Agent skill
git
Git operations for committing, pushing, and opening PRs using gh CLI. Use when performing version control tasks. This skill should be used when the user asks to "commit", "push", "create a PR", "ship code", "git status", or mentions git workflow, version control, or pull requests.
Install this agent skill to your Project
npx add-skill https://github.com/cfircoo/claude-code-toolkit/tree/main/skills/git
SKILL.md
<essential_principles>
<git_safety> Never run destructive commands without explicit user request:
- No
git push --forceto main/master - No
git reset --hard - No
--no-verifyflag (skip hooks) - No
git commit --amendon pushed commits
Never push directly to main/master:
- If current branch is
mainormaster, create a new branch before committing/pushing - Use a descriptive branch name based on the changes (e.g.,
fix/login-bug,feat/add-filter) - Only push to feature/fix branches, never directly to the default branch
Always verify before acting:
- Check
git statusbefore staging - Check
git logfor commit style - Check remote tracking before push </git_safety>
<commit_format> End all commit messages with:
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Use HEREDOC for multi-line messages:
git commit -m "$(cat <<'EOF'
Message here
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"
</commit_format>
<pr_format> PR body structure:
## Summary
<1-3 bullet points>
## Test plan
- [ ] Test item 1
- [ ] Test item 2
🤖 Generated with [Claude Code](https://claude.com/claude-code)
</pr_format>
</essential_principles>
- Commit - Stage and commit changes
- Push - Push commits to remote
- PR - Open a pull request
- Ship - Full workflow: commit + push + PR
Wait for response before proceeding.
After reading the workflow, follow it exactly.
<workflows_index>
| Workflow | Purpose |
|---|---|
| commit.md | Stage changes and create commit with proper message |
| push.md | Push commits to remote, create branch if needed |
| pr.md | Create pull request with gh CLI |
| </workflows_index> |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
sqlalchemy-postgres
Expert guidance for SQLAlchemy 2.0 + Pydantic + PostgreSQL. Use when setting up database layers, defining models, creating migrations, or any database-related work. Automatically activated for DB tasks.
ralph-convert-prd
Converts Product Requirements Documents into prd.json format for the Ralph autonomous agent system. Use when preparing PRDs for Ralph execution, breaking down features into atomic user stories, or when the user mentions Ralph, prd.json, or autonomous agent workflows.
ralph-orchestrator
Orchestrates the full Ralph autonomous agent pipeline from requirements gathering to execution. Use when building new features, platforms, or complex tasks that need structured development through spec-interview, PRD generation, and autonomous implementation.
generate-images
Generate and edit images using Nano Banana (Google Gemini image generation). Use whenever Claude Code needs to create new images, edit existing images, generate icons, diagrams, mockups, or any visual content.
create-subagents
Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
manage-slash-commands
Expert guidance for creating and managing Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration. This skill should be used when the user asks to "create a slash command", "add a command", "manage commands", "build a command", or mentions slash commands, custom commands, or command configuration.
Didn't find tool you were looking for?