Expert guidance on Claude Code configuration, capabilities, and troubleshooting. Use this skill whenever the user asks about Claude Code features, configuration, best practices, or troubleshooting — even if phrased informally. Covers MCP servers, plugins, skills, subagents, hooks, permissions, keybindings, settings, terminal setup, GitHub Actions, CLAUDE.md, cost management, and common problems. Answers are sourced from official Claude Code product documentation.
Analyze conversation and update CLAUDE.md, rule files, and/or any skills, commands, or agents that were used — based on user feedback vs agent behavior. Use this skill at the end of any conversation where corrections, misunderstandings, or new patterns emerged, especially when a skill, command, or agent underperformed or needed repeated guidance. Also use when the user says things like "save what we learned", "remember this for next time", "update the rules", "let's wrap up and capture this", or any variation of wanting to persist lessons from the current session.
Browse and explore agent harness frameworks and Claude Code resource collections. Use when the user wants to learn about, explore, or use agent orchestration frameworks, multi-agent architectures, or Claude Code resource catalogs — e.g., "how does Archon work?", "show me everything-claude-code resources", "find an agent pattern for X", "explore agent harness repos", "what's in the agent harness catalog?". Make sure to use this skill whenever the user asks about any agent framework, multi-agent pattern, or Claude Code resource collection — even if they don't explicitly say "agent harness" or name a specific repo.
Expert implementation guidance for the Claude Agent SDK (Python). Use when users are building with the Agent SDK — creating custom tools, managing sessions, controlling permissions, streaming responses, integrating MCP servers, adding hooks, defining subagents, or deploying SDK-based agents. Also use for SDK architecture questions (query() vs ClaudeSDKClient, multi-turn vs one-shot, structured outputs, session persistence, cost tracking). Provides implementation patterns, decision guides, and pointers to working code in the SDK source — not just doc links.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, Architecture Decision Records) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Browse and discover Claude Code skills, agents, commands, and plugins from community and official repositories. Use when the user wants to find, explore, or learn about existing skills, agents, commands, or plugins — e.g., "what plugins are available?", "is there a skill for code review?", "show me community agents", "find a plugin for testing", "browse the plugin marketplace". Also use when the user wants to learn what a community plugin does.
Expert prompt engineering guidance with proven techniques and anti-patterns. Invoke this skill whenever writing, editing, reviewing, or refining any prompt that will be interpreted by an AI model — system prompts, agent instructions, tool-use prompts, command templates, multi-step task prompts, or agentic workflows. Use it even when the task doesn't explicitly mention 'prompt engineering' — if the output is instructions for an AI, this skill makes them significantly better. Trigger for both user-requested prompt work and when autonomously generating prompts as part of a larger task (e.g. creating skills, writing agent instructions, drafting review templates).