hanyuancheung

6 mods across 1 repository, 22 stars between them.

llm-skill AGENTS.md

01

hanyuancheung/llm-skill

Instructions file CodexOpenCode

Instructions for hanyuancheung/llm-skill, covering agents.md — codex entrypoint, what codex should do on load, install (codex cli), option a: use this repo as the project root and option b: mount into an existing project.

22 4mo ago A 485 tokens original MIT

llm-skill CLAUDE.md

02

hanyuancheung/llm-skill

Instructions file

Instructions for hanyuancheung/llm-skill, covering claude.md — claude code entrypoint, what claude code should do on load, install (claude code), option a: use this repo as the project root and option b: mount into an existing project.

22 4mo ago A 591 tokens original MIT

_template

03

hanyuancheung/llm-skill

Skill Claude CodeCodex

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

22 4mo ago A 1 tokens original MIT

distill

04

hanyuancheung/llm-skill

Skill Claude CodeCodex

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

22 4mo ago A 2 tokens original MIT

execute

05

hanyuancheung/llm-skill

Skill Claude CodeCodex

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.

22 4mo ago A 1 tokens original MIT

guide

06

hanyuancheung/llm-skill

Skill Claude CodeCodex

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

22 4mo ago A 1 tokens original MIT