agent:context
Context Engineering - designs agent context strategy covering parallelization, context sharing, failure modes, compression, and error feedback
agent:design
Design AI Agent - comprehensive agent system design that orchestrates research sub-agents across all areas and produces a unified design document
agent:eval
Agent Evaluation System - designs failure modes, metrics, eval test suites, SME labeling, and production data evaluation pipelines
agent:memory
Memory Architecture - designs agent memory strategy with working memory, hierarchical recall, memory processors, and context management
agent:multi
Multi-Agent Design - designs multi-agent systems with supervisor patterns, control flow, A2A protocol, and workflow composition
agent:prompt
Prompt Engineering - guides through model selection, prompt writing, few-shot examples, and production prompt optimization
agent:rag
RAG Pipeline Design - guides through chunking, embedding, vector store selection, retrieval tuning, and RAG alternatives
agent:review
Agent Pattern Review - validates an AI agent against all 22 patterns from "Patterns for Building AI Agents" with a scored checklist and recommendations
agent:secure
Agent Security Audit - analyzes agent for lethal trifecta, sandboxing, access control, and guardrails
agent:tools
Tool Design - guides through agent tool architecture, MCP integration, third-party tool selection, and tool schema design
agent:workflow
Workflow Design - designs graph-based agent workflows with branching, chaining, suspend/resume, streaming, and observability
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.
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
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:approve
Approve Document - promotes a spec document to APPROVED status, unblocking downstream pipeline skills. Use when ready to advance the pipeline.
spec:design
Technical Design - generates architecture diagrams, interfaces, and data flow based on requirements and chosen research solutions. Use when designing how a feature will be built.
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 codebase and explores solution alternatives based on requirements. Use when choosing between implementation approaches.
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.