Automates the GitHub PR workflow by linting, formatting, testing, committing changes, and opening a pull request with a summary.
Install
mkdir -p .claude/skills/auto-pr && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17424" && unzip -o skill.zip -d .claude/skills/auto-pr && rm skill.zipInstalls to .claude/skills/auto-pr
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
auto_pr — an agent skill by splendidsummer.Key capabilities
- →Run `ruff check .` and fix issues
- →Run `black .` for code formatting
- →Run `pytest -q` to ensure tests pass
- →Create a feature or fix branch with a specific naming convention
- →Commit changes with conventional commit messages
- →Push the branch to GitHub and open a pull request
How it works
This skill automates the process of creating a GitHub pull request by running linters, formatters, tests, creating a branch, committing changes, and pushing to GitHub.
Inputs & outputs
When to use auto_pr
- →Create a pull request for a new feature
- →Open a PR for a bug fix after verifying tests
- →Format code and run linting before pushing changes
- →Draft a structured PR summary based on changes
About this skill
Skill: auto_pr
Goal
Create a clean GitHub PR for the current changes using MCP GitHub.
Rules
- Keep PR small and focused.
- Ensure all tests pass.
- Ensure formatting (ruff/black) passes.
- PR must contain a clear title and bullet-point summary.
Steps
- Run
ruff check .and fix issues. - Run
black .. - Run
pytest -qand ensure green. - Create a branch:
feature/<short-name>orfix/<short-name>. - Commit with message:
- feat: ...
- fix: ...
- test: ...
- docs: ...
- Push branch.
- Use MCP GitHub to open PR.
- Fill PR template:
- What changed
- Why
- How tested
Output format
- Branch name
- Commit hash
- PR title
- PR URL
When not to use it
- →When the goal is not to create a GitHub pull request for current changes
Limitations
- →Requires changes to be small and focused for the PR
- →Requires all tests to pass before opening a PR
- →Requires formatting checks to pass
How it compares
This skill automates the entire pull request workflow, including linting, formatting, and testing, providing a structured and consistent approach compared to manual steps.
Compared to similar skills
auto_pr side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| auto_pr (this skill) | 0 | 5mo | No flags | Intermediate |
| dev | 2 | 5mo | Review | Advanced |
| testing | 0 | 1mo | Review | Advanced |
| ci-pr-helper | 0 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
dev
atopile
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.
testing
hw-native-sys
Testing guide and pre-commit testing strategy for PTO Runtime. Use when running tests, adding tests, or deciding what to test before committing.
ci-pr-helper
lance-format
Run local test/style checks and open GitHub PRs for lance-context. Use when asked to run CI-equivalent checks (uv pytest, ruff/pyright, cargo fmt/clippy/test) and then create a PR with a proper title/body.
country-atlas-ci-fix
dimbo1324
Use when GitHub Actions, pre-commit, tests, typing, lint, SQL lint, Docker smoke, or Playwright checks fail.
code-change-verification
openai
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.
discovering-make-commands
streamlit
Lists available make commands for Streamlit development. Use for build, test, lint, or format tasks.