.claude/skills/commit/SKILL.md
Create a well-formatted git commit with PROJECT-STATUS.md updates. Use after completing implementation.
npx skillsauth add lucidlabs-hq/agent-kit commitInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create a well-formatted commit with automatic PROJECT-STATUS.md and README updates.
CURRENT_BRANCH=$(git branch --show-current)
If on main:
⚠️ WARNING: You are committing to main directly.
All changes should go through feature branches.
Expected workflow:
1. /execute creates a feature branch
2. /commit commits on the feature branch
3. /pr pushes and creates a Pull Request
Continue anyway? (Only for hotfixes or initial setup)
Ask user for confirmation before proceeding on main. For normal feature work, suggest running /execute first to create the branch.
If on a feature branch: Continue normally.
Run these commands to understand what's being committed:
git status
git diff HEAD --stat
git diff HEAD
Run quality checks before committing. ALL must pass:
# a) Tests
pnpm run test # fail = STOP
# b) Lint
pnpm run lint # fail = STOP
# c) Type check
pnpm run type-check # fail = STOP
If any command fails: fix the issue, then re-run. Do NOT commit with failing checks.
After automated checks pass, run code-reviewer subagent on git diff --cached:
See .claude/reference/quality-gates.md for full gate architecture.
| Type | When to Use | Updates README? |
|------|-------------|-----------------|
| feat | New feature | Yes |
| fix | Bug fix | Yes |
| docs | Documentation only | No |
| style | Formatting, no code change | No |
| refactor | Code restructure | No |
| test | Adding tests | No |
| chore | Build, dependencies | No |
| perf | Performance improvement | Yes |
git add -A
Or stage specific files:
git add path/to/file
Use Conventional Commits format:
<type>(<scope>): <description>
[optional body]
[optional footer]
| Scope | Description |
|-------|-------------|
| ui | UI components |
| api | API endpoints |
| agent | AI agent |
| db | Database schema |
| auth | Authentication |
| config | Configuration |
| skills | Claude Code skills |
# Feature
git commit -m "feat(ui): add dashboard overview component"
# Bug fix
git commit -m "fix(api): handle null response in ticket endpoint"
# With body
git commit -m "feat(agent): implement ticket classification
- Add ClassifyTicket tool
- Integrate with Sabine agent
- Add confidence scoring"
After committing, update PROJECT-STATUS.md:
| Date | Type | Description |
|------|------|-------------|
| [Today] | [feat/fix/etc] | [Commit description] |
If working on a plan, mark completed tasks:
### Completed Tasks
- [x] Task that was just completed
Only for feat, fix, perf commits:
Add to README "Features" or "Current Status" section:
## Features
- [New feature description]
Add to README "Recent Changes" or "Changelog" section:
## Recent Changes
- Fixed: [Bug description]
If PROJECT-STATUS.md or README were updated:
git add PROJECT-STATUS.md README.md
git commit --amend --no-edit
# Or create a separate commit:
git commit -m "docs: update project status and readme"
git log -1 --oneline
git show --stat HEAD
## Commit Created
**Hash:** [short hash]
**Type:** [feat/fix/etc]
**Message:** [commit message]
### Files Changed
- [X files changed, Y insertions, Z deletions]
### Tracking Updated
- PROJECT-STATUS.md: [Yes/No]
- README.md: [Yes/No - only for feat/fix/perf]
### Next Steps
- [Continue with next task / Run /validate / Push to remote]
fix(api): handle null response (#42)BREAKING CHANGE: in footerdevelopment
Deploy invoice-accounting-assistant to HQ server. Runs tests first (TDD), then builds and deploys. Use when ready to push changes to staging/production.
testing
Visual UI verification with agent-browser. Use after implementing UI components to take screenshots, verify interactions, and self-check your work. FASTER than E2E tests.
documentation
Update README with current project status and features. Use after completing features.
tools
--- name: time-report description: Cross-project time report. Aggregates all session data from ~/.claude-time/sessions/. Use to see how much time was spent across all projects. disable-model-invocation: true allowed-tools: Bash, Read argument-hint: [all | this-week | this-month | last-month | {project-name}] --- # Time Report: Cross-Project Session Overview ## Objective Read ALL session files from `~/.claude-time/sessions/*.json` and produce an aggregated time report. Supports filtering by pe