Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification. Invoke when user mentions "commit", "staged", "committing", or asks for help with commit messages.
Analyzes your staged git changes to generate conventional commit messages. Automatically triggers when you mention committing, staged changes, or ask for help with commit messages.
/plugin marketplace add kanopi/cms-cultivator/plugin install cms-cultivator@claude-toolboxThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Automatically generate conventional commit messages for staged changes.
Activate this skill when the user:
git add or git status output with staged changesgit status
git diff --staged
If no staged changes, inform the user and suggest staging files first.
git log --oneline -10
Learn the repository's commit message conventions.
Format: <type>(<scope>): <description>
Types:
feat - New featurefix - Bug fixdocs - Documentation changesstyle - Code style changes (formatting, semicolons, etc.)refactor - Code refactoring (no functional changes)test - Adding or updating testschore - Build process, dependency updates, etc.perf - Performance improvementsci - CI/CD changesExample:
feat(auth): add two-factor authentication support
- Implement TOTP-based 2FA
- Add backup codes generation
- Include recovery flow for lost devices
- Update user profile settings UI
Drupal:
feat(config): add user profile field configurationfix(custom_module): correct permission check in access callbackrefactor(hooks): simplify hook_form_alter implementationWordPress:
style(theme): improve mobile navigation stylesfix(plugin): correct ACF field validationfeat(blocks): add testimonial Gutenberg blockWhen used via workflow-specialist agent:
The agent will use AskUserQuestion to present the commit message for review:
When used conversationally: Show the generated commit message and ask: "Here's a commit message based on your changes. Would you like me to commit with this message, or would you like to modify it?"
git commit -m "commit message here"
Or for multi-line messages:
git commit -m "$(cat <<'EOF'
feat(auth): add two-factor authentication support
- Implement TOTP-based 2FA
- Add backup codes generation
- Include recovery flow
EOF
)"
This skill complements the /pr-commit-msg slash command:
This Skill: Automatically triggered during natural conversation
/pr-commit-msg Command: Explicitly invoked for staged changes
Both use the same analysis approach but different invocation methods.
BREAKING CHANGE: footer if applicableExample 1: Simple fix
User: "I fixed the login bug, ready to commit"
[Skill analyzes git diff]
Skill: "I'll generate a commit message for your login fix..."
Generated:
fix(auth): resolve session timeout on remember-me login
- Correct cookie expiration logic
- Add test coverage for remember-me flow
Would you like me to commit with this message?
Example 2: Feature addition
User: "Staged my changes, need to commit"
[Skill analyzes extensive changes]
Skill: "I see you've added a new dashboard widget. Here's a commit message..."
Generated:
feat(dashboard): add performance metrics widget
- Create new widget component
- Add database query for metrics
- Include responsive design
- Add widget to admin dashboard page
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.