review-and-ship
cursor/plugins
Review code for bugs and intent fit, run tests, and open or update a PR.
What is review-and-ship?
Automates the pre-ship code review workflow: gathers context from diffs and recent commits, runs or writes targeted tests, identifies correctness and security issues, commits focused changes, and opens or updates a pull request. Use this when you're ready to finalize a feature branch and get it reviewed.
- Compares current branch against base branch to identify all changes
- Runs targeted tests for modified behavior or writes new tests if gaps exist
- Reviews code for correctness, regressions, security issues, and alignment with intent
- Fixes critical issues and re-runs affected tests before committing
- Commits selective files with focused, concise messages
- Pushes branch and opens or updates a GitHub PR with findings summary
How to install review-and-ship
npx skills add https://github.com/cursor/plugins --skill review-and-ship- Git repository with a base branch (typically main or develop)
- GitHub CLI (gh) installed and authenticated
- Test suite configured and runnable in the project
How to use review-and-ship
- 1.Run the skill when your feature branch is ready for review
- 2.Provide context about your changes if needed (recent chat history helps)
- 3.Review the findings summary for critical issues, warnings, and notes
- 4.Address any flagged problems if the skill suggests fixes
- 5.Confirm the PR URL once the skill completes the push and PR creation
Use cases
- Finalizing a feature branch before opening a pull request
- Verifying test coverage for recent code changes
- Catching bugs and security issues before code review
- Updating an existing PR with fixes and re-running checks
- Ensuring commits are focused and unrelated files aren't accidentally included
- Software engineers preparing code for review
- Development teams automating pre-PR quality checks
- Developers working in GitHub-based workflows
review-and-ship FAQ
The skill will decide whether to write focused tests or document the test coverage gap, depending on the scope and criticality of the changes.
No. The skill prioritizes fixing issues rather than bypassing hooks. If pre-commit checks fail, it will address them before finalizing.
Yes. If a PR already exists for the current branch, the skill will update it with new commits and re-run checks.
A categorized report of critical issues, warnings, and notes identified during the review, plus test outcomes and the final PR URL.
The skill is designed for GitHub workflows using the gh CLI. It may not work with other Git hosting platforms without modification.
Full instructions (SKILL.md)
Source of truth, from cursor/plugins.
name: review-and-ship description: Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
Review and ship
Trigger
Reviewing changes before shipping. Close key issues, verify behavior, and open or update a PR.
Workflow
- Gather context: diff against base branch, uncommitted changes, recent commits, changed files, and user intent from recent relevant chats if useful.
- Run targeted tests for changed behavior. If no focused tests exist, decide whether to add them or document the gap.
- Review for correctness, regressions, security, and intent fit. Use parallel subagents for larger diffs.
- Fix critical issues before finalizing and re-run affected tests.
- Commit selective files with a concise message.
- Push branch and open or update a PR.
Suggested Checks
git fetch origin main
git diff origin/main...HEAD
git status
gh pr checks --json name,bucket,state,workflow,link
Guardrails
- Prioritize correctness, security, and regressions over style-only comments.
- Keep commits focused and avoid unrelated file changes.
- If pre-commit checks fail, fix the issues rather than bypassing hooks.
- Use
gh pr checksinstead of GitHub Actions-only commands when judging PR readiness.
Output
- Findings summary (critical, warning, note)
- Tests run and outcomes
- PR URL
Related skills
More from cursor/plugins and the wider catalog.

run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes

setup-pstack
Agent skill from cursor/plugins.

show-me-your-work
Maintain a reviewable decision log (TSV) for long-running or autonomous work, with one row per decision.

swarm
Fan out N parallel workers, drain them, and return one consolidated report.

tdd
Write focused regression tests before fixing bugs with clear, cheap test paths.

teach
Explain code and systems plainly by combining how and why analysis into one clear account.