commit

Commit staged changes with appropriate commit messages

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "commit" with this command: npx skills add gendosu/agent-skills/gendosu-agent-skills-commit

Commits staged changes with an appropriate commit message using the git-operations-specialist skill.

Core Guidelines

Before starting any task, read and follow /key-guidelines


Dependencies

  • use git-operations-specialist skill

Instructions

IMPORTANT: Use the git-operations-specialist skill (via Skill tool) for ALL git-related operations in this command.

Analyze the staged changes and safely commit them with an appropriate commit message.

Required Execution Items

  1. Check Staging Status: Run git status to confirm what changes are staged

  2. Review Staged Changes: Use git diff --staged to review the content of staged changes

  3. Create Commit: Commit the staged changes with an appropriate commit message

  4. Verify Commit: Run git status after committing to confirm the commit was successful

Commit Message Guidelines

  • Follow the .gitmessage template format
  • Use appropriate commit type prefixes: feat, fix, refactor, docs, style, test, chore
  • Write clear, concise messages that describe the change

⚠️ Important Constraints

  • Never use any git add commands – Only commit what is already staged
  • Use HEREDOC – Maintain proper formatting of commit messages
  • Stage verification first – Always check what's staged before committing
  • Single commit – Create one commit for all currently staged changes

Example Usage

If you have already staged changes:

# Staged files:
- apps/api/src/routes/timeline.ts
- apps/api/src/types/timeline.ts

This command will create a single commit containing both files with an appropriate message like:

feat: タイムラインAPIのルートと型定義を追加

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

commit

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

commit

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

todo-task-planning

No summary provided by upstream source.

Repository SourceNeeds Review