dev:create-skill
Create New Skill - scaffolds a skill definition following Claude Code conventions and this repository's patterns. Use when adding a new skill.
git:amend
Amend Commit - modifies the last commit with staged changes or new message
git:changelog
Generate Changelog - analyzes git history and creates a human-readable changelog for non-technical teams
git:commit
Smart Commit - stages all changes and creates a conventional commit
project:init
Project Init - defines the overall system goals, stakeholders, constraints, and shared architectural decisions. Use when starting a new multi-spec project.
agent:audit
Agent Audit - audits an existing AI agent against the 22 patterns from "Patterns for Building AI Agents" and the 12 factors of production-reliable agents, emitting a scored maturity report with a security gate. Use when reviewing, scoring, or assessing the production-readiness of an AI agent or agent design.
agent:developer
Designs and builds AI agents. Use when working on agent architecture, prompts, model selection, tool design, MCP, memory, context engineering, RAG, graph workflows, multi-agent systems, evaluation, or production reliability.
dev:claude-audit
Claude Code Setup Audit - reviews CLAUDE.md hierarchy, .claude/settings.json deny-list, per-directory commands, and extension layer against best practices for large codebases. Use periodically (every 3-6 months or after a major model release) or when onboarding a new repo.
journal:capture
Journal Capture - captures a thought, problem, edge case, idea, or decision into ~/journal and updates README indexes. Use when the user wants to write down a development thought or observation.
journal:promote
Journal Promote - graduates a journal entry into a new spec by seeding .specs/<name>/ with the entry's content, then linking the journal entry back. Use when the user wants to turn a captured idea, problem, or decision into a full specification.
journal:search
Journal Search - searches entries in ~/journal by query, type, project, topic, tags, or date range. Use when the user wants to find past thoughts, decisions, problems, or ideas they captured.
project:plan
Project Plan - breaks the vision into individual specs with dependencies, execution order, and shared interfaces. Use when decomposing a project into features.
project:status
Project Status - dashboard showing progress across all specs with dependency tracking and next action suggestions.
review:diff
Diff Review - analyzes code changes and provides structured feedback before commit
review:investigate
Investigate Problem - analyzes a problem in the codebase and proposes actionable solutions
review:ux
UX Review - analyzes feature for efficiency-first UX patterns, keyboard navigation, and pro-tool experience
spec:design
Technical Design - picks one variant per problem area from the research catalogue, then produces architecture diagrams, interfaces, and data flow. Decisions live here, not in research.
spec:implement
Implement Tasks - executes tasks from the tasks document using subagents. Use when ready to start coding a feature.
spec:requirements
Requirements Analysis - gathers requirements through structured questions and produces a requirements document with testable acceptance criteria. Use when starting a new feature spec or documenting requirements.
spec:research
Technical Research - investigates the codebase and builds a catalogue of solution variants per problem area. Iterative — can be re-run to widen the catalogue. Does not make decisions; selection happens in spec:design.
spec:review
Review Specification - validates documents for completeness, quality, and consistency against the codebase. Use when checking spec quality at any pipeline stage.
spec:status
Spec Status - displays pipeline progress dashboard for a single specification showing document statuses, blockers, and next action.
spec:tasks
Task Breakdown - generates an implementation plan with tracked tasks based on requirements and design documents. Use when breaking down a design into actionable work items.
spec:test-plan
Test Plan - creates a manual test plan with traceable test cases from specification documents. Use when preparing to verify a feature implementation.
spec:test
Execute Tests - walks through test cases from the test plan, collects results, and updates the plan. Use when verifying a feature implementation.