Agent skill
git-commit
Commit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/git-commit-sequenzia-agent-alchemy-3
SKILL.md
Git Commit
Create a commit with a conventional commit message based on staged changes. Automatically stages all changes and analyzes the diff to generate an appropriate commit message.
Workflow
Execute these steps in order.
Step 1: Check Repository State
Check for changes to commit:
git status --porcelain
- If output is empty, report: "Nothing to commit. Working directory is clean." and stop.
- If changes exist, continue to Step 2.
Step 2: Stage All Changes
Stage all changes including untracked files:
git add .
Report: "Staged all changes."
Step 3: Analyze Changes
View the staged diff to understand what changed:
git diff --cached --stat
git diff --cached
Analyze the diff to determine:
- The type of change (feat, fix, docs, refactor, etc.)
- The scope (optional, based on affected files/modules)
- A concise description of what changed
Step 4: Construct Commit Message
Build a conventional commit message following this format:
<type>(<optional-scope>): <description>
[optional body]
Types:
feat- New featurefix- Bug fixdocs- Documentation onlystyle- Formatting, no code changerefactor- Code restructuring without behavior changetest- Adding or updating testschore- Maintenance tasksbuild- Build system or dependenciesci- CI configurationperf- Performance improvement
Rules:
- Use imperative mood ("add" not "added")
- Use lowercase
- No trailing period
- Keep description under 72 characters
- Add a body only for complex changes or breaking changes
- Do NOT add co-author, attribution, or "Generated with" lines
Step 5: Create Commit
Create the commit using a heredoc for proper formatting:
git commit -m "$(cat <<'EOF'
<commit message here>
EOF
)"
Step 6: Handle Result
On success:
- Report the commit hash: "Committed: {short_hash} - {message}"
On pre-commit hook failure:
- Report: "Pre-commit hook failed. The commit was NOT created."
- Explain what the hook reported
- Instruct: "Fix the issues above and run the commit command again. Do NOT use --amend as that would modify the previous commit."
Error Recovery
If the commit fails:
- Hook failure: Fix the reported issues, then stage and commit again (do NOT amend)
- Unstage changes:
git reset HEADto unstage without losing changes
Notes
- This command stages ALL changes including untracked files
- Pre-commit hooks run automatically; their failures mean no commit was created
- Always create a NEW commit after hook failure, never amend the previous commit
Integration Notes
What this component does: Creates git commits with conventional commit messages by analyzing staged changes.
Capabilities needed:
- Shell command execution (for git operations)
Adaptation guidance:
- This skill is highly portable — it primarily executes git commands
- The conventional commit format (type(scope): description) is a widely-adopted standard
- Originally ran on a lightweight model — suitable for any model tier
Configurable parameters: None
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?