blog
AGENTS.md0 starsChanged 7 days agoNo licenceView on GitHub
涉及功能规划、问题反馈、开始/恢复开发、PR 或交付验收时，先读取本仓库的 github-workflow Skill。先轻后重：当前 session 能明确修复并验证闭环的小问题直接处理；跨轮、延期、阻塞或后续验收任务才使用 Issue，大功能确认范围后再建 Issue；批量反馈先分类查重，同根因合并。 遵守本仓库原有的分支、提交、推送、验证和授权规则；本 Skill 不覆盖它们，也不额外授予线上操作权限。未迁移任务继续使用现有进度入口，学习记录等非工程状态保持原归属；经授权采用 Issue 的工程任务，其动态状态只维护在 Issue/已有 Projects，设计契约仍留在仓库文档。阶段完成、阻塞或范围变化时同步获准的 Issue/PR，未同步则明确报告。本次仅接入流程，不自动迁移历史待办，合并不等于发布或人工验收。
In this repositoryOne other file it gives its agents.
- github-workflowSkill
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.