agentleFS
crux-clicrux-cli/crux/.claude/skills/create-pr/SKILL.md

create-pr

Skill0 starsChanged 8 months agoMITView on GitHub

Create a PR from the current branch with a structured description optimized for automated review.

  • 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, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a pull request from the current branch with a structured description that enables thorough automated review via /review-pr.

    line 9
  2. Distinctive:

    All work is committed (git status is clean)

    line 16
  3. Distinctive:

    If any prerequisite fails, fix it before continuing.

    line 19
  4. Very specific:

    If the branch name contains an issue number (e.g., fix/issue-42), or if commit messages reference an issue (closes #42, fixes #42), fetch …

    line 47
  5. Very specific:

    Use this exact format. Every section is required.

    line 61
  6. Distinctive:

    Always fill in "Breaking Changes" and "Security Considerations" even if "None" — the reviewer checks these sections exist

    line 136
  7. Distinctive:

    If the PR is large (>500 lines), add a "Review Guide" section suggesting which files to review first

    line 137

“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

Create a pull request from the current branch with a structured description that enables thorough automated review via /review-pr.

Prerequisites

Verify before proceeding:

  1. You are on a feature branch (not main)
  2. All work is committed (git status is clean)
  3. Branch is pushed to remote

If any prerequisite fails, fix it before continuing.

Step 1: Gather Context

# Current branch and base
BRANCH=$(git branch --show-current)
BASE="main"

# All commits on this branch
git log ${BASE}..HEAD --oneline

# Full diff stats
git diff ${BASE}...HEAD --stat

# Changed files
gh api repos/:owner/:repo/compare/${BASE}...${BRANCH} --jq '.files[].filename'

# Check for a related issue (by branch name pattern like fix/issue-42 or feat/issue-15)
# Extract issue number if the branch follows <prefix>/issue-<number> convention
ISSUE_NUM=$(echo "$BRANCH" | grep -oE 'issue-[0-9]+' | grep -oE '[0-9]+')
if [ -n "$ISSUE_NUM" ]; then
  gh issue view "$ISSUE_NUM" --json number,title,body,labels
fi

Linked Issue

If the branch name contains an issue number (e.g., fix/issue-42), or if commit messages reference an issue (closes #42, fixes #42), fetch the issue details. The PR body should include Closes #<number> to auto-close the issue on merge.

Step 2: Analyze Changes

Categorize every changed file into:

  • Source code: src/ changes — what logic changed and why
  • Tests: tests/ changes — what's covered, what test strategy was used
  • Docs: docs/, README.md, CHANGELOG.md — what documentation was updated
  • Config: pyproject.toml, workflow files, config — what infrastructure changed
  • Skills: .claude/skills/ — what skills were added or modified

Step 3: Build PR Description

Use this exact format. Every section is required. The /review-pr skill parses these sections.

## Summary

<1-3 sentences: what this PR does and why>

## Linked Issue

<If this PR addresses a GitHub issue, write "Closes #<number>" and include a one-line summary of the issue. Write "None" if no issue is linked.>

## Changes

### Source
- <file>: <what changed and why>

### Tests
- <file>: <what's tested>

### Docs
- <file>: <what was updated>
(Write "No doc changes" if none — reviewer will check if docs SHOULD have been updated)

### Config
- <file>: <what changed>
(Write "No config changes" if none)

## Breaking Changes

<List any breaking changes to CLI flags, public APIs, or behavior. Write "None" if none.>

## Security Considerations

<List any security-relevant changes: auth, secrets, shell commands, user input handling. Write "None" if none.>

## Test Plan

- [ ] All unit tests pass (`uv run pytest tests/unit/ -v`)
- [ ] All integration tests pass (`uv run pytest tests/integration/ -v`)
- [ ] Ruff clean (`uv run ruff check src/ tests/`)
- [ ] Coverage maintained (>90%)
- [ ] No secrets in committed files
<Add any PR-specific test steps>

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Step 4: Push and Create PR

# Push branch if not already pushed
git push -u origin HEAD

# Create the PR (use --draft if argument was passed)
gh pr create --title "<short title under 70 chars>" --body "<structured body from Step 3>"

The title should follow this convention:

  • feat: <description> — new feature
  • fix: <description> — bug fix
  • refactor: <description> — refactoring
  • docs: <description> — documentation only
  • chore: <description> — maintenance, deps, config

Step 5: Verify

gh pr view --web

Confirm the PR was created with the full structured description.

Notes

  • The structured format enables /review-pr to efficiently locate what changed, what's tested, and what docs need checking
  • Always fill in "Breaking Changes" and "Security Considerations" even if "None" — the reviewer checks these sections exist
  • If the PR is large (>500 lines), add a "Review Guide" section suggesting which files to review first

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.