book-to-skill / rules
Cursor rule1 starsChanged 47 days agoMITView on GitHub
Fork PRs must target SanHsien origin; upstream PRs need explicit contribute-back consent
- Commits and pushes
In this repository2 other files it gives its agents.
- AGENTS.mdAGENTS.md
- book-to-skillSkill
The file
Files
--- description: Fork PRs must target SanHsien origin; upstream PRs need explicit contribute-back consent alwaysApply: true --- # 對外只打本 fork 本 repo 是 fork(上游位址見 `git remote -v` 的 `upstream`)。PR、push、release 一律指向 `SanHsien/book-to-skill`。 **根因是機制不是粗心:** `gh` 在 fork clone 的預設 repo 就是上游,裸跑 `gh pr create` 必然打上去。 ```powershell gh repo set-default SanHsien/book-to-skill # 每個 clone 先跑一次 gh repo set-default --view # 必須回 SanHsien/book-to-skill gh pr create --repo SanHsien/book-to-skill --base main --head <分支> ``` 建完**讀輸出的 URL**,owner 必須是 `SanHsien`。不是就立刻 `gh pr close` 留言道歉說明開錯 repo, 再對 origin 重開,並主動告訴使用者。 2026-08-22 一天內兩個工具各誤開一個上游 PR(`lidge-jun/opencodex#2373`、 `hamanpaul/paulsha-cortex#787`)。兩次都是「指令成功了」的錯覺——開錯的 owner 就寫在輸出的 URL 裡。 批次跑多個 repo 時最容易略過確認,那正是出事的場合。 **唯一例外:** 使用者在**這次對話**明確同意回貢上游。fork、建環境、開 PR、比照其他 repo、 合併回 main、「所有專案都照做」都不是例外。
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.

