smart-commit
Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying "commit", "git commit", "save my changes", or ready to commit after making changes.
Best use case
smart-commit is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying "commit", "git commit", "save my changes", or ready to commit after making changes.
Teams using smart-commit should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/smart-commit/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How smart-commit Compares
| Feature / Agent | smart-commit | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Run quality gates, review staged changes for issues, and create a well-crafted conventional commit. Use when saying "commit", "git commit", "save my changes", or ready to commit after making changes.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Smart Commit
## Trigger
Use when saying "commit", "save changes", or ready to commit after making changes.
## Workflow
1. Check current state and identify what to commit.
2. Run quality gates (lint, typecheck, tests on affected files).
3. Scan staged changes for issues.
4. Draft a conventional commit message from the diff.
5. Stage specific files, create the commit.
6. Prompt for learnings from this change.
## Commands
```bash
git status
git diff --stat
npm run lint 2>&1 | tail -5
npm run typecheck 2>&1 | tail -5
npm test -- --changed --passWithNoTests 2>&1 | tail -10
git add <specific files>
git commit -m "<type>(<scope>): <summary>"
```
## Code Review Scan
Before committing, check staged changes in **production code** (not test files) for:
- `console.log` / `debugger` statements (suppressed in test files — see Review Suppressions)
- TODO/FIXME/HACK comments without ticket references (e.g., `TODO(JIRA-123)` is fine)
- Hardcoded secrets or API keys
- Leftover test-only code
Flag any issues before proceeding.
## Commit Message Format
```
<type>(<scope>): <short summary>
<body - what changed and why>
```
**Types:** feat, fix, refactor, test, docs, chore, perf, ci, style
## Guardrails
- Never skip quality gates unless user explicitly says to.
- Stage specific files by name. Never `git add -A` or `git add .`.
- Summary under 72 characters. Body explains *why*, not *what*.
- No generic messages ("fix bug", "update code").
- Reference issue numbers when applicable.
## Output
- Quality gate results (pass/fail)
- Issues found in staged changes
- Suggested commit message
- Commit hash after committing
- Prompt: any learnings to capture?
## Review Suppressions
Do NOT flag these during the pre-commit scan. They add noise without catching real bugs:
- Threshold, config value, or feature flag changes (limits, timeouts, retry counts)
- Import reordering that does not change runtime behavior
- Whitespace-only or formatting-only changes
- Adding or removing `console.log` in test files
- TODO/FIXME comments (tracked separately in issue trackers)
- Variable or parameter renames that do not change behaviorRelated Skills
wrap-up
End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.
thoroughness-scoring
Score every decision point with a Thoroughness Rating (1-10). AI makes the marginal cost of doing things properly near-zero — pick the higher-rated option every time. Includes scope checks to distinguish contained vs unbounded work.
sprint-status
Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.
session-handoff
Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying "continue later", "save progress", "session summary", or "pick up where I left off".
safe-mode
Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
replay-learnings
Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".
pro-workflow
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
permission-tuner
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
parallel-worktrees
Create and manage git worktrees for parallel coding sessions with zero dead time. Use when blocked on tests, builds, wanting to work on multiple branches, context switching, or exploring multiple approaches simultaneously.
orchestrate
Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.
mcp-audit
Audit connected MCP servers for token overhead, redundancy, and security. Use when sessions feel slow or before adding new MCPs.
llm-gate
LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.