REQUIRED before any creative work - Phase 1-2 of Auto-Coding Framework. Explores user intent, requirements and design through collaborative dialogue. Produces BRD/PRD documents.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Competitive analysis skill for market-researcher. Research at least 3 competitor websites, analyze their business logic, interaction logic, and visual style. Output as structured report for BRD/PRD input.
Phase 5 of Auto-Coding Framework. Use when you have a written implementation plan to execute. Load plan, review critically, execute tasks in batches, report for review between batches.
Phase 7 of Auto-Coding Framework. Use when implementation is complete, all tests pass, and need to decide how to integrate the work. Guides completion of development work by presenting structured options.
Use when you have lint errors, formatting issues, test failures, or before committing code to ensure it passes CI. Integrates with systematic-debugging for issue resolution.
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.
Full-stack development expertise for React, Next.js, Node.js, TypeScript, and modern databases. Use when implementing features that span frontend and backend layers, creating APIs, building React components, or working with databases.
PRD quality standards and templates for product-manager. Teaches what makes good vs bad PRDs with concrete examples and provides the recommended PRD template.
Phase 5-6 of Auto-Coding Framework. Use when encountering any bug, test failure, or unexpected behavior, BEFORE proposing fixes. Always find root cause first.
Phase 5 of Auto-Coding Framework. Use when implementing any feature or bugfix, BEFORE writing implementation code. Enforces test-first development with Red-green-refactor cycle.
Audit MCP-to-skill dependency consistency. Use when adding/updating skills, changing MCP config, investigating runtime tool failures, or during framework governance to ensure all skill-declared MCP dependencies are verifiable in mcp.json.
Use before claiming work is complete, fixed, or merged, or creating PRs - requires running verification commands and proving claims. MUST show fresh verification evidence before making any success claim.