Best MCP & Agent Tooling Skills for Claude Code

Skills for builders working on agent infrastructure itself: MCP server scaffolding, tool routing, orchestration, memory and evaluation. Ideal if you write your own SKILL.md files or connect agents to external APIs.

36 curated skills

langchain

davila7's avatarfrom davila7★ 15.4k

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

orchestration

numman-ali's avatarfrom numman-ali★ 1.3k

MANDATORY - You must load this skill before doing anything else. This defines how you operate.

langchain

zechenzhangAGI's avatarfrom zechenzhangAGI★ 62

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

ultimate-research

majiayu000's avatarfrom majiayu000★ 5

Elite multi-agent research orchestration utilizing ref MCP, exa MCP, brave-search MCP, and context7 with parallel execution of deep-research-agent, search-specialist, trend-researcher, and ux-researcher. Use for comprehensive research requiring maximum depth, breadth, and quality. Automatically invoked during /sc:research commands for world-class research capabilities surpassing any traditional deep research approach.

orchestration

duyet's avatarfrom duyet★ 4

MANDATORY - You must load this skill before doing anything else. This defines how you operate.

github-url-intercept

rjmurillo's avatarfrom rjmurillo★ 4

BLOCKING INTERCEPT: When ANY github.com URL appears in user input, STOP and use this skill. Never fetch GitHub HTML pages directly - they are 5-10MB and will exhaust your context window. This skill routes URLs to efficient API calls (1-50KB). Triggers on: pull/, issues/, blob/, tree/, commit/, compare/, discussions/.

google-workspace

plurigrid's avatarfrom plurigrid★ 1

Google Workspace MCP integration for Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, and Chat. Use when the user wants to read/send emails, manage files, create/edit documents, schedule events, or interact with any Google Workspace service.

using-loaded-knowledge

adilkalam's avatarfrom adilkalam

MANDATORY protocol enforcing knowledge check before EVERY response - prevents explaining systems without reading docs, claiming without verification, and ignoring auto-loaded context

using-skills

erikpr1994's avatarfrom erikpr1994

Core skill for understanding and using the Jarvis skill system. Loaded at every session start.

orchestration

MitchellkellerLG's avatarfrom MitchellkellerLG

MANDATORY - You must load this skill before doing anything else. This defines how you operate.

core

jeffh's avatarfrom jeffh★ 5

PAI (Personal AI Infrastructure) - Your AI system core. AUTO-LOADS at session start. USE WHEN any session begins OR user asks about PAI identity, response format, stack preferences, security protocols, or delegation patterns.

mcp-server-developer

sandraschi's avatarfrom sandraschi★ 3

Build, harden, document, and ship MCP servers to Claude standards with FastMCP 2.13+ architecture, disciplined tooling, and release-ready workflows.

serving-llms-vllm

davila7's avatarfrom davila7★ 15.4k

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

pinecone

davila7's avatarfrom davila7★ 15.4k

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

dspy

davila7's avatarfrom davila7★ 15.4k

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

markitdown

davila7's avatarfrom davila7★ 14.5k

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

Agent Browser

vercel-labs's avatarfrom vercel-labs★ 10.3k

A powerful skill for Claude agents.

sparc-methodology

ruvnet's avatarfrom ruvnet★ 9.9k

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

thealgorithm

danielmiessler's avatarfrom danielmiessler★ 4.3k

Universal execution engine using scientific method to achieve ideal state. USE WHEN complex tasks, multi-step work, "run the algorithm", "use the algorithm", OR any non-trivial request that benefits from structured execution with ISC (Ideal State Criteria) tracking.

scikit-learn

K-Dense-AI's avatarfrom K-Dense-AI★ 3.0k

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

polars

K-Dense-AI's avatarfrom K-Dense-AI★ 3.0k

Fast DataFrame library (Apache Arrow). Select, filter, group_by, joins, lazy evaluation, CSV/Parquet I/O, expression API, for high-performance data analysis workflows.

perplexity-search

K-Dense-AI's avatarfrom K-Dense-AI★ 3.0k

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model's knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.

tldr-code

parcadei's avatarfrom parcadei★ 2.2k

Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.

ai-multimodal

mrgoonie's avatarfrom mrgoonie★ 1.1k

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

browser-use

Saik0s's avatarfrom Saik0s★ 858

AI-driven browser automation via Model Context Protocol

ccw

catlog22's avatarfrom catlog22★ 837

Stateless workflow orchestrator that automatically selects and executes the optimal workflow combination based on task intent. Supports rapid (lite-plan+execute), full (brainstorm+plan+execute), coupled (plan+execute), bugfix (lite-fix), and issue (multi-point fixes) workflows. Triggers on "ccw", "workflow", "自动工作流", "智能调度".

prompt-mastery

taylorsatula's avatarfrom taylorsatula★ 336

Advanced LLM prompt engineering expertise for crafting highly effective prompts, system messages, and tool descriptions with Claude-specific techniques

Cloudflare Agents

jezweb's avatarfrom jezweb★ 207

A powerful skill for Claude agents.

context-engine

m1rl0k's avatarfrom m1rl0k★ 206

Codebase search and context retrieval for any programming language. Hybrid semantic/lexical search with neural reranking. Use for code lookup, finding implementations, understanding codebases, Q&A grounded in source code, and persistent memory across sessions.

orchestrationcreating-workflows

mbruhler's avatarfrom mbruhler★ 191

Use when user says "create workflow", "create a workflow", "design workflow", "orchestrate", "automate multiple steps", "coordinate agents", "multi-agent workflow". Creates orchestration workflows from natural language using Socratic questioning to plan multi-agent workflows with visualization.

playwright-browser-automation

smallnest's avatarfrom smallnest★ 110

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

ai-sdk-core

jezweb's avatarfrom jezweb★ 109

Build backend AI with Vercel AI SDK v5/v6. Covers v6 beta (Agent abstraction, tool approval, reranking),v4→v5 migration (breaking changes), latest models (GPT-5/5.1, Claude 4.x, Gemini 2.5), Workers startupfix, and 12 error solutions (AI_APICallError, AI_NoObjectGeneratedError, streamText silent errors).Use when: implementing AI SDK v5/v6, migrating v4→v5, troubleshooting errors, fixing Workers startupissues, or updating to latest models.

claude-agent-sdk

jezweb's avatarfrom jezweb★ 109

Build autonomous AI agents with Claude Agent SDK. Structured outputs (v0.1.45, Nov 2025) guarantee JSON schema validation, plugins system, hooks for event-driven workflows. Use when: building coding agents with validated JSON responses, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors.

clerk-auth

jezweb's avatarfrom jezweb★ 109

Clerk auth with API version 2025-11-10 breaking changes (billing endpoints, payment_source→payment_method), Next.js v6 async auth(), PKCE for custom OAuth, credential stuffing defense. Use when: troubleshooting "Missing Clerk Secret Key", JWKS errors, authorizedParties CSRF, JWT size limits (1.2KB), 431 header errors (Vite dev mode), or testing with 424242 OTP.

cloudflare-workers-ai

jezweb's avatarfrom jezweb★ 109

Run LLMs and AI models on Cloudflare's global GPU network with Workers AI. Includes Llama 4, Gemma 3, Mistral 3.1,Flux image generation, BGE embeddings (2x faster, 2025), streaming support, and AI Gateway for cost tracking.Use when: implementing LLM inference, generating images, building RAG with embeddings, streaming AI responses,using AI Gateway, troubleshooting max_tokens defaults (breaking change 2025), BGE pooling parameter (not backwardscompatible), or handling AI_ERROR, rate limits, model deprecations, token limits.Keywords: workers ai, cloudflare ai, ai bindings, llm workers, @cf/meta/llama-4-scout, @cf/google/gemma-3-12b-it,@cf/mistralai/mistral-small-3.1-24b-instruct, @cf/openai/gpt-oss-120b, workers ai models, ai inference,cloudflare llm, ai streaming, text generation ai, ai embeddings, bge pooling cls mean, image generation ai,workers ai rag, ai gateway, llama workers, flux image generation, deepgram aura, leonardo image generation,vision models ai, ai chat completion, AI_ERROR, rate li

drizzle-orm-d1

jezweb's avatarfrom jezweb★ 109

Build type-safe D1 databases with Drizzle ORM for Cloudflare Workers. Includes schema definition, migrationswith Drizzle Kit, relations, and D1 batch API patterns. Prevents 12 errors including SQL BEGIN failures.Use when: defining D1 schemas, managing migrations, writing type-safe queries, implementing relations orprepared statements, using batch API for transactions, or troubleshooting D1_ERROR, BEGIN TRANSACTION,foreign keys, migration apply, or schema inference errors.Prevents 12 documented issues: D1 transaction errors (SQL BEGIN not supported), foreign keyconstraint failures during migrations, module import errors with Wrangler, D1 binding not found,migration apply failures, schema TypeScript inference errors, prepared statement caching issues,transaction rollback patterns, TypeScript strict mode errors, drizzle.config.ts not found,remote vs local database confusion, and wrangler.toml vs wrangler.jsonc mixing.Keywords: drizzle orm, drizzle d1, type-safe sql, drizzle schema, drizzle migration

FAQ

What's the difference between MCP and Skills?

MCP (Model Context Protocol) connects your agent to live external systems — databases, APIs, browsers — through running servers. Skills (SKILL.md) are portable instruction packs that teach the agent how to do a task. They compose: a skill can tell the agent when and how to call an MCP tool. See our MCP vs Skills comparison in the install guide.

Can I use these skills to build my own MCP server?

Yes — several skills here scaffold MCP servers, generate tool schemas, and walk you through Streamable HTTP / stdio transports with working examples.

Does claudeskills.club offer a remote MCP server?

Yes — connect your agent to https://claudeskills.club/mcp to search 90,000+ skills, read SKILL.md files and list curated packs without leaving your editor. Setup takes one command; see the install guide's #mcp section.

How do I install these skills?

Run `npx skills add <owner/repo>` in your terminal, or copy SKILL.md into your agent's skills directory (~/.claude/skills, ~/.agents/skills, ~/.cursor/skills).