> browse/registry

> claude-api

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

> mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

> brand-guidelines

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.

> anthropic-administrator-automation

Automate Anthropic Admin tasks via Rube MCP (Composio). Always search tools first for current schemas.

> customgpt-automation

Automate Customgpt tasks via Rube MCP (Composio). Always search tools first for current schemas.

> eval-driven-dev

Add instrumentation, build golden datasets, write eval-based tests, run them, root-cause failures, and iterate — Ensure your Python LLM application works correctly. Make sure to use this skill whenever a user is developing, testing, QA-ing, evaluating, or benchmarking a Python project that calls an LLM. Use for making sure an LLM application works correctly, catching regressions after prompt changes, fixing unexpected behavior, or validating output quality before shipping.

> create-llms

Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/

> ai-wrapper-product

You know AI wrappers get a bad rap, but the good ones solve real problems. You build products where AI is the engine, not the gimmick. You understand prompt engineering is product development. You balance costs with user experience. You create AI products people actually pay for and use daily.

> agentic-actions-auditor

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.

> seek-and-analyze-video

Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence

> bdistill-behavioral-xray

X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.

> ai-engineer

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

> activecampaign-automation

Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.

> audio-transcriber

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

> agent-evaluation

You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer.

> ai-product

You are an AI product engineer who has shipped LLM features to millions of users. You've debugged hallucinations at 3am, optimized prompts to reduce costs by 80%, and built safety systems that caught thousands of harmful outputs. You know that demos are easy and production is hard.

> bdistill-knowledge-extraction

Extract structured domain knowledge from AI models in-session or from local open-source models via Ollama. No API key needed.

> ai-ml

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

> oracle

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns). Use when the developer needs to send a one-shot prompt with file context to another model, bundle repository files for external LLM review, run oracle browser or API queries, manage oracle sessions, attach or exclude files with glob patterns, or preview token costs with dry-run mode.

> fuzzing-dictionary

The agent creates and manages fuzzing dictionaries containing domain-specific tokens, magic bytes, protocol keywords, and format-specific strings to guide mutation-based fuzzers past early validation checks. It generates dictionary entries from header files, binary strings, man pages, and LLM prompts, and passes them to libFuzzer via -dict=, AFL++ via -x, or cargo-fuzz. The agent applies this technique when fuzzing parsers (JSON, XML, config files), protocol handlers (HTTP, DNS), file format pro