github-pr-creator
Skill0 starsChanged 2 months agoMITView on GitHub
Guides agents through creating high-quality GitHub pull requests with clear problem statements, test evidence, and issue links.
- Commits and pushes
In this repository49 other files it gives its agents.
- bug-reproducerSkill
- claim-checkerSkill
- command-failure-diagnoserSkill
- config-risk-reviewerSkill
- csv-validatorSkill
- deployment-checklist-makerSkill
- diff-reviewerSkill
- factual-summarizerSkill
- field-extractorSkill
- api-contract-testerSkill
- database-migration-helperSkill
- security-vulnerability-fixerSkill
- git-commit-stagerSkill
- git-conflict-resolverSkill
- github-actions-debuggerSkill
- github-issue-triagerSkill
- github-pr-reviewerSkill
- go-code-qualitySkill
- go-lint-and-vetSkill
- go-testingSkill
- json-schema-converterSkill
- lint-and-typecheckSkill
- meaning-preserving-editorSkill
- meeting-notes-to-actionsSkill
- minimal-bug-fixSkill
- option-comparatorSkill
- py-code-qualitySkill
- py-lint-and-typecheckSkill
- py-testingSkill
- readme-writerSkill
- regression-test-writerSkill
- release-notes-drafterSkill
- repo-inspectorSkill
- research-briefSkill
- reversible-cleanup-plannerSkill
- rust-clippy-checkSkill
- rust-code-qualitySkill
- rust-testingSkill
- small-refactorSkill
- status-updateSkill
- step-by-step-tutorialSkill
- step-decomposerSkill
- tabular-analyzerSkill
- task-briefSkill
- test-runner-debuggerSkill
- ts-code-qualitySkill
- ts-lint-and-typecheckSkill
- ts-testingSkill
- skill-templateSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use this skill when:
- Very specific: line 20
Do not use to review another contributor's PR.
- Very specific: line 21
Do not use to write end-user release notes.
- Very specific: line 29
If title is not specified: generate title from git log -n 1 --pretty=%s.
- Distinctive: line 33
Follow these numbered actions:
- Distinctive: line 35
Check git status and ensure all intended changes are committed.
- Distinctive: line 42
Ensure branch builds and tests pass locally.
- Very specific: line 47
If PR introduces breaking API changes: prepend BREAKING CHANGE: in title and description.
- Distinctive: line 48
Always link issue number if known.
- Distinctive: line 85
Stop and ask the user when:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub PR Creator
Prepares structured, review-ready GitHub Pull Requests. Ensures every PR includes problem context, verification commands, and issue references (Fixes #123).
1. Purpose
Turn raw branch commits into a professional Pull Request description that reviewers can approve quickly.
2. When to Use
Use this skill when:
- Opening a pull request after completing code and test changes.
- Preparing PR descriptions via
gh pr createor web interface. - Linking pull requests to issues (
Closes #42).
3. When Not to Use
- Do not use to review another contributor's PR; use
github-pr-reviewer. - Do not use to write end-user release notes; use
release-notes-drafter.
4. Required Inputs
title: Short PR title following Conventional Commits (e.g.feat(auth): add token refresh).branch_name: Source branch name.base_branch: Target branch (default:main).
5. Missing-Input Behavior
- If title is not specified: generate title from
git log -n 1 --pretty=%s. - Inspect
git diff <base_branch>...HEADto verify changed files before writing summary.
6. Procedure
Follow these numbered actions:
- Action 1: Verify Git Diff
- Check
git statusand ensure all intended changes are committed.
- Check
- Action 2: Draft PR Body
- Summary of Changes.
- Motivation / Linked Issue (
Fixes #...). - Testing Evidence (command and output).
- Breaking Changes (if any).
- Action 3: Check Branch Health
- Ensure branch builds and tests pass locally.
- Action 4: Emit PR Content
- Format per Section 8.
7. Decision Rules
- If PR introduces breaking API changes: prepend
BREAKING CHANGE:in title and description. - Always link issue number if known.
8. Output Format
Emit the PR description using this template:
## Description
[Brief 1-2 sentence summary of what this PR does.]
## Linked Issue
Fixes #[issue_number]
## Key Changes
- [Change 1]
- [Change 2]
## Testing & Verification
- Test command: `[e.g. npm test]` -> `[34 passed, 0 failed]`
- Manual check: `[curl or CLI test]`
## Checklist
- [x] Unit/integration tests added or updated
- [x] Linters and type-checkers pass with exit code 0
- [x] Documentation updated (if applicable)9. Verification Checklist
- PR title follows Conventional Commits.
- Test evidence included.
- Issue linked with
Fixes #.... - Zero uncommitted temporary files.
10. Common Failures and Recovery
| Failure Symptom | Cause | Recovery Action |
| Missing test proof | Forgetting to run tests | Run test command and copy summary into PR body. |
11. Stop or Escalation Conditions
Stop and ask the user when:
- Target base branch is protected and requires specialized credentials.
12. Examples
Example 1: Successful Execution
Input:
Branch: feat/jwt-refresh
Base: main
Issue: #88
Changes: Added refresh token endpoint, updated testsOutput:
## Description
Implements the `/v1/auth/refresh` endpoint allowing clients to exchange valid refresh tokens for short-lived access tokens.
## Linked Issue
Fixes #88
## Key Changes
- Added `POST /v1/auth/refresh` route in `src/routes/auth.ts`.
- Added refresh token database lookup with revocation checks.
- Added regression test in `tests/auth_refresh.test.ts`.
## Testing & Verification
- Automated tests: `npm test tests/auth_refresh.test.ts` (4 passed, 0 failed).
- Type check: `npx tsc --noEmit` exited code 0.
## Checklist
- [x] Unit/integration tests added
- [x] Linters and type-checkers pass
- [x] Documentation updatedExample 2: Ambiguous or Missing Input
Input:
Make a PR.Output:
### GitHub PR Creator: Halted - Missing Details
- **Status**: Halted
Please provide:
1. The branch name or target issue.
2. The core objective of the pull request.Example 3: Expected Final Output
Output:
## Description
Fixes zero division crash when calculating cart discounts with 0 items.
## Linked Issue
Fixes #104
## Key Changes
- Added defensive check in `src/cart.py` for empty item list.
## Testing & Verification
- `pytest tests/test_cart.py` passed (8 passed in 0.05s).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.

