This skill should be used for guidance on commit size, scope, and creating reviewable commits, splitting large changes, commit hygiene
Provides guidance on creating atomic commits with proper scope, size, and messages. Triggers when you need to split large changes or complete devloop tasks into reviewable commits.
/plugin marketplace add Zate/cc-plugins/plugin install zate-devloop-plugins-devloop@Zate/cc-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Creating reviewable commits that capture logical units of work.
Plan tasks map to commits:
When using /devloop:ship, you can choose:
Example plan:
- [x] Task 1.1: Create config skill
- [x] Task 1.2: Add parsing script
- [x] Task 1.3: Update session hook
Atomic commits would create:
feat(devloop): create local-config skill
feat(devloop): add config parsing script
feat(devloop): update session-start hook
| Size | Lines | When to Commit |
|---|---|---|
| XS | <50 | Single fix, config change |
| S | 50-200 | One feature, one refactor |
| M | 200-500 | Feature with tests |
| L | >500 | Consider splitting |
Devloop tasks typically align with S-M size commits.
Instead of one large commit:
Or with devloop: One commit per phase.
/devloop:freshThis 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.