garden-skills — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 ConardLi · Agent Tool · ★ 12.4k

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

🔒 Is garden-skills safe to install? View the security audit →

About garden-skills

Garden Skills A curated collection of production-ready Agent Skills for Claude Code, Cursor, Codex, and other AI coding agents. web-video-presentation Web video / presentation web-design-engineer Design / frontend gpt-image-2 Image generation / prompting beautiful-article

agentclaudegpt-image-2ragskillsweb-design

Quick Facts

Stars12,414
Forks1,500
LanguageCSS
CategoryAgent Tool
LicenseMIT
Quality Score61.2005711723555/100
Open Issues18
Last Updated2026-07-12
Created2026-04-21
Platformsbrowser, claude-code
Est. Tokens~24k

Compatible Skills

These tools work well together with garden-skills for enhanced workflows:

  • gpt_image_2_skill — semantic(0.36)+complementary+rare_topics+similar_pop+shared_platform (57%)
  • GPT-Image2-Skill — semantic(0.36)+complementary+rare_topics+similar_pop+shared_platform (57%)
  • gpt-image2-ppt-skills — semantic(0.24)+complementary+rare_topics+similar_pop+shared_platform (53%)
  • codex-ppt-skill — semantic(0.21)+complementary+rare_topics+similar_pop+shared_platform (52%)
  • awesome-gpt-image-2 — semantic(0.32)+complementary+rare_topics+similar_pop (51%)

garden-skills alternative? Top 6 similar tools

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

  • FastGPT by labring · ⭐ 29.6k

    FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabi

  • Upsonic by Upsonic · ⭐ 7.9k

    Build autonomous AI agents in Python.

  • casibase by casibase · ⭐ 4.5k

    ⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-a

  • headroom by chopratejas · ⭐ 44.4k

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answer

  • chatgpt-on-wechat by zhayujie · ⭐ 43.0k

    CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页

  • serena by oraios · ⭐ 29.2k

    A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your a

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular CSS Agent Tools

Frequently Asked Questions

What is garden-skills?

garden-skills is ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.. It is categorized as a Agent Tool with 12.4k GitHub stars.

What programming language is garden-skills written in?

garden-skills is primarily written in CSS. It covers topics such as agent, claude, gpt-image-2.

How do I install or use garden-skills?

You can find installation instructions and usage details in the garden-skills GitHub repository at github.com/ConardLi/garden-skills. The project has 12.4k stars and 1500 forks, indicating an active community.

What license does garden-skills use?

garden-skills is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to garden-skills?

The top alternatives to garden-skills on Agent Skills Hub include FastGPT, Upsonic, casibase. 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 Agent Tool tools