hanyuancheung/llm-skill

A minimal three-layer SKILL system for LLM agents, inspired by Karpathy's LLM-Wiki idea

This repository also configures its own agents. See what llm-skill tells them →

22Stars on the repository
6Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

_template

01

hanyuancheung/llm-skill

Skill Claude Code

Skill "_template" from hanyuancheung/llm-skill, covering what, when to use, when not to use, how and examples.

not rated 22 4mo ago A 1 tokens original MIT

distill

02

hanyuancheung/llm-skill

Skill Claude Code

Turn Raw-layer traces (conversation, pitfalls, best practices) into Wiki-layer skills, or CRUD existing ones, then notify guide to update the routing table.

not rated 22 4mo ago A 2 tokens original MIT

execute

03

hanyuancheung/llm-skill

Skill Claude Code

Select the right domain skill from the AGENT.md routing table, complete the task, and passively collect distillable signals as raw material for the next distill pass.

not rated 22 4mo ago A 1 tokens original MIT

guide

04

hanyuancheung/llm-skill

Skill Claude Code

Maintain the single Schema file AGENT.md so that execute always routes to the right skill with the minimum information possible.

not rated 22 4mo ago A 1 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: