Porkbutts/porkbutts-n-taters

Design technical architecture from a PRD. Use when user wants to create an architecture document, define system design, plan technical implementation, or needs to translate product requirements into buildable technical specs. Reads from docs/PRD.md and outputs docs/ARCHITECTURE.md.

Build working prototypes from PRDs with mock data and stubbed integrations. Use when user has a PRD, spec, or feature description and wants a clickable demo to validate flows before full implementation. Triggers: build a prototype, functional prototype, make a demo, implement this PRD, prototype this spec, make it clickable.

End-to-end project orchestration from idea to implementation. Use when user wants to build a complete project, implement an MVP, or says "build this app/feature". Coordinates product-design, architecture, task-decomposition skills, then delegates to task-spec-generator, task-implementer, and code-reviewer agents for execution. Resumable—introspects filesystem and git state to pick up where it left off if interrupted.

Design MVPs for web, mobile, and SaaS applications through adaptive interviews that achieve buildable clarity. Use when a user wants to define, scope, or document an application idea, or when they mention MVP, product requirements, PRD, app idea, or need help turning a concept into something implementable.

Capture lessons from conversation after Claude made mistakes or needed correction. Trigger phrases include "reflect", "review our mistakes", "learn from this", "capture this lesson", "remember this for next time". Analyzes the conversation to extract actionable guidance and persists it to ~/.claude/lessons/ with triggers in ~/.claude/CLAUDE.md.

Break down PRD and Architecture into implementable engineering tasks. Use when user wants to create a task list, plan implementation work, decompose features into stories and tasks, or needs to translate requirements into actionable engineering work. Reads from docs/PRD.md and docs/ARCHITECTURE.md, outputs docs/TASKS.md.