ac-commit-manager
The ac-commit-manager automates creation of well-structured git commits for completed features in autonomous coding workflows. Use it when implementing features to ensure consistent commit messages, validate changes, stage files, and maintain clear project history with atomic, traceable commits that include implementation code, tests, and descriptive context.
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry /tmp/ac-commit-manager && cp -r /tmp/ac-commit-manager/skills/agent/ac-commit-manager ~/.claude/skills/ac-commit-managerSKILL.md
# AC Commit Manager
Manage git commits for completed feature implementations.
## Purpose
Creates well-structured git commits after each feature completion, ensuring proper version control and clear project history.
## Quick Start
```python
from scripts.commit_manager import CommitManager
manager = CommitManager(project_dir)
result = await manager.commit_feature("auth-001")
```
## Commit Workflow
```
1. VALIDATE → Ensure changes are safe to commit
2. STAGE → Stage relevant files
3. MESSAGE → Generate descriptive commit message
4. COMMIT → Create the commit
5. VERIFY → Verify commit was created
6. TAG → Optional: tag milestone commits
```
## Commit Message Format
```
feat(auth): implement user registration (#auth-001)
- Add registration endpoint with email/password
- Implement password hashing with bcrypt
- Add input validation for email format
- Create user model and database migration
Test: All 5 acceptance criteria passing
Coverage: 92%
Feature: auth-001
Status: passes
```
## Commit Result
```json
{
"success": true,
"commit_hash": "abc123def456",
"feature_id": "auth-001",
"message": "feat(auth): implement user registration",
"files_changed": [
"src/auth/register.py",
"src/models/user.py",
"tests/test_auth_001.py"
],
"stats": {
"insertions": 145,
"deletions": 12,
"files_changed": 3
}
}
```
## Commit Categories
Based on feature category:
- `feat`: New features
- `fix`: Bug fixes
- `refactor`: Code refactoring
- `test`: Test additions/changes
- `docs`: Documentation
- `chore`: Maintenance tasks
- `perf`: Performance improvements
## Pre-Commit Checks
```python
# Run validation before commit
validation = await manager.pre_commit_check()
if validation.can_commit:
await manager.commit_feature(feature_id)
```
Checks include:
- No uncommitted sensitive files
- All tests pass
- Linting passes
- No merge conflicts
## Atomic Commits
Each feature gets exactly one commit:
- Includes implementation + tests
- Self-contained and revertable
- Descriptive message with context
## Configuration
```json
{
"require_tests_pass": true,
"require_lint_pass": true,
"auto_stage_tests": true,
"message_template": "{{type}}({{scope}}): {{description}}",
"protected_files": [".env", "credentials.*"],
"sign_commits": false
}
```
## Rollback Support
```python
# Rollback last commit
await manager.rollback_last_commit()
# Rollback to specific feature
await manager.rollback_to_feature("auth-003")
```
## Integration
- Uses: `ac-code-validator` for pre-commit checks
- Input: Completed features from `ac-task-executor`
- Updates: `ac-state-tracker` with commit info
## API Reference
See `scripts/commit_manager.py` for full implementation.Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project
Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions. Part of cursor-rules-java project
>
Generated skill from request: trinity auto-boot validator
Create your OpenAI Agents SDK skill in one prompt, then learn to improve it throughout the chapter
Create your OpenAI Agents SDK skill in one prompt, then learn to improve it throughout the chapter
Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter