agentleFS
shailesh17shailesh17/mcp-httpserver-proxy/.agents/skills/create-pr/SKILL.md

create-pr

Skill2 starsChanged 3 months agoMITView on GitHub

Automated end-to-end workflow to verify, format, test, push, and open a polished, AI-native Pull Request using GitHub CLI (gh) with Conventional Commits and rich markdown formatting.

  • Commits and pushes

196 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use update-pr, act-on-feedback and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    update-pr

    Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.

    Also in 9 projects that use this

  • MicrosoftSkill

    act-on-feedback

    Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

    Also in 3 projects that use this

  • ModelEngine-GroupSkill

    create-release-note

    从 PR/commit 中自动生成结构化的 Release Notes,并可选创建 GitHub Draft Release。支持 x.y.0 版本合并前一 minor 系列的 release notes。当用户要求生成发布说明、创建 release notes 时触发。参数为版本号和可选的上一版本号。

    Also in 3 projects that use this

  • frostneySkill

    native-nostalgia-stack

    Applies the user's FreePascal toolchain and its build, formatting, hook, and test contracts while leaving project-specific mechanics local. Use when scaffolding or working in a FreePascal project that follows this toolchain.

    Also in 3 projects that use this

  • frostneySkill

    software-engineering-excellence

    Applies the user's engineering standards during substantial technical work: preserve scope, use current evidence, delegate independent parts, and complete authorized outcomes. Use during substantial implementation, debugging, refactoring, or multi-part delivery work.

    Also in 3 projects that use this

  • parkchuSkill

    start-mission

    넥스트스텝(NextStep) 미션을 처음 시작할 때, 미션 저장소를 fork·clone하고 최초 작업 브랜치(step1 등)까지 만들어 준다. gh CLI로 fork하고 clone까지 이어서 처리하며, gh가 없거나 인증이 안 돼 있으면 브라우저 Fork 안내로 폴백한다. 이미 fork/clone돼 있으면 재사용하고 이어서 진행한다(재실행 안전). 사용자가 "미션 시작하려는데 저장소 세팅해줘", "새 미션 시작할래", "fork부터 해줘", "/nextstep:start-mission" 등으로 요청할 때 사용한다.

    Also in 3 projects that use this

  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when you need to prepare, verify, push, and create a Pull Request on GitHub following this repository's AI-native …

    line 9
  2. Distinctive:

    All Pull Request titles and commit messages must follow the standard Conventional Commit pattern:

    line 15
  3. Distinctive:

    Run all verification tools to ensure zero build errors, format violations, or lint issues:

    line 41
  4. Distinctive:

    If transport, proxy, or server integration was modified, run the local mock SSE server and verify end-to-end:

    line 59
  5. Very specific:

    Ensure changes are committed with Conventional Commit messages (type(scope): description).

    line 73
  6. Distinctive:

    If on main, switch to a descriptive branch:

    line 81
  7. Very specific:

    Use gh pr create with the Conventional Commit title and rich Markdown body adhering to the template below:

    line 95

“Common” is measured: kept by at least 6 in 10 of the 179 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create PR Skill

Use this skill when you need to prepare, verify, push, and create a Pull Request on GitHub following this repository's AI-native development standards.


📋 Standard PR Title Format (Conventional Commits)

All Pull Request titles and commit messages must follow the standard Conventional Commit pattern:

<type>(<optional-scope>): <description>

Type Reference

TypeDescriptionExample
featNew feature or capabilityfeat(cli): add interactive options and help flag ✨
fixBug fix or error resolutionfix(transport): prevent message drop during init 🐛
docsDocumentation changesdocs(readme): add Cursor and VS Code setup guides 📝
styleFormatting or styling adjustmentsstyle: standardize TypeScript import order 🎨
refactorCode restructuring without logic changerefactor(proxy): extract signal cleanup handlers ♻️
perfPerformance improvementperf(sse): optimize message serialization 🚀
testAdding or updating teststest: add mock SSE server end-to-end suite 🧪
buildBuild system or dependency updatesbuild: update TypeScript target to ES2022 📦
ciCI/CD workflow updatesci: add Node 24 matrix test and semantic PR check 👷
choreTooling, configs, or maintenancechore(trunk): track .trunk configs in Git 🔧
revertReverting a previous commitrevert: undo experimental stream buffer ⏪

🛠️ Step-by-Step Execution Workflow

Step 1: Pre-flight Verification & Stream Hygiene

Run all verification tools to ensure zero build errors, format violations, or lint issues:

# 1. Compile TypeScript
pnpm run build

# 2. Format code with Trunk
pnpm run format

# 3. Lint and analyze workspace
pnpm run check

[!IMPORTANT] Verify Stdout Isolation: Ensure no console.log() calls exist in runtime proxy code (src/index.ts). All logging must be routed to process.stderr via console.error().

Step 2: Testing Verification & Evidence Collection

If transport, proxy, or server integration was modified, run the local mock SSE server and verify end-to-end:

# Start mock server in background
node .agents/skills/mock-sse-server/scripts/mock-server.js

# Test connection
node dist/index.js http://127.0.0.1:8123/sse

Capture the execution logs to include in the PR description under Testing Evidence.

Step 3: Git Branch & Push

  1. Ensure changes are committed with Conventional Commit messages (type(scope): description).
  2. Check current branch:

    git branch --show-current

    If on main, switch to a descriptive branch:

    git checkout -b <type>/<short-description>
  3. Push branch to remote:

    git push -u origin <branch-name>

Step 4: Create Pull Request with GitHub CLI (gh)

Use gh pr create with the Conventional Commit title and rich Markdown body adhering to the template below:

gh pr create \
  --title "feat(cli): add interactive options and help flag" \
  --body "$(cat <<'EOF'
# Pull Request

## 📋 Description & What Changed
- Added `-h` / `--help` and `-v` / `--version` CLI flags.
- Implemented `SIGINT` and `SIGTERM` signal handlers for graceful connection cleanup.
- Configured executable `bin` field in `package.json`.

---

## 💡 Motivation & Why
Allows developers to run `mcp-httpserver-proxy` directly via `npx` with zero setup and ensures child processes terminate cleanly when the terminal session ends.

---

## 🧪 How to Test
1. Run `pnpm run build`.
2. Run `node dist/index.js --help` and verify options display correctly.
3. Run `node dist/index.js http://127.0.0.1:8123/sse` against the mock SSE server.

---

## 🔍 Testing Evidence & Execution Logs
```text
$ pnpm run build
$ trunk check
Checked 24 modified files
✔ No issues

$ node dist/index.js http://127.0.0.1:8123/sse
Proxy running. Connected to http://127.0.0.1:8123/sse
```

---

## 🤖 AI Agent & Model
- **Agent / Tool**: Antigravity
- **Model**: Gemini 3.7 Flash

---

## 🛡️ Contributor Checklist
- [x] PR Title follows Conventional Commits (`type(scope): description`).
- [x] TypeScript builds cleanly with `pnpm run build`.
- [x] Code is formatted with `pnpm run format` and passes `pnpm run check`.
- [x] Zero `console.log()` calls to `stdout` (diagnostics use `console.error()`).
EOF
)"

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.