Creates or improves Agent Skills following official documentation and best practices. Use when creating new skills, improving existing skills, evaluating skill quality, or ensuring skills follow naming conventions, structure requirements, and discovery patterns. Guides through description writing, progressive disclosure, workflows, and testing.
Guide for creating high-quality Agent Skills following the open standard (agentskills.io). Use this when asked to create or update a skill, write a SKILL.md file, convert custom instructions or chatmodes into portable skills, or design specialized AI agent capabilities.
Use this skill when you need to invoke another Claude Code session via the cli-agent-runner.sh script to perform specialized, potentially long-running tasks in a simplified way. This wrapper handles session management, result extraction, and can be run in background with polling support.
Spawn an AI coding agent in a new terminal (Claude, Codex, Gemini, Cursor, OpenCode, Copilot). Defaults to Claude Code if unspecified.
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.
This skill should be used when the user asks to "connect React to agent runtime", "use useAgentSession", "use useMessages", "set up AgentServiceProvider", "stream agent responses", "build agent chat UI", "render conversation blocks", or needs to build a React frontend with @hhopkins/agent-runtime-react.
Analyze processed D&D sessions to extract and summarize campaign knowledge including NPCs, locations, quests, items, and factions. Use when the user wants to review campaign content, find specific entities, or understand the campaign narrative.
Master the Arcanean Prompt Language - advanced prompt engineering using mythological frameworks, constraint architecture, and the Centaur Principle for human-AI co-creation
This skill should be used when the user asks to "create an agent runtime server", "set up agent runtime backend", "configure Modal sandbox", "implement PersistenceAdapter", "start WebSocket server", "create REST API for agents", or needs to build a Node.js backend using @hhopkins/agent-runtime.
Use when building AI agent systems. Covers agent loops, tool calling, planning patterns, memory systems, multi-agent coordination, and safety guardrails. Apply when creating autonomous AI workflows, coding assistants, or task automation systems.
Token-efficient proxy for Naki's 47 MCP tools. Routes user intent to optimal MCP tool via agent isolation, saving 40-70% tokens. Use for any Naki game control, bot status, or UI operation.
This skill should be used when the user asks about "Burn tensors", "tensor operations", "Module derive", "burn config", "autodiff", "backward pass", "gradient", "record serialization", "model weights", or core Burn application development patterns.
This skill should be used when the GM needs storytelling techniques, handling player failure, NPC creation, scene pacing, or improv principles. Triggers on "fail forward", "succeed at cost", "yes and", "how do you want to do this", "NPC motivation", "scene transitions", "player agency".
Expert knowledge on creating Claude Code subagents. Use when designing or creating subagent .md files, understanding subagent structure, tool restrictions, or model selection.
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
This skill should be used when the user asks about "multi-agent coordination", "agent spawning", "parallel agents", "agent communication", "team coordination", "sub-agent management", "agent limits", "agent layers", or needs guidance on coordinating multiple agents for complex tasks.
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.
Comprehensive draft and post access, creating, editing and analysis. When Claude needs to work with the Ghost Admin API to access content published on alt-counsel.com as Houfu's partner.
Model Context Protocol (MCP) server implementation specialist for Claude Desktop integration. Handles TypeScript/Node.js server scaffolding, endpoint creation, telemetry setup, npx distribution, and comprehensive documentation. Follows MCP specification and best practices for production-grade server deployment.
The Meta-Architect of the Brain. Generates new AI agent skills based on the Gamma-Class v2.0 Schema. Use for
This skill should be used when the user asks to "create a plugin", "build a plugin", "write a plugin", or wants to bundle agents, hooks, commands, skills, or MCP servers into a distributable Claude Code plugin.
Foundational Roc patterns covering platform/application architecture, records, tags, pattern matching, abilities, and functional idioms. Use when writing Roc code, understanding the platform model, or needing guidance on which specialized Roc skill to use. This is the entry point for Roc development.
Multi-layer validation to catch bugs before they escape
