencode-gpt-imagegen by yuji-hatakeyama
★ 126 GPT Image

OpenCode plugin: image generation via your ChatGPT subscription

81 fantasy-qiqiguaiguai-skill by dacnay816y62-hub
★ 125 Design assets

FANTASY-qiqiguaiguai Codex skill for funny editorial social posts, 3:4 posters, collage, street snapshots, pets, travel and Chinese typography.

🧪 Image test, 2026-11-08: Big-type posters; added lines of its own on the poster, the bag and the mascots. · made all six but broke a rule: 5 not square; extra text on the poster; text on the mascot pictures · a look of its own · 8.0 min · 15 image calls ($0.13) · See the six pictures →
★ 124 Open models

Natural language → ComfyUI workflow JSON. 34 built-in templates, 360+ node definitions, auto model download. Supports txt2img, img2img, txt2vid, img2vid, audio, 3D generation across SD1.5/SDXL/SD3/FLUX/Wan2.2/HunyuanVideo/LTXV/Mochi/Cosmos + LLM integration. Works as a skill for Claude Code, Cursor, and other AI coding agents.

git clone https://github.com/twwch/comfyui-workflow-skill.git ~/codes/comfyui-workflow-skill
83 ComfyUI-Agent-Kit by SlavaSexton
★ 123 MCP servers

One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt recipes, 581 templates, plus standalone Seedance, Krea and MiniMax H3 skills. Hardware-aware selection, workflow building, multi-shot video, ControlNet, HDR. By Chronicle of Brothers.

git clone https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git
84 c2c_img by actionow-ai
★ 123 GPT Image

Native-feeling image generation for Claude Code, powered by your local Codex (ChatGPT) image_gen. No API key needed.

/plugin marketplace add actionow-ai/c2c_img
85 xhs-imagen by NimaChu
★ 121 Design assets

Skill for popular science image content creation on Xiaohongshu

🧪 Image test, 2026-11-08: made all six but broke a rule: 5 not square; text on the mascot pictures · a look of its own · 5.7 min · 7 image calls ($0.06) · See the six pictures →
git clone https://github.com/NimaChu/xhs-imagen.git
86 comfyui-agent-skill by MieMieeeee
★ 119 Open models

Enable agents to run registered ComfyUI workflows through a local ComfyUI server using this repo’s CLI, returning structured JSON outputs.

pipx install comfyui-agent-skill-mie
87 comfy-webui by RioShiina47
★ 117 MCP servers

A recipe-driven WaaS platform for ComfyUI that turns complex workflows (Image, Audio, Video, 3D) into intuitive Gradio UIs, high-level semantic APIs, and MCP tools for LLMs & AI Agents.

88 claude-image-generation by hassancs91
★ 115 MCP servers

Connect Claude to image generation with Agent Skills. Three levels: a zero-cost code-based design engine, a Three.js 3D renderer, and a real diffusion model on Cloudflare. Plus an AI Storybook pipeline that turns a plain-English story into an illustrated, narrated HTML book.

89 Phil-design-skills by FANzR-arch
★ 111 GPT Image

19 visual-style skills for gpt-image-2 that turn articles, topics, products, or existing visual assets into complete prompts.

90 api-image by yc-duan
★ 109 GPT Image

Codex skill for API-based image generation through OpenAI-compatible providers

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.4 min · 7 image calls ($0.06) · See the six pictures →
91 paper-signal by jiahuiqu17
★ 109 Design assets

Subject-aware minimal-zine image production for Agent Skills: art direction, generation, series, evidence, and real-bitmap QA.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.3 min · 7 image calls ($0.06) · See the six pictures →
npx skills add jiahuiqu17/paper-signal
92 codexQIYU-image-workflow by QIYU-JACKMAN
★ 109 GPT Image

Codex plugin for cross-border ecommerce images: 8 workflows, GPT Image 2 prompt optimization, approval, per-image checks, and resumable runs.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 6.1 min · 6 image calls ($0.05) · See the six pictures →
93 oil-visual by oil-oil
★ 106 Design assets

Create explanatory diagrams and transparent character illustrations in a consistent comic ink-line style for concepts, processes, comparisons, and articles.

npx skills add oil-oil/oil-visual
94 replicate-flux-mcp by awkoy
★ 106 MCP servers

MCP for Replicate Flux Model - A powerful tool for generating customized images and SVG assets that match specific coding vibes and aesthetic styles. Streamline your visual asset creation process with AI-powered design generation tailored for developers.

git clone https://github.com/awkoy/replicate-flux-mcp.git
95 voxel-icon by BIAsia
★ 105 Design assets

Voxel Icon — 30 free PNG icons plus a self-contained Codex skill for low-density isometric voxel art

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · a look of its own · 4.7 min · 8 image calls ($0.07) · See the six pictures →
npx skills add BIAsia/voxel-icon
96 higgsfield-mcp-unified by Hikhakk
★ 105 MCP servers

Local-first MCP server for the Higgsfield AI API: 85 typed image & video models (Seedance 2.5, Kling 3.0, Wan 3, Genjutsu, Soul, Cinema Studio), webhooks, cost estimates, Soul ID training. Opt-in web backend for Sora 2, Veo 3, Nano Banana.

uvx --from higgsfield-mcp-unified higgsfield-mcp # starts the stdio MCP server
★ 104 MCP servers

Open-source ai image generator skill and ai video generator skill for Codex, Claude Code, OpenClaw, Cursor, and more. Powered by CyberBara API with Nano Banana, Sora 2, Seedance, and Kling support. No need to master prompt, this skill optimize your prompt for all kinds of creations like slides, anime and much more.

npx skills add ZeroLu/Ultimate-AI-Media-Generator-Skill --list
98 agent-meme-forge by lisamsung
★ 99 Open models

Codex skill that turns one image or text concept into a WeChat-ready Chinese sticker pack people will actually send. Sendability-gated, 4-keypose → 16-frame, no model-drawn text.

git clone https://github.com/lisamsung/agent-meme-forge.git
99 xiaohongshu-skills by freestylefly
★ 98 Design assets

Xiaohongshu skill that generates cover images from user-defined topics using the Nano Banana Pro image-generation model.

100 codex-image-context-runtime by shixinnt
★ 97 MCP servers

A Codex plugin and local MCP runtime for context-bounded image generation and inspection.

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 2:3 · close to the no-skill set · 3.1 min · 6 image calls ($0.05) · See the six pictures →
101 skills by CaliCastle
★ 97 Design assets

A collection of Agent Skills by Cali Castle.

🧪 Image test, 2026-11-08: A chalkboard look; the poster carries the shop name and none of the other five lines. · made all six but broke a rule: 1 of 6 poster lines right; the mascots less alike (judge 4/5) · a look of its own · 8.1 min · 15 image calls ($0.13) · See the six pictures →
npx skills add CaliCastle/skills --skill signal-geometry
102 ComfyUI-Expert by MCKRUZ
★ 94 Open models

Session-scoped Claude Code agent for ComfyUI video production — 12 specialized skills for image gen, video, voice cloning, LoRA training, and publishing

git clone https://github.com/MCKRUZ/ComfyUI-Expert.git
103 gpt-image-2-mcp by lownamlee
★ 94 GPT Image

Local MCP server for ChatGPT image generation.

104 muted-zine-poster-v01 by moonlin1213
★ 90 Design assets

A muted, poetic paper-poster Agent Skill for low-saturation zine-style image generation.

🧪 Image test, 2026-11-08: A muted zine look on 9:16 pages, with the mascot's name on its pictures. · made all six but broke a rule: all six 9:16; text on the mascot pictures · a look of its own · 3.4 min · 7 image calls ($0.06) · See the six pictures →
105 claude-image by jiangmuran
★ 88 GPT Image

教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — intent-first prompting, surgical edits, parallel batching, visual self-verification

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.5 min · 6 image calls ($0.05) · See the six pictures →
git clone https://github.com/jiangmuran/claude-image.git
106 PaperBanana-CN by mituan-ai
★ 85 MCP servers

Scientific figure workbench with independent VLM/image connections, Chinese UI, and unified size controls.

🧪 Image test, 2026-11-08: A pipeline for research-paper figures: 3 pictures in 20 minutes. · 3 of the 6 pictures in 20 minutes · 20.1 min · 3 image calls ($0.04) · See the six pictures →
uvx paperbanana-cn studio
107 scene-card-studio by swping999
★ 85 Open models

AI visual director for turning personal photos into structured, editable visual narratives.

git clone https://github.com/swping999/scene-card-studio.git
108 DJZ-Nodes by MushroomFleet
★ 81 Open models

Custom nodes for ComfyUI — video effects, batch processing, prompt tools, image manipulation & automation utilities

git clone https://github.com/MushroomFleet/DJZ-Nodes
109 claude-image-gen by guinacio
★ 80 MCP servers

AI-powered image generation using Google Gemini or OpenAI (gpt-image-2), integrated with Claude Code via Skills or Claude.ai via MCP (Model Context Protocol).

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.8 min · 9 image calls ($0.11) · See the six pictures →
/plugin marketplace add guinacio/claude-image-gen
110 visual-explainer-skill by ericblue
★ 80 GPT Image

A Claude Code skill that transforms any content or Mermaid diagram into stunning visual explanations — whiteboard sketches, infographics, mind maps, and more — powered by OpenAI or Gemini image generation.

111 piapi-mcp-server by apinetwork
★ 76 MCP servers

A TypeScript implementation of a Model Context Protocol (MCP) server that integrates with PiAPI's API. PiAPI makes user able to generate media content with Midjourney/Flux/Kling/LumaLabs/Udio/Chrip/Trellis directly from Claude or any other MCP-compatible apps.

npx -y @smithery/cli install piapi-mcp-server --client claude
112 bria-skill by Bria-AI
★ 75 MCP servers

Claude Code skills for Bria AI - generate, edit, and transform images with Fibo, RMBG-2.0, and VGL structured prompts

🧪 Tried in our test, no picture. Works only with its own service or account: needs a Bria API key.
npx skills add bria-ai/bria-skill
113 awesome-ppt-skills by stevenjinlong
★ 75 GPT Image

Turn a prompt into polished, full-slide PPT decks with gpt-image-2. 把一句提示词转换成由 gpt-image-2 生成的、精美完整的整页式 PPT 演示文稿。

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 1:1; text on the mascot pictures · close to the no-skill set · 3.8 min · 8 image calls ($0.07) · See the six pictures →
git clone https://github.com/stevenjinlong/awesome-ppt-skills.git
114 gpt-image-2-skill by robonuggets
★ 74 GPT Image

GPT Image 2 (ChatGPT Images 2.0) skill for Claude Code — best-in-class typography, two endpoints (T2I + edit), Fal AI integration, structured-JSON prompting patterns

Quick Start: Install the skill Copy the file to your Claude Code project's directory. Add your Fal AI key Get a key at fal.ai/dashboard/keys. Generate Tell Claude ...
echo "FAL_KEY=your-fal-ai-key" >> .env
115 ComfyUI-IF_Gemini by if-ai
★ 73 Nano Banana & Gemini

New nANO-Banana Google Gemini API for ComfyUI generate images, transcribe audio, sumarize videos. Making a separate implemetation of my old IF_AI tools for easy installation

git clone https://github.com/if-ai/ComfyUI-IF_Gemini
116 xxd-panel-028 by nevertoday
★ 72 GPT Image

Turn photographs into quiet source-colour isometric paper miniatures with four combinable output modes.

🧪 Image test, 2026-11-08: Built to turn photos into isometric paper miniatures; from the brief alone it staged the mascot in a tiny bakery stall. · followed the brief: all six pictures, all text right, formats as asked · a look of its own · 4.6 min · 12 image calls ($0.10) · See the six pictures →
git clone https://github.com/nevertoday/xxd-panel-028.git
117 nano-banana-skills by ShinChven
★ 72 Nano Banana & Gemini

Nano Banana Pro Skills

🧪 Tried in our test, no picture. Does another job, not pictures from a brief: needs existing pictures of the character; makes a three-view sheet.
118 codex-gpt-image by ningzimu
★ 71 GPT Image

OpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required

🧪 Tried in our test, no picture. Works only with its own service or account: needs a Codex sign-in and says not to use an API key.
119 image-gen-mcp by lansespirit
★ 69 MCP servers

An MCP server that integrates with gpt-image-1 & Gemini imagen4 model for text-to-image generation services

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 2:3 · close to the no-skill set · 9.1 min · 14 image calls ($0.12) · See the six pictures →
120 regional-culture-poster by dacnay816y62-hub
★ 69 Design assets

Translate Chinese regional culture into restrained contemporary large-type and editorial posters, not tourism promotion.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · a look of its own · 3.6 min · 6 image calls ($0.05) · See the six pictures →
git clone https://github.com/dacnay816y62-hub/regional-culture-poster.git ~/.agents/skills/regional-culture-poster
121 gemini-webapi-mcp by AndyShaman
★ 66 MCP servers

MCP server for Google Gemini — free image generation, editing & chat via browser cookies. No API keys needed.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a signed-in Gemini web session (browser cookies).
git clone https://github.com/AndyShaman/gemini-webapi-mcp.git
122 codex-image by wjb127
★ 66 GPT Image

Claude Code skill for AI image generation via Codex CLI OAuth (gpt-image-2) / Codex CLI OAuth를 통한 AI 이미지 생성 Claude Code 스킬

git clone https://github.com/wjb127/codex-image.git ~/.claude/skills/codex-image
123 PotionUI by PotionUI
★ 65 Open models

Self-hosted AI studio for images, video and music on your own GPU. Multi-user with logins and limits, no node graphs, drivable over MCP.

git clone https://github.com/PotionUI/PotionUI.git potionui && cd potionui
★ 63 MCP servers

Standalone Skill and Codex Plugin for OpenAI-compatible image generation, editing, batch workflows, QA, and focused canvas editing.

125 NanoBananaASO by chawlaaditya
★ 61 Nano Banana & Gemini

Nano Banana App Store Screenshot Skill

🧪 Image test, 2026-11-08: made all six but broke a rule: 5 not square · close to the no-skill set · 6.8 min · 8 image calls ($0.11) · See the six pictures →
npx skills add chawlaaditya/NanoBananaASO
126 mold by utensils
★ 57 MCP servers

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, REST/SSE, and MCP.

127 gpt-image-2-gen-skill by EvoLinkAI
★ 56 GPT Image

GPT Image 2 AI image generation skill for OpenClaw, Claude Code, OpenCode, and Cursor - one command install

128 mcp by runapi-ai
★ 56 MCP servers

RunAPI MCP server for model discovery, pricing lookup, media task creation, and balance checks.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a RunAPI account.
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
129 gpt-image-2-prompting-skill by zhouwei713
★ 56 GPT Image

A high-quality GPT-Image-2 prompting skill with bilingual README, structured prompting methods, templates, and examples.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.2 min · 7 image calls ($0.06) · See the six pictures →
130 zimage-skill by yizhiyanhua-ai
★ 52 MCP servers

Z-Image Skill - AI Image Generation for Claude Code | 用自然语言生成 AI 图片的 Claude Code 技能

Quick Start: All steps can be completed using natural language in Claude Code - no manual commands needed! Step 1: Get Your Free API Key Visit ModelScope Click "Lo...
Install zimage-skill from https://github.com/yizhiyanhua-ai/zimage-skill
131 mediagen by Cripacx
★ 50 MCP servers

AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with EU AI Act content marking.

npx -y mediagen mark ./output/hero.jpg --visible-label
132 skills by awesome-genmedia
★ 48 MCP servers

Awesome skills for AI image generation, video generation, song generation and more!

133 codex-image-in-cc by KingGyuSuh
★ 47 GPT Image

Claude Code plugin that exposes Codex CLI's built-in imagegen skill as /codex-image:* user-invoked slash commands.

134 agnes-ai-skill by jomeswang
★ 47 MCP servers

Agnes AI skill for text, image, and video APIs with persistent auth and OpenAI-style workflows

🧪 Tried in our test, no picture. Works only with its own service or account: needs an Agnes API key.
135 Picxel by See-Sol-Lab
★ 45 GPT Image

Turn reference images into pixel-art game assets,for indie game developers.

136 Generative-Media-Skills by SamurAIGPT
★ 44 MCP servers

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a MuAPI account and key.
137 multi-style-image-generator by shengjidaguai-china
★ 43 Open models

Codex skill with game-inspired and crochet style templates, plus 2D, 360° panorama, spatial-depth, colored point-cloud, and video workflows.

★ 41 GPT Image

Agent Skill for creating BioRender-inspired, publication-quality biomedical mechanism figure prompts for GPT Image, Codex, Claude Code, and OpenCode.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.3 min · 7 image calls ($0.06) · See the six pictures →
★ 41 GPT Image

A policy-aware Codex skill that turns product photos into platform-adapted e-commerce detail pages with modular image generation, deterministic typography, slicing, manifests, and validation.

🧪 Tried in our test, no picture. Waits for a person first: asks for missing shop details before drawing, and makes text-free product shots only.
140 sci-figure-workflow by james20141606
★ 41 GPT Image

Claude Code Skill: AIGC 科研绘图 4 步工作流(GPT-image-2 × Gemini Vision × Nano Banana 2 × draw.io)— 把顶会论文配图从半天压缩到 10 分钟,产出可编辑 .drawio/.pptx/.svg

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · a look of its own · 7.8 min · 6 image calls ($0.05) · See the six pictures →
141 image-inspirer by wukongnotnull
★ 41 GPT Image

灵感绘.skill: A tested library of GPT-Image2 image prompt examples covering 13 categories, for AI image ideas and creative reference.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.5 min · 7 image calls ($0.06) · See the six pictures →
142 custom-icons-skill by JKc66
★ 41 Design assets

skill to create custom icons using IDEs or extentions that have image generation support

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 1:1 · close to the no-skill set · 4.7 min · 7 image calls ($0.06) · See the six pictures →
143 image-prompt-studio by liangdabiao
★ 41 MCP servers

Skill for image-style replication and generation with structured JSON prompts, not long prose, for Nano Banana and GPT-Image; apiz-cli generates, runtime agent…

144 antibanana-mcp by awei84
★ 40 MCP servers

MCP server for Google Antigravity image generation

🧪 Tried in our test, no picture. Works only with its own service or account: needs Antigravity credentials.
145 aiChatGptAgent by boteSu
★ 40 GPT Image

ChatGPT image generation/editing: OpenAI-compatible API, studio, account pools, signup, logs/images, Docker self-hosting, gpt-image-2/codex-gpt-image-2.

🧪 Tried in our test, no picture. Works only with its own service or account: needs ChatGPT web accounts, which it offers to mass-register: against OpenAI's terms, so not done.
146 imagegen-mcp by spartanz51
★ 37 MCP servers

MCP server for OpenAI Image Generation & Editing — text-to-image, image-to-image (with mask), no extra plugins.

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 2:3 · close to the no-skill set · 6.0 min · 6 image calls ($0.05) · See the six pictures →
147 FigFox-Gen-skill by LawrenceRiver
★ 35 MCP servers

Scientific paper figure generation Skill for agents: web research-figure conventions, controlled colour, topology planning, and image generation. 科研论文图生成 Skill:联网参考、配色与拓扑规划。

★ 34 Nano Banana & Gemini

MCP server for AI image generation and editing using Google's Gemini Flash models. Create images from text prompts with intelligent filename generation and strict text exclusion. Supports text-to-image generation with future expansion to image editing capabilities.

🧪 Image test, 2026-11-08: 23 image calls and no text on any picture. · made all six but broke a rule: 0 of 6 poster lines right; the shop name on the bag wrong or missing; poster 1:1 · close to the no-skill set · 10.3 min · 23 image calls ($0.28) · See the six pictures →
★ 34 Open models

Codex skill for director-level Eastern beauty AI image prompts, covering gu feng, Eastern fantasy, modern Chinese aesthetics, SweetHomeGirl lifestyle portraits, prompt routing, style systems, and image-generation-ready prompts.

150 digital-human-koubo-comfyuiNEW by walkskysu
★ 34 Open models

一张照片生成 AI 数字人口播:本地 ComfyUI 全流程(Qwen3-TTS 克隆声音 + MiniMax H3 对口型 + Qwen Image + Music 3),不花积分;5 种剪辑风格 + 48 个博主级包装组件。AI digital-human talking-head videos from one photo, generated locally with ComfyUI (Qwen3-TTS + MiniMax H3 lip sync), no credits. Agent skill for Claude Code / Codex / OpenClaw / WorkBuddy …

151 SCOPE by nopnor
★ 33 GPT Image

Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation

🧪 Tried in our test, no picture. Works only with its own service or account: needs a JD Cloud account.
152 gen-images-skill by dancolta
★ 32 Nano Banana & Gemini

Context-aware image generation skill for Claude Code — analyzes website brand identity and generates on-brand images via Gemini MCP

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 6.8 min · 7 image calls ($0.09) · See the six pictures →
153 codex-image by IanShaw027
★ 32 GPT Image

Codex skill for OpenAI Images API generation and editing in API key mode

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.5 min · 7 image calls ($0.06) · See the six pictures →
154 30x-image by norahe0304-art
★ 32 GPT Image

Generates on-brand marketing imagery (ad creatives, logos, slides, carousels) from a brand DESIGN.md via gpt-image-2 — a Codex / Claude Code skill.

155 nanobanana-mcp by YCSE
★ 32 Nano Banana & Gemini

Gemini Vision & Image Generation MCP for Claude Desktop and Claude Code

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 7.8 min · 6 image calls ($0.07) · See the six pictures →
156 product-motion-gif by liangdabiao
★ 30 GPT Image

Send a product photo; this skill uses GPT-Image 2.5 to generate frames and a looping product GIF in one call. No design or technical skills needed.

157 ccskill-nanobanana by feedtailor
★ 29 Nano Banana & Gemini

Claude Code skill for AI image generation using Nano Banana Pro

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.6 min · 6 image calls ($0.07) · See the six pictures →
158 huashu-gpt-image by alchaincyf
★ 29 GPT Image

GPT-image-2 prompt engineering methods: use real reference names instead of adjectives, default to short Chinese prompts. Includes single-image, batch-grid, an…

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.5 min · 7 image calls ($0.06) · See the six pictures →
159 ai-pixel-art-image-generation by ianlintner
★ 26 GPT Image

AI Claude Code Skill: GPT-Image-2, Foundry, Gemini Game Development Pixel Art, Sprite & Tilemap Image Generation

🧪 Image test, 2026-11-08: Despite the name, the same photo and 3D look as Claude Code with no skill; the fastest here at 1.6 minutes. · followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 1.6 min · 6 image calls ($0.05) · See the six pictures →
160 huashu-slide-codex by alchaincyf
★ 25 GPT Image

Codex-only AI visual material production skill — slides + WeChat covers + Bilibili/YouTube thumbnails, powered by built-in image_gen (no API fees)

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 10.1 min · 8 image calls ($0.07) · See the six pictures →
161 gpt-image-2-5-agent-kit by AlekseiUL
★ 25 GPT Image

GPT Image 2.5 Sunburst & Flare toolkit for agents: generation, reference and masked edits, PNG/JPEG/WebP, dry-runs and validated receipts. Experimental ChatGPT/Codex backend.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.4 min · 6 image calls ($0.05) · See the six pictures →
162 ip-character-designer by Beatatata
★ 24 Design assets

🎨 自媒体 IP 配图生成器 — 10种画风 × 双版本输出 × 中文提示词 | Cola/Claude Skill for IP image generation with Dreamina

163 remote-imagegen by stevenjinlong
★ 24 MCP servers

适用于自定义 OpenAI 兼容 base_url 的 Codex 独立生图 skill,支持文生图与参考图编辑,并可自动从本地 Codex 配置中读取 URL 和 API Key。 An independent Codex image-generation skill for custom OpenAI-compatible base_url setups, supporting text-to-image and reference-image editing while automatically loading the endpoint URL and API key from the local Codex configuration.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.4 min · 7 image calls ($0.06) · See the six pictures →
164 claude-skill-codex-imagegen by JunSeo99
★ 22 GPT Image

Generate, compare, and edit images in Claude Code using your Codex subscription. Background jobs, parallel drafts, and lean context. No image API bill.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.2 min · 7 image calls ($0.06) · See the six pictures →
165 gpt-image-2-skill by dshark3y
★ 19 GPT Image

Claude Code skill for generating and editing images with OpenAI's gpt-image-2

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.4 min · 6 image calls ($0.05) · See the six pictures →
166 museav-mcp by webkubor
★ 19 MCP servers

CS system (CortexOS) MCP — one agent service that strings a personal open-source toolchain together: image generation, local vision, contrast gating, Markdown typesetting. Capability groups: a group's tools appear only when its CLI is installed.

167 flux-mcp by black-forest-labs
★ 18 MCP servers

Official FLUX MCP server. Generate, edit, vary, and browse FLUX images from any MCP client.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a Black Forest Labs account (the hosted official MCP).
168 ai-hive-agent-skills by wubin1836
★ 18 MCP servers

680个AI-HIVE Agent Skills:新增340个AI大模型专家中文技能,覆盖Seedance、Nano Banana、GPT Image 2、Seedream、MiniMax、电商图片视频、广告营销与AIGC工作流。

169 gpt-image-1-mcp by CLOUDWERX-DEV
★ 18 GPT Image

A Model Context Protocol (MCP) server for generating and editing images using the OpenAI gpt-image-1 model.

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 2:3 · close to the no-skill set · 6.8 min · 6 image calls ($0.05) · See the six pictures →
170 scientific-visual-skills by 2023Anita
★ 17 GPT Image

Codex skills for scientific infographics, research cover visuals, and publication-grade paper figures using ChatGPT image generation.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.7 min · 7 image calls ($0.06) · See the six pictures →
171 nano-banana-pro-mcp by mrafaeldie12
★ 17 MCP servers

MCP server for Gemini 3 Nano Banana Pro image generation

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.5 min · 6 image calls ($0.08) · See the six pictures →
172 NexcoreMultimodalSkill by yan-stone-computer
★ 17 MCP servers

NexcoreVision OCR + CNN + VLM evidence architecture, consent-gated local ComfyUI/Qwen deployment, and Agnes media generation in one Agent Skill.

★ 16 Design assets

Use Codex + GPT Image 2 to generate minimalist Anthropic-style cover images directly from article content.

🧪 Image test, 2026-11-08: made all six but broke a rule: all six 5:2; text on the mascot pictures; the mascots less alike (judge 4/5) · a look of its own · 3.0 min · 6 image calls ($0.05) · See the six pictures →
174 Derekwen-aigc-visual-skills by derekwalldevin-wen
★ 16 Open models

Open-source AIGC visual workflows, reusable Agent Skills and real image-generation cases by DerekWen.

175 higgsfield-studio by avenoxai
★ 16 MCP servers

Claude Code + Higgsfield ile görsel/video üretim skill'leri — GPT Image 2, Seedance loop'ları, sunum sitesi

176 gpt-image2-layered-psd by JongLeePc
★ 15 GPT Image

Codex skill for image-to-layered-PSD workflows with confirmed single-element extraction

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.0 min · 6 image calls ($0.05) · See the six pictures →
177 gpt-image-2-studio by KDB-Wind
★ 15 GPT Image

轻量 GPT-Image-2 生图工作台,特别支持批量调用 GPT-Image-2:支持 AI 拆分提示词、队列、重试和图生图 / Lightweight GPT-Image-2 studio with batch calls, AI prompt splitting, queueing, retries, and image-to-image.

178 style-prompt-forger-skill by Andy20010101
★ 14 GPT Image

Codex/OMX skill for Gemini-to-GPT image style prompt forging

🧪 Tried in our test, no picture. Does another job, not pictures from a brief: writes reusable style prompts, not pictures.
179 nano-banana-claude-plugin by Ibrahim-3d
★ 14 Nano Banana & Gemini

Nano Banana - AI image generation plugin for Claude Code. 13 modes: text-to-image, editing, style transfer, inpainting, 4K, search grounding. Powered by Google Gemini API.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.6 min · 6 image calls ($0.07) · See the six pictures →
180 GPT-upscale-skills by AKRTR465
★ 14 Image editing

An image upscaling workflow skill based on GPT-6-astra and gpt-image-2.5

181 ultimate-image-gen-mcp by nikships
★ 14 Nano Banana & Gemini

Ultimate Gemini 3.1 Flash Image MCP server with 4K generation, Google Search grounding, reference images (up to 14), and thinking mode. Professional image generation made simple.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 5.5 min · 7 image calls ($0.10) · See the six pictures →
★ 14 GPT Image

A Codex skill for planning, generating, evaluating, and refining enterprise architecture diagrams with GPT Image 2.

🧪 Tried in our test, no picture. Does another job, not pictures from a brief: draws architecture diagrams only.
183 imagegen-mac by ph1lb4
★ 13 MCP servers

Local AI image generation for Mac. Run Qwen-Image 2.1 on Apple Silicon, offline and private, with a built-in MCP server for Claude Code and AI agents.

184 NanoBanana-PPT-Skills by xj-bear
★ 13 Nano Banana & Gemini

NanoBanana PPT Skills - AI-powered PPT generator with Veo support

185 nano-banana by v587d
★ 13 Nano Banana & Gemini

NanoBanana — Gemini Image Generator Skill for AI Agents

186 sub2api-4k-image-generator-ts by fengyunzaidushi
★ 12 GPT Image

Codex skill and TypeScript CLI for 4K AI image generation through self-hosted sub2api OpenAI-compatible endpoints, with streaming, SSE, partial image capture, and Cloudflare 524 timeout mitigation.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 5.2 min · 10 image calls ($0.09) · See the six pictures →
187 NovelAI-Image-MCP by xinvxueyuan
★ 12 MCP servers

MCP server for integrating NovelAI Image generation into AI agents.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a NovelAI account.
188 nan-mcp-server by luciferfran
★ 12 MCP servers

MCP server exposing NaN API media tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank

🧪 Tried in our test, no picture. Works only with its own service or account: needs a NaN API key.
★ 12 GPT Image

Codex skill for GPT Image 2.5 prompt writing, editing and reference-image workflows. Based on official OpenAI guidance.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.0 min · 6 image calls ($0.05) · See the six pictures →
190 pushing-creation by PUSHINGSQUARES
★ 12 MCP servers

Cinematic prompt methodology for AI image and video generation. Install into Claude Code, author director-grade style packs and storyboards from your reference images. Output is markdown, drop-in compatible with PUSHING FRAMES.

191 dsh-pbr-material by zhangx413
★ 12 Open models

DeepSeek Harness plugin: a photo of a surface becomes a complete tileable PBR material set, fully local via ComfyUI (FLUX.2 Klein 4B instruction edit + deterministic PBR derivation). GUI workbench, five agent tools, and a setup tool that finds your ComfyUI and downloads its own weights.

192 claude-code-generate-images-mcp by TamerinTECH
★ 11 MCP servers

Auto generate and insert image assets during UI coding in Claude Code, using an MCP server for Azure OpenAI gpt-image-1 and Flux-1.1 Pro

🧪 Tried in our test, no picture. Works only with its own service or account: calls a retired Gemini 2.0 endpoint written into its code, or Azure OpenAI; our sandbox's relay did not serve that endpoint.
193 prompt-reverse-engineer-skill by niobium617
★ 11 Open models

多模态 Prompt 逆向工程 Skill:把文本/图片/视频/剧本拆解还原为可复用 Prompt,适配 Midjourney V8.2 / Stable Diffusion 3.5 / FLUX.2 / GPT Image 2.5(文生图·复刻·编辑·参考图·合成五模式)/ Nano Banana Pro / GPT-5.5·Claude 5.5 / DeepSeek V4.1 / Sora 2 / Runway Gen-4.5 / Veo 3.1 十种模型,支持 Claude Code / Cursor / Codex / DeepSeek Harness / 豆包五平台,附百分制六维评分(剧本可逐场景出图)

194 ai-logo-maker-skill by beatra-ai
★ 11 Design assets

AI logo maker agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn a brand name, industry, or reference image into logo concepts, brand marks, and app icons with exact brand colors. AI Logo设计 · 品牌标识

195 mcp-replicate-flux by andylee20014
★ 11 Open models

196 krea-mcp by keugenek
★ 10 MCP servers

MCP server for Krea.ai - Generate stunning AI images & videos with Flux, Hailuo, Runway, Kling, Ideogram, Imagen & more. Works with Claude Desktop, Claude Code, and any MCP client.

197 universal-image-mcp by Onward0131
★ 10 MCP servers

Provider-neutral image generation and editing MCP with a Codex Skill. Supports OpenAI Images, Gemini, and chat image APIs.

198 together-mcp-server by manascb1344
★ 10 Open models

MCP server enabling high-quality image generation via Together AI's Flux.1 Schnell model.

199 sub2api-gpt-image-2 by huysh3
★ 10 GPT Image

Fix the issue of being unable to generate images after codex sub2api.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.3 min · 7 image calls ($0.06) · See the six pictures →
200 gpt-image-2-ecommerce-skill by gpt-img-2
★ 10 GPT Image

GPT Image 2 ecommerce Skill for product-preserving main images, white-background product photos, PDP prompts, and QA|电商商品图 Agent 工作流

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.4 min · 7 image calls ($0.06) · See the six pictures →
201 jimeng-cli-skill by wallfacer005-vip
★ 10 MCP servers

Agent Skill for AI image/video generation via Dreamina (即梦) CLI

★ 9 MCP servers

AI storyboard generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn a script, scene, or ad brief into a practical shot list and a few storyboard key-frame images for film, ads, animation, and social video. AI分镜生成 · 分镜表

203 bold-contour-ink-portrait by chiyolyn
★ 9 Design assets

An image-generation skill for turning illustrated characters into bold, airy black-ink portraits on clean white. 借助这个图像生成 Skill,可以将单个插画角色转换为纯白底、轮廓有力且留白充足的纯黑墨人物线描。

🧪 Image test, 2026-11-08: Black ink line art: the red scarf came out black. · made all six but broke a rule: the mascots less alike (judge 4/5) · a look of its own · 4.5 min · 8 image calls ($0.07) · See the six pictures →
★ 9 GPT Image

gpt-image-2 images on your ChatGPT/Codex subscription — no API key, reference images supported. Claude Code skill.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.6 min · 7 image calls ($0.06) · See the six pictures →
205 artifex-mcp by jkalasas
★ 9 MCP servers

A vendor agnostic MCP server for AI image generation.

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 9:16 · close to the no-skill set · 3.1 min · 6 image calls ($0.05) · See the six pictures →
206 slopcore by obie
★ 9 GPT Image

A Claude Code skill and toolkit for making AI music videos from a finished song: Midjourney stills, Seedance clips, and every lyric drawn in code on the beat.

207 X2V-AI-Images-Videos-skill by xinyiqin
★ 8 MCP servers

[LightX2V](https://x2v.light-ai.top) integration for [OpenClaw](https://openclaw.ai) — image generation (t2i/i2i), video (t2v/i2v/s2v), TTS, and voice clone via cloud API.

208 nanobanana by skorfmann
★ 8 Nano Banana & Gemini

Lightweight CLI for AI image generation using Google Gemini API. Text-to-image, image editing, multi-image composition. Perfect for coding agents like Claude Code.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.8 min · 7 image calls ($0.10) · See the six pictures →
209 gpt-image by egoist
★ 8 GPT Image

A CLI and agent skill to work with gpt-image-2 using API key or subscription

210 design-bridge by missuo
★ 8 GPT Image

Design skill for crafting GPT image prompts and generating compact mockups.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.4 min · 8 image calls ($0.07) · See the six pictures →
211 creating-social-media-visuals by bushibohai
★ 8 GPT Image

Skill for generating covers and infographics for WeChat Official Accounts, Xiaohongshu, Douyin, and other social media platforms. Recommends GPT Image 2.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.0 min · 9 image calls ($0.08) · See the six pictures →
212 nano-banana-2-promptor-skill by thangphistudent
★ 8 Nano Banana & Gemini

Claude Code skill that generates optimized Nano Banana 2 (Gemini 3.1) image prompts for ecommerce, marketing, and print-on-demand design

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 5.9 min · 8 image calls ($0.14) · See the six pictures →
213 PaperBanana-AIMSLab by zhouzhq2021
★ 8 MCP servers

PaperBanana-AIMSLab generates academic figures from methods, captions, or chart intent; supports multi-Agent workflows, API switching, and image-to-image.

🧪 Image test, 2026-11-08: 48 image calls in 21 minutes, the most here; a 2:3 poster. · made all six but broke a rule: poster 2:3 · close to the no-skill set · 21.2 min · 48 image calls ($0.41) · See the six pictures →
214 ai-image-studio by Raines-01
★ 8 GPT Image

买了 gpt-image-2 中转 API 不知道怎么调用?启动即用,填入配置就能生图!A local web UI for image generation APIs — just plug in your API key and start creating.

215 dsh-image2-draw by JuneLearn
★ 8 GPT Image

DeepSeek Harness Image2 生图插件,通过第三方 OpenAI Images 兼容接口调用 gpt-image-2,只需配置 baseURL 和 API Key。 | Image2 generation plugin for DeepSeek Harness via third-party OpenAI Images-compatible APIs.

216 img2img-studio by Dogwind221
★ 8 MCP servers

Image-to-image studio: vision-gated routing + multi-provider generation (DashScope / ChatGPT-web / OpenAI / Z.AI / Doubao / MiniMax) with auto failover. E-commerce sets & photo-art styles. 图生图工作台 · 多供应商自动降级 · 电商套图与照片艺术

★ 7 GPT Image

Codex skill for academic slides, posters, proofsheets, and architecture diagrams via GPT Image 2

🧪 Image test, 2026-11-08: made all six but broke a rule: all six 16:9 · close to the no-skill set · 4.4 min · 7 image calls ($0.06) · See the six pictures →
218 gpt-image-cookbook by eugeniughelbur
★ 7 MCP servers

Multi-provider AI image generation cookbook: prompt gallery, agentic skill, and CLI for OpenAI gpt-image-2, Google Imagen, Flux, and more. Claude Code plugin + Codex/OpenClaw skill + Python CLI.

219 zven-imagegen by zvensmoluya
★ 7 GPT Image

An image-generation skill for Codex that supports base_url + key and stream streaming to reduce long-connection timeouts and disconnects.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.2 min · 6 image calls ($0.05) · See the six pictures →
220 character-animation-skill by karem505
★ 7 Nano Banana & Gemini

Turn any character image into a looping animated sprite (moving SVG, WebP & GIF) with Google's Nano Banana 2 (gemini-3.1-flash-image) — a Claude Code skill.

🧪 Tried in our test, no picture. Does another job, not pictures from a brief: animates a character picture you give it.
221 codex-imagegen-mcp by ShalomObongo
★ 7 MCP servers

Codex's image generation in every coding agent: an MCP server + Agent Skill with a one-command installer for opencode, Claude Code, Codex, Cursor, VS Code, Gemini CLI and 20 more tools. Runs on your ChatGPT plan with no API key.

222 studiomcphub by metavolve-labs
★ 7 MCP servers

Creative AI MCP server — 32 tools (18 free): image generation, upscaling, bg removal, mockups, CMYK, print-ready PDF, vectorization, watermarking, enrichment, provenance. Pay per call via x402/Stripe/GCX.

🧪 Tried in our test, no picture. Works only with its own service or account: needs paid credits on its hosted server.
223 claude-custom-skills-demo by zackproser
★ 7 Nano Banana & Gemini

A custom skill to generate and then animate an image via Google's Gemini / Nano Banana and Veo models

🧪 Image test, 2026-11-08: made all six but broke a rule: poster 1:1 · close to the no-skill set · 3.7 min · 13 image calls ($0.16) · See the six pictures →
★ 7 MCP servers

Run any awesome-gpt-image-2 or Seedance prompt as a one-line Claude Code command. Pay per image with x402 USDC on Base via BlockRun.ai. v1: /headshot, /dance, /poster + 1010-case library.

🧪 Tried in our test, no picture. Works only with its own service or account: needs a funded BlockRun wallet (USDC on Base).
225 cli by AtlasCloudAI
★ 7 MCP servers

Generate AI images, videos, speech, and 3D assets from your terminal, Claude Code, or Codex with Atlas Cloud CLI.

226 PiAPI-Skills by wesleysimplicio
★ 6 MCP servers

Skill bundle for Claude, Codex, Hermes, OpenClaw, Cursor, Windsurf, and generic agents covering PiAPI (Midjourney, Suno, Kling, Flux, Hailuo, Luma, Hunyuan, Faceswap, Trellis 3D, MMAudio, F5-TTS, Veo 3, Gemini 2.5 Flash Image, Seedance, and the OpenAI-compatible LLM gateway).

227 imagegen-skills by veryCoolTimo
★ 6 GPT Image

Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-image-2. MIT.

228 codex-imagegen-free-reference by luckyabsoluter
★ 6 MCP servers

An extension of Image Gen skill in Codex, it gives you full control to explicitly choose your reference image

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.7 min · 7 image calls ($0.06) · See the six pictures →
229 image-first-frontend by jinshiqwq
★ 6 GPT Image

This is a frontend design skill specifically tailored for the Codex and GPT-5.6 series models, aiming to enhance the frontend design capabilities of the GPT series models. Through a customized GPT image-compatible API, user interface previews are generated and iterated, and then the approved designs are recreated as high-quality web pages.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 5.1 min · 6 image calls ($0.05) · See the six pictures →
230 generate-nanobanana by AntonioCardenas
★ 6 Nano Banana & Gemini

Claude Code skill for AI image & video generation with Google Gemini — Nano Banana 2 Lite, Nano Banana Pro, Gemini Omni Flash. Cost gates before paid runs, real reference images, a prompt log beside every file.

231 nano-banana-mcp by frannkurt
★ 6 Nano Banana & Gemini

Free AI image generation MCP server — no API key, no billing. Nano Banana via Google Flow with your own Google account. Exact pixel sizes, reference images, $0 per image.

232 jingzao-image-forge by papperrollinggery
★ 6 GPT Image

镜造 Image Forge — Codex Skill for reference-image distillation, character consistency and AI image generation: preserve hair, expression, pose, body, wardrobe and cinematography.

233 ai-media-generator-skill by beatra-ai
★ 6 MCP servers

AI media generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: create AI images, video, music, and voice-over, and look up public social data through one connection. AI内容创作 · 图片视频音乐配音生成

234 creative-claw-marketplace by CreativeClawCo
★ 6 MCP servers

Creative Claw: AI video, image and voiceover generation inside ChatGPT, Claude, Codex and Cursor. Seedance 2.5, Gemini Omni, Nano Banana 2, voice cloning. Pay as you go.

235 hermes-codex-image-skill by techkwon
★ 6 MCP servers

Stable local Codex image generation for Hermes/OpenClaw with predictable file output and JSON metadata.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.2 min · 7 image calls ($0.06) · See the six pictures →
236 deepseek-imagegen by dqtx760
★ 6 MCP servers

DeepSeek can generate images via an open-source skill and Python script: AI agents understand needs, extract visuals, using Apimart gpt-image-2.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.2 min · 6 image calls ($0.05) · See the six pictures →
237 flux-api-control-surface by koshimazaki
★ 6 MCP servers

Local control surface to explore FLUX API with additional tools and MCP

🧪 Tried in our test, no picture. Works only with its own service or account: needs a Black Forest Labs key in the macOS Keychain.
238 aigc-cli by martianzhang
★ 6 MCP servers

Terminal-native AIGC toolkit: multi-provider image/video/audio generation, Midjourney, chat, AIGC forensics, knowledge base, MCP Server. 终端原生 AIGC 工具包:多厂商图片/视频/音频生成、Midjourney、AI 对话、AIGC 取证、知识库、MCP 集成。

239 motion-skill by LunaAI519
★ 6 Nano Banana & Gemini

Claude Code skill: one reference image → retro scrapbook-style animated short video with Nano Banana keyframes, Kling image-to-video, and copyright checks.

240 image-gen-plugin by harshkedia177
★ 5 Nano Banana & Gemini

AI image generation skill for coding agents — crafts optimal prompts, generates images via Gemini/Nano Banana, self-reviews, and post-processes. Works with Claude Code, Codex, Gemini CLI, Copilot, and more.

241 pruna-mcp-server by charlesrapp
★ 5 MCP servers

MCP server for Pruna AI — ultra-fast image generation, editing, upscaling, and video generation

242 ai-workflow-generator by ahao0625
★ 5 Open models

AI image/video workflow generator — SKILL.md for Claude, GPTs, Gemini, LangChain, Dify, Coze, and more.

243 directing-image-prompts by Nanoleava
★ 5 Open models

Director-style Codex skill for AI image-generation prompts

244 gd-image-gen by aidenli
★ 5 GPT Image

Streaming image generation and editing skill for Codex-compatible OpenAI APIs.

245 claude-code-image-generation by mishagavura
★ 5 GPT Image

Claude Code image generation skill: generate & edit images with GPT Image 2 (gpt-image-2) from Claude Code via Codex CLI on your ChatGPT subscription. No OpenAI API key. One-line install.

246 hermes-daily-image-training by xujie8867
★ 5 GPT Image

Hermes daily AI image generation skill — photojournalism approach, zero art references

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 4.5 min · 7 image calls ($0.06) · See the six pictures →
247 nano-banana-prompting-skill by minilozio
★ 5 Nano Banana & Gemini

Transform natural language into optimized structured prompts for Gemini image generation. Auto-detects style. Works with OpenClaw and Claude Code.

🧪 Image test, 2026-11-08: Wrote no text on the poster or the bag. · made all six but broke a rule: 0 of 6 poster lines right; the shop name on the bag wrong or missing · close to the no-skill set · 3.3 min · 7 image calls ($0.10) · See the six pictures →
248 gpt-image-skills by kismmmnato0933
★ 5 GPT Image

gpt-image-skills generates or edits images using OpenAI-compatible image APIs configured with base_url and api_key.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 2.6 min · 6 image calls ($0.05) · See the six pictures →
★ 5 GPT Image

★ 5 Nano Banana & Gemini

Natural, SNS-ready photorealistic portrait prompt skill for Midjourney, Stable Diffusion, Nano Banana, and GPT Image 2.

251 ai-image-gpt-mcp by andyluu98
★ 5 MCP servers

Standalone MCP server + CLI for ChatGPT image generation (image only), with reliable single-file output

🧪 Tried in our test, no picture. Works only with its own service or account: needs a ChatGPT sign-in in a browser; it does not read an API key.
252 codex-gpt-image-mcp by Xuan-BOMS
★ 5 GPT Image

Use your own OpenAI-compatible GPT Image API directly from Codex through MCP, with generation, editing, local originals, and inline previews.

🧪 Image test, 2026-11-08: followed the brief: all six pictures, all text right, formats as asked · close to the no-skill set · 3.3 min · 7 image calls ($0.06) · See the six pictures →
253 qwen-image-local by Mats2208
★ 5 Open models

Type a prompt or drop up to 10 photos: Qwen-Image-2.1 renders it on your 12 GB GPU in ~35 s. Desktop app + CLI, honest benchmark vs gpt-image-2.

254 ai-image-generator-skill by beatra-ai
★ 5 MCP servers

AI image generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: generate, compose, and edit product images, brand visuals, posters, social graphics, illustrations, and photo variations. AI图片生成 · 文生图 · AI修图

255 ai-image-realism-skill by beatra-ai
★ 5 Image editing

AI image realism agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: make AI portraits, product images, and marketing visuals look more natural by fixing plastic skin, malformed hands and faces, repeated textures, and inconsistent lighting. 去AI味 · AI图片修复

256 illustration-studio by sammyteng
★ 5 Design assets

🎨 内容配图工作室 · 19 套插画风格 Agent Skill:先读懂文章→挑认知锚点→选风格→可粘贴生图提示词/双后端渲染(gpt-image-2 + Gemini Nano Banana)。Understands your article, picks 1 of 19 illustration styles, emits ready-to-paste prompts.

257 tropNEW by absolument-ai
★ 5 GPT Image

TROP turns creative briefs into art-directed AI image prompts. Claude Skill and Custom GPT setup.

258 claude-media-generationNEW by krowten
★ 5 MCP servers

Image, SVG and video generation for Claude Code: GPT Image 2.5, Nano Banana, Recraft, MiniMax H3, Kling, Seedance and Veo via fal.ai

259 ai-gallery by klarkxy
★ 5 MCP servers

Agent skill: fetch pose / depth / costume / face reference images from AI reference galleries (POSE-DB-01/02, COSTUME-DB-01, あぎ face DB, CC0 shisei) for GPT Image, Nano Banana, ComfyUI, H3.

260 prompt-constraints by q253595422
★ 4 Open models

生图 / 视频提示词约束引擎 — 把模糊需求变成可执行的提示词。An Agent Skill for constrained image & video prompt engineering (Nano Banana / Seedance / Veo / Sora / Kling / Midjourney / FLUX).

261 generate-image-skill by ethanplusai
★ 4 MCP servers

Give Claude Code image generation with your ChatGPT plan: Claude hands the job to Codex and gets the image back. No API key. Free local FLUX fallback on Apple Silicon. An Agent Skill + CLI.

262 image-skillbook by AlbertAZ1992
★ 2 GPT Image

Open-source AI image Skills and GPT Image prompt recipes for Codex—turn photos into doodle stories, crayon art, enamel keepsakes, rubber stamps, editorial paintings, and impasto worlds.

263 claude-codex-connectorNEW by alfeusaditya
★ 2 MCP servers

Claude-Codex Connector: let Claude Code use Codex (ChatGPT subscription) to generate images, review code and give second opinions. Skills + installer + docs.

264 image-to-svg-skills by cheshireyang
★ 0 MCP servers

Codex skill for converting complex generated images into clearer, second-editable SVG layouts through model-aware image generation, overview design, element decomposition, and SVG assembly.

265 codex-image-gen by stephenlzc
★ 0 GPT Image

Agent skill that generates images through your locally installed, OAuth-authenticated Codex CLI — no API keys, exact-size enforcement, and full prompt archiving for reproducibility.

Top 20 Compared

Tool Stars Score
ian-xiaohei-illustrations ★ 13.2k 77
ip-as-logo-skill ★ 6.4k 77
mono-color-skill ★ 3.6k 65
skills ★ 3.8k 72
paperbanana ★ 2.5k 70
MeiGen-AI-Design-MCP ★ 1.8k 78
female-portrait-director ★ 1.7k 79
ecom-details-image ★ 1.7k 70
guizang-material-illustration ★ 1.3k 58
banana-claude ★ 1.2k 72
codex-ppt-skill ★ 7.8k 73
GPT-Image2-Skill ★ 6.0k 72
NanoBanana-PPT-Skills ★ 3.4k 51
hand-drawn-styles ★ 2.7k 72
MiniMax-MCP ★ 1.6k 78
ian-handdrawn-ppt ★ 1.5k 63
gpt-image2-ppt-skills ★ 1.4k 61
ai-image-prompts-skill ★ 1.4k 67
comfyui-mcp ★ 938 72
ima2-gen ★ 904 67

Related Categories

Frequently Asked Questions

Can Claude generate images?

Claude itself does not output images, but Claude Code can, by calling an image model's API (GPT Image, Nano Banana, FLUX and others) through a skill, an MCP server or directly with your key. In our November 2026 test, Claude Code with no skill and a GPT Image key made a bakery poster with six exact lines of English and Chinese text, a product photo and four matching mascot pictures in 5.1 minutes, for $0.07.

Where are image generation skills and MCP servers on GitHub?

Everything on this page is in the open-source list zhuyansen/awesome-ai-image-skills on GitHub, grouped by model and use. Our test of 130 of them, with every picture each one made, is in the test section above; 20 of those work only with their own service or account, such as Bria, NovelAI, Scenario or Black Forest Labs.

What are the best image generation tools in 2026?

The top image generation tools in 2026 are ian-xiaohei-illustrations, ip-as-logo-skill, mono-color-skill. Agent Skills Hub ranks 265 options by GitHub stars, quality score (9 dimensions, including completeness, examples and agent readiness), and recent activity. The list is rebuilt every 8 hours from live GitHub data.

How do I choose between ian-xiaohei-illustrations and ip-as-logo-skill?

ian-xiaohei-illustrations (13.2k stars) is the most adopted choice for general image generation workflows. ip-as-logo-skill (6.4k stars) is a strong alternative. Pick by your existing stack: match the language and runtime your team already uses to minimize integration cost. If unsure, start with ian-xiaohei-illustrations — it has the deepest community and the most examples online.

When should I NOT use an image generation tool?

Avoid pre-built image generation tools when (1) your use case requires deep customization that the tool's plugin system doesn't support, (2) you have strict compliance requirements that ban third-party dependencies, (3) the tool's maintenance is inactive (last commit >6 months ago), or (4) your data volume is small enough that a 50-line custom script is cheaper than learning the tool. For most production workflows above 100 requests/day, the time savings from a maintained tool outweigh the customization loss.

What's the difference between image generation and ai design tools?

Image Generation focuses specifically on image generation skills and mcp servers for claude code, codex and other agents, security-graded: gpt image, nano banana, flux, image editing and design assets. vet before you install. AI Design Tools is a related but distinct category — see https://agentskillshub.top/best/ai-design/ for those tools. The two often appear in the same agent pipeline but solve different problems: choose image generation when your primary goal is the specific task, and ai design tools when the workflow is broader.

Is ian-xiaohei-illustrations better than building it yourself?

For most teams, yes. ian-xiaohei-illustrations has 13.2k stars worth of community testing, handles edge cases you haven't thought of, and ships with documentation. Build your own only when (1) your requirements are deeply non-standard, (2) you have a security/compliance reason to avoid OSS dependencies, or (3) the maintenance burden is small enough (<200 lines of code) that you'll save time long-term. The break-even point is usually around 2-3 weeks of dev time saved.

Are these image generation tools free to use?

Most image generation tools listed are open source under permissive licenses (MIT, Apache 2.0). A handful offer paid managed/cloud versions on top of free self-hosted core. Always check the LICENSE file on each tool's GitHub repository before commercial use — some use AGPL or non-commercial restrictions that may not fit your deployment model.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

Get Weekly AI Tool Picks

Top 20 fastest-growing AI tools delivered every Monday. Free.

No spam, unsubscribe anytime.

Explore All Skills on Agent Skills Hub