Multi Perspective Review
Multi-perspective collaborative review of plans or documents. Ten expert viewpoints deliberate in 3 rounds to reach consensus.
Using Claude Code Kit
Session-start meta-skill. claude-code-kit-specific workflow chain, agent map, and Work system rules (generic skill-invocation discipline is shared with superpowers when present).
Native Watch
Audit Claude Code native feature absorption. Use to compare the kit's components against the latest Claude Code releases and propose absorption-ledger updates. Trigger with /native-watch or on a schedule.
Auto Dev
Automated development pipeline. Runs a completed Planning Work through Development and Validation phases end-to-end.
Plan Task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.
Web Research
Research external information using MCP servers. Use when users need to find documentation, compare technologies, or research best practices.
Skill Creator
Create new Claude Code skills. Applies standard templates and best practices to scaffold a skill file automatically.
Doc Coauthoring
AI-assisted documentation authoring. Use when writing, reviewing, or updating technical documents and READMEs.
Agent Creator
Create Claude Code sub-agents with optimal configuration. Use when users ask to create a new agent, custom agent, specialized assistant, or want to configure task-specific AI workflows.
Mcp Builder
Build and configure MCP servers. Use when scaffolding a new Model Context Protocol server or adding tools to an existing one.
Review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.
Self Improve
Propose improvements to agent/skill/rule definitions from accumulated feedback-ledger defects and eval reports. Proposal-only - applies changes exclusively after evals show no regression AND the user approves. Trigger with /self-improve.
Debug
Analyze errors and apply fixes. Use when you have an error message, traceback, or failing log to diagnose.
Brainstorming
Design and spec before any planning or code. MUST USE before new features, creative work, or any implementation. Explores requirements, proposes approaches, gets design approval, then chains to plan-task.
Agent Teams
Large-scale parallel work guidance. Routes 10+ parallel independent tasks to native dynamic workflows (ultracode), with legacy experimental Agent Teams as fallback.
Test
Run tests and auto-fix failures. Detects the test framework, executes tests, and iterates on fixes until all pass.