Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.
Evaluates Claude skills against official best practices from Anthropic documentation. Use when reviewing skill quality, ensuring compliance with guidelines, or improving existing skills.
Design and implement long-term memory systems for AI agents using vector stores, knowledge graphs, and hybrid approaches. Includes benchmarks and decision frameworks. Use when building persistent agent memory, implementing RAG, designing knowledge bases, or when user mentions 'memory', 'RAG', 'vector store', 'knowledge graph', 'long-term memory', 'retrieval', or 'embeddings'.
Check and process messages from autonomous AILANG agents. Use when starting a session, after agent handoffs, or when checking for completion notifications.
Universal execution engine using scientific method to achieve ideal state. USE WHEN complex tasks, multi-step work, "run the algorithm", "use the algorithm", OR any non-trivial request that benefits from structured execution with ISC (Ideal State Criteria) tracking.
Use for language design questions including syntax decisions, semantics, grammar authoring, and comparing DomainLang with other DSLs. Activate when designing new language features, evaluating syntax alternatives, or discussing DDD pattern representation.
Julia package equivalents for 137 K-Dense-AI scientific skills. Maps Python bioinformatics, chemistry, ML, quantum, and data science packages to native Julia ecosystem.
MLOps best practices for model versioning, experiment tracking, deployment, monitoring, and retraining workflows. Covers reproducibility, CI/CD for ML, model registry, and production ML system design.
Detect N+1 queries, analyze slow queries with EXPLAIN, identify missing indexes, and ensure safe online index migrations for MySQL/MariaDB. Use when optimizing query performance, preventing performance regressions, or debugging slow endpoints. Complements database-migrations skill which covers index creation syntax.
Use for implementing features, writing production TypeScript/Langium code, code review guidance, and ensuring technical quality. Activate when implementing new functionality, reviewing PRs, or optimizing performance.
Maintain Structurizr C4 architecture diagrams in sync with code changes. Use when adding components, modifying relationships, changing architectural boundaries, or implementing new patterns. Ensures workspace.dsl accurately reflects the current system architecture.
DevOps and infrastructure troubleshooting for Cloudflare Workers, PlanetScale PostgreSQL, and distributed systems. Use when debugging deployment issues, infrastructure problems, connection errors, or performance degradation.
Grey Haven's security best practices - input validation, output sanitization, multi-tenant RLS, secret management with Doppler, rate limiting, OWASP Top 10 for TanStack/FastAPI stack. Use when implementing security-critical features.
AI-powered intelligent debugging with stack trace analysis, error pattern recognition, and automated fix suggestions. Use when debugging complex errors, analyzing stack traces, or performing root cause analysis. Triggers: 'debug', 'error analysis', 'stack trace', 'root cause', 'troubleshooting'.
Design component architecture and module structure using established architectural patterns for clean, maintainable, and scalable systems.
Meta-level plugin suite auditor that uses subagents to analyze any plugin for usability improvements, missing agents, duplication, and workflow optimizations. Generates comprehensive reports with user-approved todo conversion. Triggers: 'audit suite', 'analyze plugin usability', 'find duplicate agents', 'suggest new agents', 'optimize plugin workflow', 'plugin gap analysis'.
Design and implement DDD patterns (entities, value objects, aggregates, CQRS). Use when creating new domain objects, implementing bounded contexts, designing repository interfaces, or learning proper layer separation. For fixing existing Deptrac violations, use the deptrac-fixer skill instead.
Grey Haven's authentication patterns using better-auth - magic links, passkeys, OAuth providers, session management with Redis, JWT claims with tenant_id, and Doppler for auth secrets. Use when implementing authentication features.
Design RESTful APIs following Grey Haven standards - FastAPI routes, Pydantic schemas, HTTP status codes, pagination, filtering, error responses, OpenAPI docs, and multi-tenant patterns. Use when creating API endpoints, designing REST resources, implementing server functions, configuring FastAPI, writing Pydantic schemas, setting up error handling, implementing pagination, or when user mentions 'API', 'endpoint', 'REST', 'FastAPI', 'Pydantic', 'server function', 'OpenAPI', 'pagination', 'validation', 'error handling', 'rate limiting', 'CORS', or 'authentication'.
