tiny-steps
Skill0 starsChanged 31 days agoMITView on GitHub
当改动涉及多个文件或多个步骤，或用户说「一步步来」「别一次改太多」时使用。一次只推进一小步，每步验证过再走下一步。
In this repository5 other files it gives its agents.
- ask-firstSkill
- plain-wordsSkill
- prove-itSkill
- setup-ticketsSkill
- write-my-skillSkill
The file
Files
一次只推进一小步，每一步都验证过再走下一步。
怎么算一小步
- 只做一件能用一句话说清的事。可以改多个文件，但必须是为了同一件事。
- 做完能立刻验证：跑测试、跑命令、打开页面看一眼，随便哪种都行。
- 如果这一步没法验证，说明步子太大，再拆。
每步报告三件事
- 这一步做了什么
- 用什么验证的，结果是什么
- 下一步准备做什么
然后停下等用户说继续。用户明确说「不用问我，全做完」时才连续做，但仍然每步都验证并汇报。
不要做
- 不要把三步合并成一步顺手做完。
- 不要在没验证的情况下进入下一步。
- 不要一边做这件事，一边改无关的东西。
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.