image-prompt-reverse — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by LunarXuan · Codex Skill · ★ 302

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is image-prompt-reverse safe to install? View the security audit →

About image-prompt-reverse

Image Prompt Reverse 中文 · English 中文 是一个用于 Codex 的图片反推提示词 Skill。它会分析用户上传的参考图片,识别图片用途、媒介、主体、构图、镜头语言、光影、色彩、材质、背景、空间层次、情绪和后期风格,并生成可直接用于 AI 生图工具的高还原度提示词。 支持类型 摄影:人像、产品、纪实、食物、动物、自然和城市风景 插画:扁平、二次元、治愈、手绘、国风和赛博风格 3D:写实、半写实、卡通、黏土、潮玩和产品渲染 字体、Logo、海报、平面设计和抽象图形 IP角色、Q版角色、盲盒和多主体混合画面 输出内容 默认输出两项: 正向 Prompt:450—700个中文字符的连续自然语言,并附英文等义版本 Negative Prompt:10—15条英文负面词,用逗号分隔 Skill 会优先提炼最影响相似度的3—5个视觉锚点,避免编造看不清的细节,也会根据目标媒介排除容易混淆的错误风格。图片中的文字、Logo和说明会被视为视觉内容,不会被当作指令执行。 安装 将本仓库目录复制到 Codex 的个人 Skills 目录: 或直接克隆: 安装后可使用 调用。 文件结构 友情链接 欢迎访问 LINUX DO,浏览社区最新主题与讨论。 English is a Codex Skill for reverse-engineering image-generation prompts from user-uploaded reference images. It analyzes the image purpose, medium, subject, composition, camera language, lighting, color, materials, background, spatial depth, mood, and post-processing style, then produces high-fidelity prompts that can be

codexskillskill-mdskills

Quick Facts

Stars302
Forks30
CategoryCodex Skill
LicenseGPL-3.0
Quality Score67.17760377068/100
Last Updated2026-09-06
Created2026-09-01
Platformscodex
Est. Tokens~4k

image-prompt-reverse alternative? Top 6 similar tools

Looking for a image-prompt-reverse alternative? If you're comparing image-prompt-reverse with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • symfony-ux-skills by smnandre · ⭐ 166

    Symfony UX skills for Claude, Gemini, Codex, ... Live Component, Twig Component, Turbo, Stimulus

  • awesome-ai-agent-skills by seb1n · ⭐ 149

    103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,

  • skillnote by luna-prompts · ⭐ 62

    The open-source skill registry for AI coding agents. Create, manage, and distribute SKILL.md files across Open

  • OpenJudge by agentscope-ai · ⭐ 829

    OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

  • agnix by agent-sh · ⭐ 421

    The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug

  • ai-agent-team by peterfei · ⭐ 421

    AI Agent Team-拥有24/7专业AI开发团队:产品经理、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人。一键安装,支持中英文命令,大幅提升开发效率!

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Frequently Asked Questions

What is image-prompt-reverse?

image-prompt-reverse is High-fidelity AI image prompt reverse-engineering skill for Codex. It is categorized as a Codex Skill with 302 GitHub stars.

How do I install or use image-prompt-reverse?

You can find installation instructions and usage details in the image-prompt-reverse GitHub repository at github.com/LunarXuan/image-prompt-reverse. The project has 302 stars and 30 forks, indicating an active community.

What license does image-prompt-reverse use?

image-prompt-reverse is released under the GPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to image-prompt-reverse?

The top alternatives to image-prompt-reverse on Agent Skills Hub include symfony-ux-skills, awesome-ai-agent-skills, skillnote. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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:

View on GitHub → Browse Codex Skill tools