Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
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 becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task.
| Date | Stars |
|---|---|
| 2026-07-31 | 468 |
| 2026-08-06 | 488 |
Today
+20 stars today
This week
— stars this week
This month
— stars this month
Momentum
95.0
growth rate 0.00%/day
<p align="center">
<img src="assets/skill-based-architecture-title.png" alt="skill-ba" width="720">
</p>
# Skill-Based Architecture
<p align="center">
<a href="https://github.com/WoJiSama/skill-based-architecture/stargazers">
<img alt="GitHub stars" src="https://img.shields.io/github/stars/WoJiSama/skill-based-architecture?style=flat&logo=github">
</a>
<a href="https://github.com/WoJiSama/skill-based-architecture/forks">
<img alt="GitHub forks" src="https://img.shields.io/github/forks/WoJiSama/skill-based-architecture?style=flat&logo=github">
</a>
<a href="LICENSE">
<img alt="License" src="https://img.shields.io/github/license/WoJiSama/skill-based-architecture?style=flat">
</a>
<img alt="Status" src="https://img.shields.io/badge/status-alpha-orange">
<a href="https://linux.do/">
<img alt="LinuxDO" src="https://img.shields.io/badge/LINUX-DO-f59e0b?style=flat">
</a>
</p>
<p align="center"><strong>English</strong> | <a href="README.zh-CN.md">中文</a></p>
A **lifecycle framework for AI-agent rule systems.** Turns scattered prompt documents (`AGENTS.md`, `CLAUDE.md`, `.cursor/rules/`, README rules) into routable, verifiable, updatable engineering assets under `skills/<name>/`.
It focuses on the rule system itself: structure, routing, workflows, validation, after-action learning, and upstream/downstream updates. It does **not** ship technology-specific rules — those belong in your downstream project skill.
## Install
**Claude Code — one line:**
```text
/plugin marketplace add WoJiSama/skill-based-architecture
/plugin install skill-based-architecture@skill-based-architecture
```
Then [trigger it](#quick-start); pull updates later with `/plugin marketplace update`.
**Try without installing:** [Run Skill Based Architecture in Telegram or WhatsApp](https://app.clawmama.run/skills/i78bb1/hermes?utm_source=github&utm_medium=issue&utm_campaign=skill_outreach_wojisama_skill_based_architecture) via ClawMama's Skill catalog. Use it with the [copy-paste demo input](examples/simple-repo/COPY-PASTE-INPUT.md) or other non-sensitive rule files. The bundled demo is deliberately the most basic smoke-test input, so the generated structure will be small; for real project migration, install locally with Claude Code or clone the repo.
**Cursor / Codex / Gemini / other harnesses** don't share Claude Code's plugin system — clone the repo instead (see [Quick Start](#quick-start)).
## What it produces
```
scattered project guidance
AGENTS.md / CLAUDE.md / .cursor/rules / README notes
│
▼
skills/<project>/
├── SKILL.md # router: description ≤ 25 + body ≤ 90 lines (dual budget)
├── rules/ # stable constraints
├── workflows/ # repeatable procedures
├── references/ # architecture, gotchas, indexes
└── docs/ # optional reports and prompts
tool entry files
AGENTS.md / CLAUDE.md / CODEX.md / GEMINI.md / .cursor/rules / .codex
└── thin shells: route to skills/<project>/, no duplicated rule bodies
```
## Why
| Symptom | What goes wrong |
|---|---|
| Single `SKILL.md` with 400+ lines | Agent reads everything every task — wastes tokens, hides what matters |
| Rules duplicated across `AGENTS.md`, `.cursor/rules/`, `CLAUDE.md` | Drift, contradictions, no source of truth |
| Skill activation is unreliable | Description is a passive summary instead of explicit trigger conditions |
| Hard-won lessons buried in docs | Costly pitfalls never surface during the next task |
| Rule files only grow, never shrink | Useful rules get buried by obsolete ones |
The architecture answers each: a routing source-of-truth (`routing.yaml`), thin shells everywhere else, description-as-trigger discipline, AAR with a recording threshold, and self-maintenance via line-count signals + split/merge procedures.
## When NOT to use
- Total rule content < 50 lines (a single `CLAUDE.md` is enough)
- Single harness, no team sharing, no recurring tasks
- Short-lived solo project (< 2 Excerpt of 13,333 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:51eb697cbaa7456d, topic:chatbot