Core

Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use when testing prompts, validating outputs, comparing models, or when user mentions 'evaluation', 'testing LLM', 'rubric', 'LLM-as-judge', 'output quality', 'prompt testing', or 'model comparison'.

Python Test-Driven Development expertise with pytest, strict red-green-refactor methodology, domain-first modeling (DDD), principled DRY discipline, FastAPI testing patterns, and Pydantic model testing. Use when implementing Python features with TDD, writing pytest tests, testing FastAPI endpoints, developing with test-first approach, modeling domain concepts, refactoring duplication, or when user mentions 'Python TDD', 'pytest', 'FastAPI testing', 'red-green-refactor', 'Python unit tests', 'test-driven Python', 'domain modeling', 'value object', 'ubiquitous language', 'DRY', or 'Python test coverage'.

Design effective MCP tools and Claude Code integrations using the consolidation principle. Fewer, better-designed tools dramatically improve agent success rates. Use when creating MCP servers, designing tool interfaces, optimizing tool sets, or when user mentions 'tool design', 'MCP', 'fewer tools', 'tool consolidation', 'tool architecture', or 'tool optimization'.

Guide for creating effective skills that extend Claude's capabilities. Use when users want to create a new skill, update an existing skill, or need guidance on skill structure and best practices. Triggers: 'create skill', 'new skill', 'skill template', 'build skill', 'skill structure', 'skill design'.

TypeScript/JavaScript Test-Driven Development with Vitest, strict red-green-refactor methodology, domain-first modeling (DDD) via branded types, principled DRY discipline, React component testing, and comprehensive coverage patterns. Use when implementing TypeScript features with TDD, writing Vitest tests, testing React components, developing with test-first approach, modeling domain concepts, refactoring duplication, or when user mentions 'TypeScript TDD', 'Vitest', 'React testing', 'JavaScript TDD', 'red-green-refactor', 'TypeScript unit tests', 'branded types', 'value object', 'ubiquitous language', 'DRY', or 'test-driven TypeScript'.

Master TDD orchestration with multi-agent coordination, strict red-green-refactor enforcement, a Layer-0 domain-modeling gate (DDD) that blocks Red until concepts are named in domain vocabulary and primitives promoted to types, and principled DRY enforcement at Refactor (same-concept repetition ≥3 sites only). Automated test generation, coverage tracking, >90% coverage quality gates. Supports Claude Teams for parallel TDD workflows with plan approval gates, or falls back to sequential subagent coordination. Use when implementing features with TDD workflow, coordinating multiple TDD agents, enforcing test-first development, modeling a domain, orchestrating TDD teams, or when user mentions 'TDD workflow', 'test-first', 'TDD orchestration', 'multi-agent TDD', 'domain modeling', 'value object', 'ubiquitous language', 'DRY', 'test coverage', or 'red-green-refactor'.

Master 26 documented prompt engineering principles for crafting effective LLM prompts with 400%+ quality improvement. Includes templates, anti-patterns, and quality checklists for technical, learning, creative, and research tasks. Use when writing prompts for LLMs, improving AI response quality, training on prompting, designing agent instructions, or when user mentions 'prompt engineering', 'better prompts', 'LLM quality', 'prompt templates', 'AI prompts', 'prompt principles', or 'prompt optimization'.

Generate production-ready project scaffolds for Grey Haven stack with Cloudflare Workers, React + TypeScript, Python + Pydantic, PlanetScale, proper structure, and configuration. Use when starting new projects, creating microservices, setting up monorepo workspaces, initializing projects, or when user mentions 'new project', 'project scaffold', 'project template', 'project setup', 'bootstrap project', 'project starter', or 'initialize project'.

Multi-mode code quality analysis covering security reviews (OWASP Top 10), clarity refactoring (readability rules), synthesis analysis (cross-file issues), and DDD/DRY lenses (flags mechanical naming, primitive obsession, domain rules leaking into infrastructure, and premature abstractions via the three-occurrences-same-concept rule). Supports team-mode parallel analysis when invoked from quality-pipeline. Use when reviewing code for security vulnerabilities, improving code readability, conducting quality audits, pre-deployment checks, or when user mentions 'code quality', 'code review', 'security review', 'refactoring', 'code smell', 'OWASP', 'code clarity', 'primitive obsession', 'value object', 'ubiquitous language', 'DRY', 'premature abstraction', or 'quality audit'.

6-phase verification system ensuring code matches documentation with automated alignment scoring (signature, type, behavior, error, example checks). Reduces onboarding friction 40%. Use when verifying code-docs alignment, onboarding developers, after code changes, pre-release documentation checks, or when user mentions 'docs out of sync', 'documentation verification', 'code-docs alignment', 'docs accuracy', 'documentation drift', or 'verify documentation'.

Build LLM-powered applications and pipelines using proven methodology - task-model fit analysis, pipeline architecture, structured outputs, file-based state, and cost estimation. Use when building AI features, data processing pipelines, agents, or any LLM-integrated system. Inspired by Karpathy's methodology and production case studies.

Comprehensive performance analysis and optimization for algorithms (O(n²)→O(n)), databases (N+1 queries, indexes), React (memoization, virtual lists), bundles (code splitting), API caching, and memory leaks. 85%+ improvement rate. Use when application is slow, response times exceed SLA, high CPU/memory usage, performance budgets needed, or when user mentions 'performance', 'slow', 'optimization', 'bottleneck', 'speed up', 'latency', 'memory leak', or 'performance tuning'.