You are generating commit messages that follow Conventional Commits format.
Generates commit messages following Conventional Commits format. Activated when you request commits via "/commit", prepare-commit-msg hooks, or ask to write a commit message.
/plugin marketplace add grumps/claude-dotfiles/plugin install gdf@gdf-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
You are generating commit messages that follow Conventional Commits format.
<type>(<scope>): <subject>
<body>
<footer>
Examples (customize per repository):
BREAKING CHANGE: descriptionCloses #123, Fixes #456Co-authored-by: Name <email>git diff --cached
Understand what changed and why.
Body is optional but recommended for:
feat(api): add rate limiting middleware
Implements token bucket algorithm with Redis backend.
Configurable via RATE_LIMIT_* environment variables.
Default: 100 requests per minute per IP.
Closes PLAT-123
fix(k8s): correct probe timeout values
Liveness probe was too aggressive causing unnecessary restarts.
Increased timeout from 1s to 5s based on p99 latency metrics.
Also increased failure threshold from 3 to 5.
feat(auth)!: migrate to OAuth 2.0
BREAKING CHANGE: JWT tokens issued before this release are invalid.
Users will need to re-authenticate.
Replaces custom token auth with industry-standard OAuth 2.0.
Improves security and enables SSO integration.
Closes AUTH-45
refactor(db): extract query builders to separate package
No functional changes. Improves testability and reusability
of database query construction logic.
docs(readme): add installation instructions for Windows
Includes PowerShell and WSL setup steps.
! or BREAKING CHANGE: for breaking changesThis 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 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 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.