
Break a PRD into independently grabbable GitHub issues with dependency relationships. Use when asked to 'break this PRD into issues', 'create issues from PRD', 'plan the work', 'create a kanban', or after writing a PRD to prepare work for execution.
Write a Product Requirements Document from a rough idea. Use when asked to 'write a PRD', 'create a PRD', 'plan a feature', or when starting a new feature that needs scoping.
Cache expensive exploration into a research document before building. Use when asked to 'research', 'investigate before building', 'gather context', 'flush unknowns', or before a large feature where unknowns need flushing.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Ruthless codebase audit reporting only real problems. Use when asked to 'audit', 'code audit', 'codebase audit', 'review code', 'find bugs', or 'code review'.
Use when repeated Claude Code session errors need analysis; scans session transcripts for errors, clusters by root cause, and suggests remediations.
Atomic commits on a feature branch with conventional messages — Commit mode for checkpoints, Ship mode for PR. Use when committing, checkpointing, shipping, pushing, or creating a PR.
Auto-invoke after any do-work, tdd, systematic-debugging, or review-pr-copilot task completes to review the diff against active rules and skills, flag violations, update the skill if a gap is found, and close the loop between 'rule was loaded' and 'rule was followed'.
Address GitHub Copilot review comments on the active PR by triaging into confidence tiers, fixing in atomic commits, resolving threads, and re-requesting review.
Frontend component file structure, naming, and layer separation for new or refactored components.
Step 3.2 of Sketch the Solution. Map navigation paths between screens as a Mermaid flowchart. Use when asked to 'create flow diagram', 'user flow', 'navigation map', or 'screen flow diagram'.
Step 5.1 of Sketch the Solution. Define 1-2 goals for each screen in the flow diagram. Use when asked to 'create screen goals', 'define screen purpose', 'screen objectives', or 'what should each screen do'.
Step 2.1 of Sketch the Solution. Identify core players and actions from entity inventory. Use when asked to 'create system map', 'identify entities', 'core players', or 'entity inventory'.
Step 6.3 of Sketch the Solution. Develop detailed screen specs with UI controls and interaction patterns. Use when asked to 'detailed wireframes', 'detailed sketches', 'UI specification', 'screen spec', or 'wireframe details'.
Step 6.1 of Sketch the Solution. Research UI patterns and build an inspiration reference. Use when asked to 'get inspired', 'UI inspiration', 'research UI patterns', 'pattern library', or 'design inspiration'.
Step 5.2 of Sketch the Solution. Apply the Inform → Engage → Invite framework to each screen. Use when asked to 'inform engage invite', 'screen intent', 'screen structure framework', or 'IEI framework'.
Step 3.1 of Sketch the Solution. Derive the complete screen list from the system map. Use when asked to 'list screens', 'screen inventory', 'what screens do I need', or 'enumerate pages'.
Phase 2 of Sketch the Solution. Map entities, relationships, and CRUD actions from user stories. Use when asked to 'create system map', 'map entities', 'entity relationship diagram', or 'system diagram'.
Focused review of staged or recent changes to find edge cases, logic errors, and integration risks before merging. Use when asked to 'do a code review', 'review my changes', 'review this PR', 'check my diff', 'review staged changes', or 'pre-merge review'.
Core execution loop for implementing tasks. Use when asked to 'do work', 'implement', 'build this', 'fix this', 'plan execute clear', 'plan then execute', 'work loop', or when working through a plan or backlog item.
Deep codebase exploration using parallel subagents. Use when asked to 'explore', 'understand', 'investigate', 'map out', 'how does X work', or 'audit' a part of the codebase.
Explore the codebase for architectural improvements using deep module analysis. Use when asked to 'improve architecture', 'improve codebase', 'find shallow modules', 'refactor architecture', or for periodic codebase health checks.
Sanity development best practices — schemas, GROQ, TypeGen, Visual Editing, Functions, Blueprints, and framework integrations. Use when working with Sanity content, schemas, queries, or Studio.
Invoke to run the adversarial stress test protocol against ctrl+shft rule compliance. Guides a human reviewer through systematic attempts to break rule boundaries — the same methodology a skeptical senior engineer would use before trusting the system in production.
Red-green refactor workflow for test-driven development. Use when asked to 'write tests first', 'TDD', 'red-green refactor', 'test-driven', or 'failing test first'. Backend-only — do not use for frontend components.
Phase 3 of Sketch the Solution. List screens, draw navigation flows, validate against user stories. Use when asked to 'create flow diagram', 'map user flows', 'screen flow', or 'navigation diagram'.
Step 5.3 of Sketch the Solution. Define ABC spec for each screen: what user gets, does, and how they navigate. Use when asked to 'screen attributes', 'ABC spec', 'screen requirements list', or 'what goes on each screen'.
Layered security audit on npm/pnpm/yarn projects before installing or running. Use to vet a GitHub repo, npm package, or local project before npm install/start/npx.
Write, update, or audit documentation. Use when asked to 'document this', 'write docs', 'update the README', 'add JSDoc', 'write a changelog', or 'create an ADR'.
Edit and punch up sales copy, marketing emails, landing pages, ads, and any persuasive writing using the Halbert Copywriting Method.
Exhaustive pre-PR audit that front-runs code review tools by catching the same issues Copilot/reviewers find iteratively, across any stack.
Comprehensive implementation planning with vertical slices. Use when asked to 'act as an Architect', 'plan this', 'create an implementation plan', 'slice this into tasks', or when a task needs decomposition before execution.
Step 1.1 of Sketch the Solution. Identify goals for each user type/avatar. Use when asked to 'identify user goals', 'define user goals', 'map user types', or 'list personas'.
Step 6.2 of Sketch the Solution. Create high-level component layout specs for each screen. Use when asked to 'sketch screens', 'high-level wireframes', 'rough sketches', 'layout specs', or 'component layout'.
7-phase UX design process from user stories to tested interfaces. Use when asked to 'sketch the solution', 'design UX', 'UX process', 'product design process', or when going from idea to interface design.
Step 1.3 of Sketch the Solution. Extract entities (nouns) and actions (verbs) from user stories. Use when asked to 'highlight key terms', 'extract entities', 'identify nouns and verbs', or 'entity extraction'.
Phase 6 of Sketch the Solution. Create wireframe variations per screen from screen requirements. Use when asked to 'design interface', 'wireframes', 'create UI', 'interface design', or 'sketch screens'.
Step 2.2 of Sketch the Solution. Draw interaction relationships between entities as a Mermaid ERD. Use when asked to 'draw relationships', 'entity relationships', 'relationship diagram', or 'ERD'.
Phase 5 of Sketch the Solution. Define goals and ABC requirements for every screen. Use when asked to 'screen requirements', 'screen specs', 'define screens', or 'screen goals'.
Phase 4 of Sketch the Solution. List exhaustive attributes for every entity in the system map. Use when asked to 'model attributes', 'list attributes', 'data model', or 'entity attributes'.
Phase 7 of Sketch the Solution. Plan user testing sessions and validate designs. Use when asked to 'test design', 'user testing', 'validate UI', 'test driven design', or 'get feedback on design'.
Phase 1 of Sketch the Solution. Write pain-state user stories per avatar, highlight entities and actions. Use when asked to 'write user stories', 'user stories', 'capture user goals', or starting the UX process.
Step 7.2 of Sketch the Solution. Validate test plan against the six common user testing mistakes. Use when asked to 'six mistakes', 'testing anti-patterns', 'validate test plan', or 'user testing checklist'.
Step 4.1 of Sketch the Solution. List exhaustive attributes for every entity from stories, surveys, and flow. Use when asked to 'list attributes', 'entity attributes', 'data attributes', or 'attribute inventory'.
Step 7.1 of Sketch the Solution. Create structured user testing session plan with per-screen questions. Use when asked to 'user testing', 'test plan', 'feedback session', 'validate with users', or 'customer feedback'.
Step 3.3 of Sketch the Solution. Cross-check flow diagram against user stories to find gaps. Use when asked to 'validate flow', 'test user flow', 'check flow against stories', or 'flow validation'.
Step 1.2 of Sketch the Solution. Write pain-state user stories for each avatar. Use when asked to 'write user story', 'pain story', 'user narrative', or 'describe user journey'.
Use after merging a PR or during periodic cleanup to archive plan-mode files by linking them to merged PRs.
Use when stress-testing a plan against the project's domain model — grills the design, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.
Interview the user relentlessly about a plan or design until reaching shared understanding. Use when asked to 'grill me', 'interview me', 'ask me questions about this', or before writing a PRD to flesh out vague ideas.
Use when Claude Code sessions had many manual approval ("press 1") prompts or when auditing hook permissions; identifies which Bash commands required approval.
Use when implementing UI, checking dark/light mode, or validating animations — adds a visual feedback loop via browser screenshots so frontend changes are verified, not assumed.
Pre-flight checklist that runs quality gates before ending a coding session.
Meta-skill for creating new agent skills that involve multi-step automation, browser navigation, state tracking, evidence capture, and both local (VS Code Insiders) and VPS (Playwright) execution. Use when the user wants to 'create a skill', 'build a new skill', 'scaffold a skill', 'make a skill for X', or describes a multi-step agentic workflow they want to automate.