LLM & Agents

This skill should be used when the user asks "what is agent-runtime", "why use agent-runtime", "what does this repo do", "agent runtime architecture", "how does agent-runtime work", or needs to understand the purpose, value proposition, and high-level architecture of the @hhopkins/agent-runtime monorepo.

Analyze Claude Code usage patterns, project structure, and discover community resources for workflow optimization

Expert knowledge on creating slash commands for Claude Code. Use when designing or creating slash command .md files, understanding command arguments, or implementing bash execution.

Review guidelines. Always use when Claude needs to review the code changes

Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate

Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan.

Design and create Claude Skills for this Rails event-sourced codebase. Use when you need to capture repeatable workflows, complex multi-step processes, or domain-specific patterns that Claude should handle consistently.

Decide whether to delegate lower-level execution to Qwen MCP while Claude handles planning/review.

How assistants (LLMs or humans following scripted workflows) should interact with this project and its repos.

Soracom testing standards (unit/contract/E2E, Root vs SAM users, 80% coverage). Use when writing tests or creating test plans.

Create new Claude Code skills in this repository. Use when user wants to add a new skill, create a skill, implement a skill, or extend Claude's capabilities with a custom workflow.

Expert on Move programming language - abilities (copy/drop/store/key), generics, phantom types, references, global storage operations, signer pattern, visibility modifiers, friend functions, inline optimization, and advanced type system. Triggers on keywords move language, abilities, generics, phantom type, borrow global, signer, friend, inline, type parameter

Expert assistant for creating and maintaining admin panel pages in the KR92 Bible Voice project. Use when creating admin pages, building admin components, integrating with admin navigation, or adding admin features.

Recognize when user requests new feature implementation and prompt for TDD workflow. Triggers on phrases like "implement", "create function", "add feature", "build a", "write code for". Suggests generating failing tests first.

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

Minimal starter template for creating new Claude skills following the v1.0 specification

Leverage iterator chains for efficient, lazy data processing without intermediate allocations. Use when processing collections.

Persistence and human-in-the-loop patterns for LangGraph. Use when implementing checkpointing, saving/restoring graph state, adding human approval workflows, managing conversation memory across sessions, enabling time-travel debugging, or building fault-tolerant agents that resume from failures.

Guide for creating Claude Code skills that mirror library documentation. Covers sync strategies, SKILL.md structure, and best practices.

Specialized agent configurations for specific industries