Agent skill
pr-create
Creates GitHub pull requests with properly formatted conventional commit-style titles. Use when creating PRs, submitting changes for review, or when user says /pr, /pr-create, or asks to create a pull request.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/pr-create-dohernandez-claude-project-skill
SKILL.md
PR Create
Purpose
Creates GitHub pull requests with conventional commit-style titles and structured bodies.
Quick Reference
- Creates: GitHub PR via
gh pr create - Requires: GitHub CLI installed and authenticated, committed changes on a feature branch
Prerequisites
Before creating a PR, verify:
- gh CLI installed:
gh --version- if missing:brew install gh - gh CLI authenticated:
gh auth status- if not:gh auth login
PR Title Format
<type>(<scope>): <subject>
Types
| Type | Use for |
|---|---|
feat |
New features |
fix |
Bug fixes |
chore |
Maintenance, refactoring |
docs |
Documentation |
test |
Test changes |
perf |
Performance improvements |
ci |
CI/CD changes |
Scopes
workflows- GitHub Actions workflow filesscripts- Shell scripts (setup, orchestration)ci- CI pipeline configuration and logicrunner- Self-hosted runner setup and provisioningconfig- Configuration files
Title Rules
- Max 50 characters
- Capitalized first letter after colon
- No period at the end
- Be specific - avoid "improve", "enhance", "update"
- NO AI ATTRIBUTION - STRICTLY FORBIDDEN
AI Attribution Policy
COMPLETE VIOLATION - Never include ANY of the following in PR titles, bodies, or commits:
Co-Authored-By: Claude,Co-Authored-By: GPT, or any AI name- AI-related emojis
- "Generated by", "Created with", or similar phrases
- Any reference to AI tools (Claude, ChatGPT, Copilot, etc.)
PRs and commits must appear as human-authored work. This is a strict project requirement.
PR Body Template
## Summary
[2-3 sentences summarizing what changed and why]
## Changes
- [bullet point of change 1]
- [bullet point of change 2]
- [bullet point of change 3]
## Checklist
- [ ] Code follows project conventions
- [ ] Documentation updated (if needed)
- [ ] Changes tested locally (if applicable)
Fill in Summary and Changes with specifics. Check applicable Checklist items with [x].
User Review Step
Before creating the PR, present it to the user for review:
## PR Preview
**Title:** feat(workflows): Add retry logic to E2E pipeline
**Body:**
## Summary
Adds retry logic to the E2E test pipeline to handle transient network failures
during consensus deployment.
## Changes
- Add retry wrapper for task consensus:deploy
- Configure max 3 retries with exponential backoff
- Log retry attempts for debugging
## Checklist
- [x] Code follows project conventions
- [x] Documentation updated (if needed)
- [ ] Changes tested locally (if applicable)
---
Any changes I should make?
Wait for user confirmation:
- If user says "no" or confirms -> create the PR
- If user requests changes -> incorporate feedback and show again
Automation
See skill.yaml for the full procedure and patterns.
See sharp-edges.yaml for common failure modes.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?