validate-output
**Check that your generated output is properly formatted and ready to use.**
A command is the one you type. It runs exactly when you ask it to, and never before.
9,228 commands across 665 plugins.
**Check that your generated output is properly formatted and ready to use.**
Generate production-ready project structures, components, and boilerplate code with modern best practices and comprehensive tooling
Generate comprehensive test suites automatically for components, functions, and APIs with multiple framework support
Analyze the current project's structure **and** your past routing history, then recommend a per-project routing profile — e.g. a small, low-risk project can…
Set the issue tracker for the current project.
Spawn the default agent team for this project. Creates a coordinated team of agents that implement features in parallel following the strict TDD pipeline.
Analyze the current project's structure **and** your past routing history, then recommend a per-project routing profile — e.g. a small, low-risk project can…
Set the issue tracker for the current project.
Spawn the default agent team for this project. Creates a coordinated team of agents that implement features in parallel following the strict TDD pipeline.
Scaffold repo-local Ralph autonomous harness (scripts/ralph/)
Refine a spec, task, or spec file in-depth - question passes (business, technical, both) or a read-only research pass
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
Runs feature-scoped mutation testing to validate test suite quality. Use after implementation to verify tests catch real bugs (kill rate >= 80%).
Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.
Minimizes test count while preserving coverage. Detects byte-identical pairs, parametrize-inflation, language-guarantee tests, AST-shape tests, stale migration…
Convert delivery findings into skill, eval, workflow, and documentation improvements.
Review a system design someone else provided - screenshot, drawio, Mermaid, slides, doc, or IaC - by extracting it into a confirmed fact sheet, then scoring it…
Review a ticket or PR through focused specialist lenses: scope, architecture, security, tests, AC coverage, and PR metadata.
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
Use the @mako-marketing agent to help the user with the following marketing matter: $ARGUMENTS
Use the @mentor-courses agent to help the user with the following education/courses matter: $ARGUMENTS
Use the @mirror-retro agent to run a retrospective on the following feature, sprint, or incident: $ARGUMENTS
Install RLS policies per the plan; folded into /butterbase-skills:journey-schema in hackathon mode.
System design with Memory-based coordination for scalable architectures.
❓Ask - You are a task-formulation guide that helps users navigate, ask, and delegate tasks to the correc...
Automatically spawn and manage agents based on task requirements.
Resolve all pending CLI todos using parallel processing
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and worktrees
**Read-only quality check - determines if refactor is needed.**
Generate a complete PRP-style medium plan for general feature implementation with thorough research. Ensure context is passed to the AI agent to enable…
name: "Base Medium Plan Template - Context-Rich and Fast" description: |
Use when the user asks for a deck, architecture review board slides, keynote, or demo. Runs the /team present pipeline in the Consulting or Apple format with…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic