Loading...
Loading...
Found 1,211 Skills
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications
Guide for using Microsoft MarkItDown - a Python utility for converting files to Markdown. Use when converting PDF, Word, PowerPoint, Excel, images, audio, HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs, Jupyter notebooks, RSS feeds, or Wikipedia pages to Markdown format. Also use for document processing pipelines, LLM preprocessing, or text extraction tasks.
Designs robust function/tool calling schemas for LLMs with JSON schemas, validation strategies, typed interfaces, and example calls. Use when implementing "function calling", "tool use", "LLM tools", or "agent actions".
Use this skill when building MCP (Model Context Protocol) servers with FastMCP in Python. FastMCP is a framework for creating servers that expose tools, resources, and prompts to LLMs like Claude. The skill covers server creation, tool/resource definitions, storage backends (memory/disk/Redis/DynamoDB), server lifespans, middleware system (8 built-in types), server composition (import/mount), OAuth Proxy, authentication patterns, icons, OpenAPI integration, client configuration, cloud deployment (FastMCP Cloud), error handling, and production patterns. It prevents 25+ common errors including storage misconfiguration, lifespan issues, middleware order errors, circular imports, module-level server issues, async/await confusion, OAuth security vulnerabilities, and cloud deployment failures. Includes templates for basic servers, storage backends, middleware, server composition, OAuth proxy, API integrations, testing, and self-contained production architectures. Keywords: FastMCP, MCP server Python, Model Context Protocol Python, fastmcp framework, mcp tools, mcp resources, mcp prompts, fastmcp storage, fastmcp memory storage, fastmcp disk storage, fastmcp redis, fastmcp dynamodb, fastmcp lifespan, fastmcp middleware, fastmcp oauth proxy, server composition mcp, fastmcp import, fastmcp mount, fastmcp cloud, fastmcp deployment, mcp authentication, fastmcp icons, openapi mcp, claude mcp server, fastmcp testing, storage misconfiguration, lifespan issues, middleware order, circular imports, module-level server, async await mcp
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
Analyzes and improves LLM prompts and agent instructions for token efficiency, determinism, and clarity. Use when (1) writing a new system prompt, skill, or CLAUDE.md file, (2) reviewing or improving an existing prompt for clarity and efficiency, (3) diagnosing why a prompt produces inconsistent or unexpected results, (4) converting natural language instructions into imperative LLM directives, or (5) evaluating prompt anti-patterns and suggesting fixes. Applies to all LLM platforms (Claude, GPT, Gemini, Llama).
Performance optimization patterns covering Core Web Vitals, React render optimization, lazy loading, image optimization, backend profiling, and LLM inference. Use when improving page speed, debugging slow renders, optimizing bundles, reducing image payload, profiling backend, or deploying LLMs efficiently.
Generate a custom trace annotation web app for open coding during LLM error analysis. Use when the user wants to review LLM traces, annotate failures with freeform comments, and do first-pass qualitative labeling (open coding). Also use when the user mentions "annotate traces", "trace review tool", "open coding tool", "label traces", "build an annotation interface", "review LLM outputs", or wants to manually inspect pipeline traces before building a failure taxonomy. This skill produces a tailored Python web application using FastHTML, TailwindCSS, and HTMX.
Optimizes text, prompts, and documentation for LLM token efficiency. Applies 41 research-backed rules across 6 categories: Claude behavior, token efficiency, structure, reference integrity, perception, and LLM comprehension. Use when optimizing prompts, reducing tokens, compressing verbose docs, or improving LLM instruction quality.
Build AI-powered chat applications with TanStack AI and React. Use when working with @tanstack/ai, @tanstack/ai-react, @tanstack/ai-client, or any TanStack AI packages. Covers useChat hook, streaming, tools (server/client/hybrid), tool approval, structured outputs, multimodal content, adapters (OpenAI, Anthropic, Gemini, Ollama, Grok), agentic cycles, devtools, and type safety patterns. Triggers on AI chat UI, function calling, LLM integration, or streaming response tasks using TanStack AI.
Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering the full eval-driven development cycle. Make sure to use this skill whenever a user is developing, testing, QA-ing, evaluating, or benchmarking a Python project that calls an LLM, even if they don't say "evals" explicitly. Use for making sure an AI app works correctly, catching regressions after prompt changes, debugging why an agent started behaving differently, or validating output quality before shipping.