Menu
Create a clean, review-ready pull request with a good title, structured description, linked issues, and appropriate reviewers.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | creating-pr |
| description | Create a clean, review-ready pull request with a good title, structured description, linked issues, and appropriate reviewers. |
| user-invocable | true |
Package work into a pull request that's easy to review and merge.
Before creating the PR:
# Ensure branch is up to date with base
git fetch origin
git rebase origin/main # or merge, depending on project convention
# Check what will be in the PR
git log origin/main..HEAD --oneline
git diff origin/main --stat
Squash fixup commits if the project prefers clean history. Keep logical commits separate if the project prefers granular history.
Format: <type>: <short description>
| Type | When |
|---|---|
feat | New feature |
fix | Bug fix |
refactor | Code change that neither fixes a bug nor adds a feature |
docs | Documentation only |
test | Adding or fixing tests |
chore | Build, CI, deps, or tooling |
perf | Performance improvement |
Examples:
feat: add dark mode toggle to settings pagefix: prevent duplicate form submissions on checkoutrefactor: extract auth middleware into shared moduleUse this structure:
## Summary
1-3 sentences explaining what this PR does and why.
Closes #123
## Changes
- Added `ThemeToggle` component with system/light/dark options
- Updated `Layout` to read theme from context
- Added theme persistence to localStorage
## Test Plan
- [ ] Toggle between light/dark/system themes
- [ ] Refresh page โ theme persists
- [ ] Check no flash of unstyled content on load
Before requesting review:
console.log, TODO, commented-out code)npm testnpx tsc --noEmitnpm run lint.env, lockfile conflicts)git push -u origin HEAD
gh pr create --title "<title>" --body "$(cat <<'EOF'
## Summary
...
## Changes
...
## Test Plan
...
EOF
)"
Generate or edit images using the OpenAI Image API (gpt-image-2). Use when the user asks to generate, create, draw, render, illustrate, mock up, or edit an image, icon, logo, mockup, illustration, OG image, blog hero, marketing asset, or similar visual. Also use when the user supplies a reference image and asks to modify, restyle, or remix it. Triggers on: "generate an image", "create an image", "make a picture of", "edit this image", "restyle this", "make a mockup of", "draw a", "render a", "illustration of".
When the same multi-step workflow repeats in Cursor (user corrections or agent redos), capture it as a new SKILL.md under .cursor/skills/ so future sessions load it automatically.
After navigating and interacting in Cursor's built-in browser, use browser_network_requests to audit every fetch/XHR for failures, slowness, duplicate calls, and suspicious payloads. Use for API-heavy pages and after backend or client networking changes.
When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel. Use for multi-job CI failures where jobs are independent.
Run four parallel read-only subagents that each review the same diff from a different lens โ security, performance, correctness, and readability โ then merge findings into one report. Use before merging large or risky PRs.
Execute a user flow step-by-step in Cursor's built-in browser while documenting each action, then emit a Playwright test that replays the same flow using stable selectors derived from the accessibility tree.