ch-skills
AGENTS.md4 starsChanged 3 months agoNo licenceView on GitHub
Skill 不是程序，而是给模型的专业方法论。 真正完成任务的是模型本身，SKILL.md 才是核心产物。脚本只承担模型无法直接完成的原子能力：调用外部 API、读取本地文件/数据库、执行确定性计算或格式转换。判断、分析、措辞、结构组织、风险提示都交给模型。 一句话：把"手"留给脚本，把"脑"留给模型。 Skill 系统采用三层加载，token 经济性差异巨大： SKILL.md 主体越精简，触发成本越低。大段领域知识、案例库、字段字典、表格速查应拆到 references/，主体只留纲要 + 指引（"当遇到 X 情况，读 references/x.md"）。 资源层三种角色不要混用： 以下信号通常说明 Skill 设计可以向"模型判断"方向优化： 代码越大，Skill 越僵。保持脚本原子性，把领域知识下沉到 references/，Skill 才具备可组合性与可演化性。 SKILL.md 同时承担两个角色：触发说明书（让模型知道何时用）和 工作手册（让模型知道怎么用）。两者缺一不可。 需要完整模板时，参考 references/SKILL.md.template。
- Reads credentials
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- open-code-review-delegateSkill
- ch-dc-credit-monitorSkill
- ch-gpu-compute-monitorSkill
- ch-news-reporterSkill
- md-pushplusSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.