workflow-integration-git
Git commit workflow with conventional commits, artifact cleanup, and optional push/PR creation
Best use case
workflow-integration-git is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Git commit workflow with conventional commits, artifact cleanup, and optional push/PR creation
Teams using workflow-integration-git 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/workflow-integration-git/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How workflow-integration-git Compares
| Feature / Agent | workflow-integration-git | 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?
Git commit workflow with conventional commits, artifact cleanup, and optional push/PR creation
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.
SKILL.md Source
# CUI Git Workflow Skill
**EXECUTION MODE**: You are now executing this skill. DO NOT explain or summarize these instructions to the user. IMMEDIATELY begin the workflow below based on the task context.
Provides git commit workflow following conventional commits specification. Includes artifact cleanup, commit formatting, and optional push/PR creation.
## What This Skill Provides
### Commit Workflow (Absorbs commit-changes Agent)
Complete git commit workflow:
- Artifact detection and cleanup
- Commit message generation following conventional commits
- Optional push to remote
- Optional PR creation
### Commit Standards
- **Format:** `<type>(<scope>): <subject>`
- **Types:** feat, fix, docs, style, refactor, perf, test, chore
- **Quality:** imperative mood, lowercase, no period, max 50 chars
## When to Activate This Skill
- Committing changes to repository
- Generating commit messages from diffs
- Cleaning build artifacts before commit
- Creating pull requests after commit
## Workflow: Commit Changes
**Purpose:** Commit all uncommitted changes following Git Commit Standards.
**Input Parameters:**
- **message** (optional): Custom commit message
- **push** (optional): Push after committing
- **create-pr** (optional): Create PR after pushing
### Steps
**Step 1: Load Commit Standards**
```
Read standards/git-commit-standards.md
```
**Step 2: Check for Uncommitted Changes**
```bash
git status --porcelain
```
If no changes → Report "No changes to commit"
**Step 3: Analyze Changes for Artifacts**
Use Glob to detect artifacts:
```
Glob pattern="**/*.class"
Glob pattern="**/*.temp"
```
Artifact patterns to clean:
- `*.class` files in `src/` directories
- `*.temp` temporary files
- Files in `target/` or `build/` accidentally staged
**Step 4: Clean Artifacts**
**Safe Deletions (automatic):**
- `*.class` in `src/main/java` or `src/test/java`
- `*.temp` anywhere
- Delete using `rm <file>`
**Uncertain Cases (ask user):**
- Files >1MB
- Files outside safe list
- Files in `target/` that are tracked
**Step 5: Generate Commit Message**
If custom message provided:
- Validate format
- Use provided message
If no message:
- Analyze diff using script:
```bash
python3 .plan/execute-script.py pm-workflow:workflow-integration-git:git-workflow analyze-diff --file <diff-file>
```
- Generate message following standards
**Multi-type priority:** fix > feat > perf > refactor > docs > style > test > chore
**Step 6: Stage and Commit**
```bash
git add .
git commit -m "$(cat <<'EOF'
{commit_message}
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"
```
**Step 7: Push (Optional)**
If `push` parameter:
```bash
git push
```
**Step 8: Create PR (Optional)**
If `create-pr` parameter:
```bash
gh pr create --title "{title}" --body "$(cat <<'EOF'
## Summary
{summary}
🤖 Generated with [Claude Code](https://claude.com/claude-code)
EOF
)"
```
### Output
```json
{
"status": "success",
"commit_hash": "abc123",
"commit_message": "feat(http): add retry configuration",
"files_changed": 5,
"artifacts_cleaned": 2,
"pushed": true,
"pr_url": "https://github.com/..."
}
```
## Scripts
**Script**: `pm-workflow:workflow-integration-git:git-workflow`
| Command | Parameters | Description |
|---------|------------|-------------|
| `format-commit` | `--type --subject [--scope] [--body] [--breaking] [--footer]` | Format commit message |
| `analyze-diff` | `--file` | Analyze diff for commit suggestions |
### format-commit
Format commit message following conventional commits.
```bash
python3 .plan/execute-script.py pm-workflow:workflow-integration-git:git-workflow format-commit \
--type feat \
--scope http \
--subject "add retry config" \
[--body "Extended description..."] \
[--breaking "API changed"] \
[--footer "Fixes #123"]
```
**Parameters**:
- `--type` (required): Commit type (feat, fix, docs, style, refactor, perf, test, chore)
- `--subject` (required): Commit subject line
- `--scope`: Optional component scope
- `--body`: Optional commit body
- `--breaking`: Optional breaking change description
- `--footer`: Optional additional footer
**Output** (JSON):
```json
{
"type": "feat",
"scope": "http",
"subject": "add retry config",
"formatted_message": "feat(http): add retry config\n\n🤖 Generated...",
"validation": {"valid": true, "warnings": []},
"status": "success"
}
```
### analyze-diff
Analyze diff file to suggest commit message parameters.
```bash
python3 .plan/execute-script.py pm-workflow:workflow-integration-git:git-workflow analyze-diff \
--file changes.diff
```
**Parameters**:
- `--file` (required): Path to diff file to analyze
**Output** (JSON):
```json
{
"mode": "analysis",
"suggestions": {
"type": "feat",
"scope": "auth",
"subject": null,
"detected_changes": ["Significant new code added"],
"files_changed": ["src/main/java/auth/Login.java"]
},
"status": "success"
}
```
## Standards (Load On-Demand)
### Git Commit Standards
```
Read standards/git-commit-standards.md
```
Provides:
- Conventional commits format specification
- Commit type definitions and usage
- Subject, body, and footer guidelines
- Best practices and anti-patterns
## Critical Rules
**Artifacts:** NEVER commit `*.class`, `*.temp`, `*.backup*`
**Permissions:** NEVER push without `push` param, NEVER create PR without `create-pr` param
**Standards:** Follow conventional commits format, add Co-Authored-By footer
**Safety:** Ask user if uncertain about file deletion
## Integration
### Skills Using This Skill
- **plan-finalize** - Commits and creates PR after plan execution
- **plan-execute** - May commit after task completion
### Related Skills
- **manage-lifecycle** - Phase transitions that trigger finalize
## Quality Verification
- [x] Self-contained with relative path pattern
- [x] Progressive disclosure (standards loaded on-demand)
- [x] Script outputs JSON for machine processing
- [x] commit-changes agent functionality absorbed
- [x] Clear workflow definition
- [x] Standards documentation maintained
## References
- Conventional Commits: https://www.conventionalcommits.org/
- Git Commit Best Practices: https://cbea.ms/git-commit/
- Angular Commit Guidelines: https://github.com/angular/angular/blob/main/CONTRIBUTING.md#commitRelated Skills
julien-workflow-advice-codex
Get OpenAI Codex CLI's opinion on code, bugs, or implementation. Use when you want a second AI perspective during coding sessions.
jira-integration
Agent Skill: Comprehensive Jira integration through lightweight Python scripts. AUTOMATICALLY TRIGGER when user mentions Jira URLs like 'https://jira.*/browse/*', 'https://*.atlassian.net/browse/*', or issue keys like 'PROJ-123'. Use when searching issues (JQL), getting/updating issue details, creating issues, transitioning status, adding comments, logging worklogs, managing sprints and boards, creating issue links, or formatting Jira wiki markup. If authentication fails, offer to configure credentials interactively. Supports both Jira Cloud and Server/Data Center with automatic authentication detection. By Netresearch.
fal-workflow
Generate workflow JSON files for chaining AI models
Directus AI Assistant Integration
Build AI-powered features in Directus: chat interfaces, content generation, smart suggestions, and copilot functionality
create-workflow
Create Jazz workflow automation files (WORKFLOW.md). Use this for scheduling Jazz agents to run recurring tasks. For OS-level scripts/commands, use create-system-routine.
airflow-workflows
Apache Airflow DAG design, operators, and scheduling best practices.
ai-integration
AI/LLM integration patterns - Claude API, fal.ai, streaming, tool use
ai-annotation-workflow
Эксперт по data annotation. Используй для ML labeling, annotation workflows и quality control.
adaptive-workflows
Self-learning workflow system that tracks what works best for your use cases. Records experiment results, suggests optimizations, creates custom templates, and builds a personal knowledge base. Use to learn from experience and optimize your LLM workflows over time.
accessibility-object-model-integration
Programmatic manipulation of the accessibility tree to support complex custom controls in React.
academic-data-integration
When the user needs to integrate multiple data sources (Canvas API, user memory, file systems) to create comprehensive academic reports. This skill combines course information, assignment details, submission status, and user context to generate actionable insights. Triggers include requests that involve cross-referencing multiple data sources or creating consolidated academic reports from disparate systems.
302ai-api-integration
ALWAYS use this skill when user needs ANY API functionality (AI models, image generation, video, audio, text processing, etc.). Automatically search 302.AI's 1400+ APIs and generate integration code. Use proactively whenever APIs or AI capabilities are mentioned.