hanyuancheung/llm-skill
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
A minimal three-layer SKILL system for LLM agents, inspired by Karpathy's LLM-Wiki idea
概要
A minimal three-layer skill system for LLM agents, inspired by Karpathy's idea: Three meta-skills operate on the skill system itself: End-to-end pipeline (Execute → Distill → Guide, illustrated with a review-go-pr walkthrough): install.sh runs layout checks and calls scripts/validate.py. 1. — the agent reads AGENT.md §2, routes to ≤ 3 skills, executes, and collects distill candidates. 2. : 3. — say "distill this" and the agent walks the four-phase SOP in skills/distill/SKILL.md. - AGENT.md is pure routing + contract. - — Execute (read-only on skills) / Distill (writes skills) / Guide (writes AGENT.md only). - — never ls skills/ and batch-read; match triggers first, load ≤ 3 SKILL.md. - on every skill — version and status.
README
以下は原文 README の抜粋です。原文を見る。
llm-skill — Execute / Distill / Guide
English | 中文
A minimal three-layer skill system for LLM agents, inspired by Karpathy’s LLM-Wiki idea:
The closed loop
Three meta-skills operate on the skill system itself:
| Meta-skill | Responsibility | Output |
|---|---|---|
| execute | Read AGENT.md routing → load the smallest skill subset → finish the task → log reusable signals |
deliverable + distill-candidates |
| distill | Refine traces into new/updated skills per contract | skills//SKILL.md changes |
| guide | Maintain the AGENT.md routing table & skill health |
AGENT.md changes |
[Execute] ──traces──► [Distill] ──skill CRUD──► [Guide] ──routing──► [Execute] ...
Repository layout
llm-skill/
├── README.md # this file (English default)
├── README_zh.md # Chinese
├── CHANGELOG.md # append-only
├── AGENT.md # Schema: routing + contract (single source of truth)
├── AGENTS.md # Codex entrypoint
├── CLAUDE.md # Claude Code entrypoint
├── HERMES.md # HERMES entrypoint
├── install.sh # one-shot install / sanity check
├── scripts/
│ └── validate.py # front-matter + routing consistency checker
└── skills/
├── execute/ SKILL.md + SKILL_zh.md
├── distill/ SKILL.md + SKILL_zh.md
├── guide/ SKILL.md + SKILL_zh.md
└── _template/ SKILL.md + SKILL_zh.md
End-to-end pipeline (Execute → Distill → Guide, illustrated with a review-go-pr walkthrough):
Install
Option A — standalone repo
git clone llm-skill
cd llm-skill
bash install.sh
Option B — mount into an existing project
git clone .llm-skill
ln -s .llm-skill/AGENT.md ./AGENT.md
ln -s .llm-skill/AGENTS.md ./AGENTS.md # for Codex
ln -s .llm-skill/CLAUDE.md ./CLAUDE.md # for Claude Code
ln -s .llm-skill/HERMES.md ./HERMES.md # for HERMES
ln -s .llm-skill/skills ./skills
bash .llm-skill/install.sh
install.sh runs layout checks and calls scripts/validate.py.
Quick start
- Run a task — the agent reads
AGENT.md§2, routes to ≤ 3 skills, executes, and collects distill candidates. - Add a skill:
cp -r skills/_template skills/ # edit SKILL.md (and SKILL_zh.md if you want) # ask the agent to run `guide` to register it in AGENT.md §2.2 - Distill a pitfall — say “distill this” and the agent walks the four-phase SOP in
skills/distill/SKILL.md.
Design invariants
- Domain knowledge belongs only in
SKILL.md.AGENT.mdis pure routing + contract.
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add hanyuancheung/llm-skill