Commit
Create git commits in spaces/[project]/ with conventional message format. Use for saving progress with quality checks and proper commit messages.
MCP get_skill({ skillId: "commit-3311feb7" })Use this skill with your agent
Create a free account and connect via MCP
# /commit
Create git commits in `spaces/[project]/` with quality checks and conventional message formatting.
## Usage
```bash
/commit yourbench # Interactive commit
/commit yourbench "feat: add auth" # Direct with message
/commit coordinatr --amend # Amend last commit (safety checks)
/commit yourbench "fix: typo" --no-verify # Skip hooks
```
## Two Repos Involved
```
Meta-repo (ideas/): spaces/yourbench/
├── ideas/yourbench/ ├── src/
│ ├── specs/ ├── tests/
│ └── issues/ └── .git/ <- Project git
├── .claude/
└── .git/ <- Meta-repo git
```
**Auto-detect behavior:**
- Only `spaces/[project]/` changed -> commit in project repo
- Only `ideas/` or meta-repo changed -> commit in meta-repo
- Both changed -> ask: "Commit to both repos? (project/meta/both)"
## Execution Flow
### 1. Detect Changes
```bash
# Check meta-repo
git status --porcelain ideas/ .claude/ shared/ resources/
# Check project repo
git -C spaces/[project] status --porcelain
```
### 2. Run Quality Checks (unless --no-verify)
```bash
npm test # or pytest, cargo test, etc.
npm run lint
```
### 3. Review Changes
```bash
git status
git diff --staged
```
### 4. Generate Commit Message
**Conventional commit format:**
```
type(scope): description
[optional body]
Co-Authored-By: Claude <noreply@anthropic.com>
```
**Types:**
- `feat`: New feature
- `fix`: Bug fix
- `docs`: Documentation
- `refactor`: Code refactoring
- `test`: Adding/updating tests
- `chore`: Maintenance
**Auto-detect type from changes:**
- New files in `src/` -> `feat`
- Changes to existing behavior -> `fix` or `refactor`
- Only test files -> `test`
- Only docs -> `docs`
### 5. Link to Issue (if applicable)
If on feature branch like `feature/001-auth`:
```
feat(001): implement user authentication
Refs: TASK-001
```
### 6. Execute Commit
```bash
cd spaces/yourbench
git add .
git commit -m "message..."
```
## Amend Mode
**Safety checks before amending:**
1. Not pushed to remote: `git log @{u}..HEAD`
2. You're the author: `git log -1 --format='%ae'`
## Branch-Aware Messages
| Branch | Commit Type |
|--------|-------------|
| `feature/001-auth` | `feat(001): ...` |
| `bugfix/002-login` | `fix(002): ...` |
| `main` / `develop` | No issue reference |
## Error Handling
| Error | Resolution |
|-------|------------|
| Project not found | Check `spaces/[project]/` exists |
| Not a git repo | Run `git init` in project |
| Tests failing | Fix tests before committing |
| Nothing to commit | No staged/unstaged changes |
| Amend pushed commit | Cannot amend, create new commit |Related Skills
More skills in Software Engineering
Accessibility Standards
Comprehensive web accessibility standards based on WCAG 2.2 AA, with 38+ anti-patterns, legal enforcement context (EAA, ADA Title II), WAI-ARIA patterns, and framework-specific fixes for modern web frameworks and libraries.
Accord
Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision → L1 Requirements → L2 Team Detail → L3 Acceptance Criteria). No code. Use when authoring cross-team specs, building L0-L3 packages, or aligning Biz/Dev/Design on a single source of truth.
Acquire Codebase Knowledge
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
Acreadiness Assess
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.
Acreadiness Generate Instructions
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
Acreadiness Policy
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.
Explore Other Categories
Skills from other categories with shared topics
Brief
Create or update project brief through interactive discovery. Use when starting any new idea, revisiting an idea after time away, or when vision feels unclear.
Critique
Challenge idea assumptions with skeptical VC-style evaluation. Use when user requests critique, validation, or 'is this a good idea' assessment.
Daily Review
Complete daily journal review. Use at end of day or next morning to fill in journal sections, review highlights, and plan tomorrow. Triggers on "daily review", "end of day", "journal review", "what did I do today".