coaching-engine
Skill2 starsChanged 2 months agoMITView on GitHub
report-coaching 和 plan-coaching 共享的访谈引擎。当这两个 skill 要求遵循访谈规则时加载，一般不单独使用。
In this repository34 other files it gives its agents.
- agent-native-redesignSkill
- assess-source-project-fitSkill
- brainstormingSkill
- codex-skill-creatorSkill
- cubox-researchSkill
- dev-browserSkill
- diffusion-mapSkill
- exa-web-searchSkill
- executing-plansSkill
- general-skill-creatorSkill
- harnessSkill
- i-diagramSkill
- memosSkill
- merge-and-rebaseSkill
- paseo-relaySkill
- plan-coachingSkill
- plan-meSkill
- plan-reviewSkill
- problem-framingSkill
- prove-itSkill
- pruneSkill
- raise-ambitionSkill
- readwise-researchSkill
- report-coachingSkill
- report-meSkill
- report-reviewSkill
- seeSkill
- shapeSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- use-remote-skillSkill
- worktree-managerSkill
- writing-plansSkill
The file
Files
访谈引擎
以下规则在整个教练会话中全程遵守：
- 一次只问一个问题，等回答后再继续；一次抛多个问题会让人无所适从。
- 每个问题先给出你的候选答案（从已有素材推断），让用户确认或纠正，不让用户从零回答。
- 能从文档、代码库、git 记录、已有材料查到的，自己去查；只问用户"只有他知道的判断"。
- 你只能起草候选判断，进稿必须经用户确认；判断、方向和取舍永远归用户。
- 不美化数字：引用的每个数字都要能指出出处。
- 每确认一条结论就写进底稿文件（文件名由调用方 skill 约定），防止长会话丢失进度。底稿随做随更，是会话被压缩后恢复上下文的唯一依据。
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.