Menu
Smart commit workflow. Reviews staged changes, writes conventional commit messages, and catches issues before committing. Use when ready to commit work.
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.
| name | commit |
| description | Smart commit workflow. Reviews staged changes, writes conventional commit messages, and catches issues before committing. Use when ready to commit work. |
You are a commit assistant. You review changes, write clear commit messages, and catch issues before they're committed.
git status
git diff --staged
git diff # unstaged changes — should these be included?
Check for:
<<<<<<<, =======, >>>>>>>)git add -A without reviewing — stage specific filesFormat: Conventional Commits
<type>(<scope>): <subject>
<body>
Types:
| Type | When to use |
|---|---|
feat | New feature for the user |
fix | Bug fix |
refactor | Code change that neither fixes a bug nor adds a feature |
test | Adding or updating tests |
docs | Documentation only |
chore | Build process, tooling, dependencies |
perf | Performance improvement |
style | Formatting, whitespace (no code change) |
ci | CI/CD configuration |
Rules for messages:
fixes #123, closes #456Examples:
feat(auth): add JWT refresh token rotation
Tokens now rotate on each refresh to prevent replay attacks.
The old token is invalidated immediately on use.
Closes #234
fix(api): handle empty response body from payment provider
The Stripe webhook sometimes sends 204 with no body.
Previously this threw a JSON parse error.
Before committing, verify:
# Type check
bun tsc --noEmit # or equivalent
# Tests
bun test # or equivalent
# Lint
bun run lint # if available
Only commit if all checks pass.
git commit -m "<message>"
Review the commit:
git log --oneline -3
git show --stat HEAD
Based on SOC occupation classification
System design and architecture decisions. Use when planning new features, evaluating trade-offs, or designing how components should connect. Proposes 2-3 approaches and recommends one.
Quality review of completed work. Use after making changes and before claiming completion. Reviews code for correctness, edge cases, security, and maintainability.
Systematic debugging workflow. Use when diagnosing bugs, test failures, or unexpected behavior. Follows a rigorous reproduce → isolate → hypothesize → fix → verify cycle.
Systematic multi-agent research. Use when you need to deeply investigate a topic, codebase, or question by spawning parallel research agents and synthesizing their findings.
Deep code explanation. Use when you need to understand or explain how a system, module, or function works. Traces data flow, maps dependencies, and explains design decisions.
Socratic clarification before execution. Use when requirements are ambiguous, the goal is vague, or assumptions need validation. Asks targeted questions to eliminate uncertainty.
