LLM & Agents

Use when requesting or receiving code reviews - covers dispatching review subagent, handling feedback with technical rigor, and avoiding performative agreement

Generate comprehensive specification documents including requirements, technical design, and detailed task breakdown from any feature request. Use when the user asks to create specs, requirements docs, design docs, or needs to break down a feature into implementation tasks. Perfect for planning new features, understanding system architecture, or preparing work for AI coding agents.

Kailash DataFlow - zero-config database framework with automatic model-to-node generation. Use when asking about 'database operations', 'DataFlow', 'database models', 'CRUD operations', 'bulk operations', 'database queries', 'database migrations', 'multi-tenancy', 'multi-instance', 'database transactions', 'PostgreSQL', 'MySQL', 'SQLite', 'MongoDB', 'pgvector', 'vector search', 'document database', 'RAG', 'semantic search', 'existing database', 'database performance', 'database deployment', 'database testing', or 'TDD with databases'. DataFlow is NOT an ORM - it generates 11 workflow nodes per SQL model, 8 nodes for MongoDB, and 3 nodes for vector operations.

Expert Svelte/SvelteKit development assistant for building components, utilities, and applications. Use when creating Svelte components, SvelteKit applications, implementing reactive patterns, handling state management, working with stores, transitions, animations, or any Svelte/SvelteKit development task. Includes comprehensive documentation access, code validation with svelte-autofixer, and playground link generation.

Expert on Shelby Protocol architecture, erasure coding, placement groups, read/write procedures, Clay Codes, chunking, storage providers, RPC servers, and decentralized storage system design on Aptos blockchain. Triggers on keywords Shelby Protocol, erasure coding, Clay Codes, placement groups, Shelby architecture, storage provider, blob storage, chunking, Shelby whitepaper.

Sync Claude Code skills from the ChillSkills GitHub repository

External LLM invocation. Triggered ONLY by @council,@probe,@crossref,@gpt,@gemini,@grok,@qwen.

Claude Code CLI development patterns, hooks, plugins, MCP integration, and agentic workflows.

NVIDIA NeMo framework for building and training conversational AI models. Use for NeMo Retriever models, RAG (Retrieval-Augmented Generation), embedding models, enterprise search, and multilingual retrieval systems.

Delegate tasks to remote Claude Code agent containers for parallel execution, long-running analysis, or resource-intensive operations.

Add a new event type to the frontend feed system with corresponding React component. Use when user mentions "new event", "add event type", "event block", "new block type", or wants to display new agent output types.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Comprehensive code review with parallel specialist sub-agents. Analyzes requirements traceability, code quality, security, performance, accessibility, test coverage, and technical debt. Produces detailed findings and calls /qa-gate for final gate decision.

Generate Pictionary drawing cards using AI (Groq) with fallback to hardcoded libraries. Use when creating new game cards, implementing category-based card selection, or handling AI card generation with graceful degradation.

Role assignment for Claude Agent

Guide for versioning and releasing Claude Code plugins. Covers semantic versioning, CHANGELOG maintenance, and the automated release workflow.

Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.

Methodological skill for Test-Driven Development in NestJS backend. This skill should be used when strict quality requirements demand tests-first approach, refactoring critical services, or building MVPs with mandatory coverage. Complements nestjs-architect skill with TDD methodology.

Google Gemini API development with google-genai SDK. Use for prompting, multimodal inputs, structured outputs, and agentic workflows.

This skill should be used when the user asks about "tests", "unit tests", "EditMode tests", "PlayMode tests", "Test Runner", "test coverage", "NUnit", "Assert", "test fixtures", "writing tests", "running tests", or discusses Unity testing patterns and practices.