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 WoJiSama · Codex Skill · ★ 597
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is skill-based-architecture safe to install? View the security audit →
Featured in: Skill Creation & Meta-Tools
Skill-Based Architecture English | 中文 A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated directory — a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task. The output is the point. What you get is not just a tidier docs folder — it is the skill that understands your project best: routable, self-maintaining, lesson-capturing, and triggered automatically when the task matches. Community support Learn AI on LinuxDO — LinuxDO Why This Exists AI coding agents (Cursor, Claude Code, Codex, Windsurf, etc.) rely on project documentation to understand rules, conventions, and workflows. But as projects grow, that documentation inevitably becomes a mess: | Single S
| Stars | 597 |
| Forks | 50 |
| Language | Shell |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66.2594210444691/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-20 |
| Created | 2026-04-08 |
| Platforms | claude-code, cli, codex, gemini |
| Est. Tokens | ~17k |
These tools work well together with skill-based-architecture for enhanced workflows:
Looking for a skill-based-architecture alternative? If you're comparing skill-based-architecture 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.
Just a Better Chatbot. Powered by Agent & MCP & Workflows.
An md file as a chat interface and editable history in one.
Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
Desktop AI Assistant powered by GPT-6, GPT-5, Gemini, Claude, Ollama, Grok, DeepSeek, Perplexity, Bielik, chat
Make your own story. User-friendly software for LLM roleplaying
Explore other popular codex skill tools:
skill-based-architecture is A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/<name>/ directory — a project skill that become. It is categorized as a Codex Skill with 597 GitHub stars.
skill-based-architecture is primarily written in Shell. It covers topics such as agent, ai, chatbot.
You can find installation instructions and usage details in the skill-based-architecture GitHub repository at github.com/WoJiSama/skill-based-architecture. The project has 597 stars and 50 forks, indicating an active community.
skill-based-architecture is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to skill-based-architecture on Agent Skills Hub include better-chatbot, chat.md, Claude-to-IM-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: