fork-pr-flow SKILL.md skillA
fork-pr-flow from esonhugh/claude-code is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add esonhugh/claude-code/fork-pr-flow@v0.1.0Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- esonhugh/claude-code
- Path
.claude/skills/fork-pr-flow/SKILL.md- Versions recorded
- 1
- Latest version
- v0.1.0, committed Oct 25, 2026
- Size
- 2,505 bytes
- Repository stars
- 61
- License
- none declared
在 Esonhugh/claude-code fork 發現問題、提交修復、開 PR 與合併時使用：先開 issue、依領域拆 commit、PR 開到 dev 並自行驗證後合併。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Fork 的 issue → PR → 合併流程 ## 規則（使用者訂的） - **目標分支是 `dev`**（2026-10-21 起取代 feat/mods）。只有 Direct Connect 這類大功能才另開長期分支。永不推 master、不發 release。 - **修復直接合進 dev，不等使用者 review**（2026-10-23）：驗證過（重建 binary 實測、相關測試綠、tsc/lint 乾淨）就自己合併，再回報。 - **先開 issue 再開 PR**，PR 內文連結 issue（例如 #4 → #5）。 - **commit 依領域拆分**：啟動/退出、Agent、設定/權限、任務框架/Teams、Mods。一個 commit 不跨領域。 ## 步驟 1. **重現並記錄**：用 fork-binary-testing 在隔離環境重現，和官方 2.1.303 對照。先搜既有 issue 避免重複，再開 issue：現象、重現步驟、官方行為、證據路徑。 2. **最小失敗測試**：先寫能重現的最小測試，再修根因；不跳過、不放寬斷言、不吞例外。 3. **分支與 commit**：從最新 `origin/dev` 開分支；按領域拆 commit，訊息說清目的，不誇大範圍。提交前看 `git status`、`git diff`，清掉除錯碼。若改到 CHANGELOG，衝突時兩邊保留、新的在上。 4. **驗證**：`bun run lint`、`tsc --noEmit`（`NODE_OPTIONS=--max-old-space-size=12000`）、相關 `bun test`、`make build` 後用新 binary 實測（流程見 fork-release-wiki 的合併前檢查）。 5. **開 PR 到 dev**：內文含 `Fixes #NN`、修復前/後行為、驗證命令與結果、證據檔路徑（`/mnt/project-files/research/acceptance/accept-<topic>.md`、`research/probe/<topic>/`）。 6. **合併**：CI 綠後用 merge commit 合進 dev，標題沿用 `Merge PR #NN: <title>`。 7. **手動關 issue**：dev 不是預設分支，`Fixes #NN` 不會自動關；合併後手動關閉並註明 PR。 8. **回報**：修了什麼、修復前/後行為、驗證了什麼、未驗證項與風險。 ## 常見注意 - 多個 PR 改同一檔（如 permissions.ts）時，以「對官方 binary 實測的行為」決定保留哪邊，並在 PR 寫明取捨。 …
Read the whole file at its exact version.
How to install
mdr add esonhugh/claude-code/fork-pr-flow@sha256:391a253908b15676The line at the top of this page pins the label v0.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_i6omj2w7r5menxt5)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 25, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2505 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
esonhugh/claude-code · 61 stars · license none declared · pushed 2026-11-04 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_i6omj2w7r5menxt5 GET https://markdownregistry.com/api/v1/resolve?ref=esonhugh/claude-code/fork-pr-flow GET https://markdownregistry.com/api/v1/blob/391a253908b15676534a36557fb4fad5df564c3a114d4602ddaa9add4b80cae0
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.