LLM & Agents

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Expert MCP (Model Context Protocol) orchestration with n8n workflow automation. Master bidirectional MCP integration, expose n8n workflows as AI agent tools, consume MCP servers in workflows, build agentic systems, orchestrate multi-agent workflows, and create production-ready AI-powered automation pipelines with Claude Code integration.

Choose and execute orchestration commands (/solo for straightforward tasks, /spec for planning, /conduct for complex features with SPEC.md). Covers decision tree, sub-agents, validation standards, and best practices. Use when planning complex tasks or understanding orchestration patterns.

Implement client-side data storage with localStorage, IndexedDB, or SQLite WASM. Use when storing user preferences, caching data, or building offline-first applications.

Automate Git worktree creation with isolated Docker services and browser automation for parallel Claude Code development sessions. This skill should be used when creating, managing, or removing Git worktrees for isolated development environments with automatic port allocation, environment file copying, and browser MCP isolation.

Configuring Claude Code Hooks System. Design, implement, and manage PreToolUse/PostToolUse/SessionStart/Notification/Stop hooks. Use when enforcing safety checks, auto-formatting, running linters, or triggering automated workflows based on development events.

Optimize CLAUDE.md following best practices from humanlayer.dev - apply after /init to transform verbose output into focused, high-leverage project context

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Agent-to-Agent (A2A) server configuration patterns for HTTP, STDIO, SSE, and WebSocket transports. Use when building A2A servers, configuring MCP transports, setting up server endpoints, or when user mentions A2A configuration, server transport, MCP server setup, or agent communication protocols.

Guide for creating CLAUDE.md files. Use when: user asks to create CLAUDE.md, document project, add project instructions, or mentions CLAUDE.md.

Design, optimize, and refactor AI agent systems based on Anthropic best practices and latest research. Guides you through architectural decisions with interactive questionnaire, loads current documentation, and launches specialized agent-architect for detailed analysis.

Propose multi-agent and workflow architectures for CustomGPT.ai Labs projects, showing how Claude Code, CustomGPT.ai, and supporting tools interact to deliver the desired business outcome.

Context-efficient Git and Graphite workflows for Claude Code. Automatically delegates verbose git/Graphite CLI operations to isolated subagents, reducing context pollution by 225x. Use when working with git operations, Graphite stacked diffs, or any git workflow that produces verbose output. Prevents context window exhaustion by automatically applying delegation patterns via SessionStart hooks.

Use when mapping audit targets to appropriate config or domain agents. Analyzes file types, patterns, and content to determine which agents should audit each file/target. Returns agents[] needed for audit workflow.

Retrieves power plants, buildings, or underground storage tanks at flood risk as a GeoDataFrame.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (devlog reports, leadership updates, 22A updates, 22B consended, company newsletters, FAQs, incident reports, project updates, etc.).

Analyze CSS coverage, identify unused rules, and detect stylesheet conflicts. Use after visual QA to optimize stylesheets before publication.

Pattern for producing quality reflections after completing work. Required for all agent outputs.

Query and analyze logs using Grafana Loki for the Kagenti platform, search for errors, and investigate issues

Optimize websites for AI assistant recommendations. ChatGPT, Gemini, Perplexity, Claude. Get cited in AI answers.