Top 60 Claude Skills, Workflows, and GitHub Repos for AI — The Complete List.
I spent 100+ hours testing AI tools so you do not have to.
Save this :)
The AI tooling landscape in 2026 is overwhelming. New frameworks every week. New agents every day. New repos trending on GitHub every morning.
Most of them are hype. Some of them are genuinely useful. A few of them will fundamentally change how you work.
I filtered the noise. Here are the 60 tools that actually matter right now - organized by category, tested personally, with honest notes on what each one is actually good for.
Bookmark this. You will come back to it.
Part 1: AI Coding Agents & IDEs 🛠️
These are the tools that let AI write, review, and manage code on your behalf. The ones that actually work in real workflows, not just demos.
01. Claude Code:
Anthropic's command line coding agent. Reads files, writes code, runs tests, operates directly in your local environment. The gold standard for AI-assisted development when you want full control.
02. Cursor:
AI-first code editor built on VS Code. Inline completions, chat with your codebase, multi-file editing. The best editor for developers who want AI integrated into their existing workflow.
03. Codex CLI:
OpenAI's terminal coding agent. Takes natural language instructions, reads your codebase, writes and executes code. Strong at multi-step implementation tasks.
04. Windsurf:
AI coding IDE by Codeium. Cascade agent for multi-file editing, deep codebase understanding, and flow-state coding. Growing fast.
05. Superpowers:
20+ battle-tested Claude Code skills. TDD, debugging, plan-to-execute pipelines. 96,000+ stars on GitHub. If you use Claude Code, install this first.
06. Spec Kit (GitHub):
Spec-driven development. Write specifications, AI generates code from them. Forces you to think before you build. 50,000+ stars.
07. Aider:
AI pair programming in your terminal. Works with any LLM. Strong at working with existing codebases. 30,000+ stars.
Part 2: Agent Frameworks 🤖
Build autonomous systems that think, act, and iterate.
08. OpenClaw:
The viral open-source AI agent. Persistent, multi-channel (WhatsApp, Telegram, Discord), writes its own skills. 210,000+ stars and growing fast. The most accessible entry point for personal AI agents.
09. LangGraph:
Multi-agent orchestration as code. Build agents as graphs with branching logic, human-in-the-loop, and persistent state. 26,000+ stars.
10. CrewAI:
Multi-agent framework with roles, goals, and backstories. Each agent has a defined persona and responsibility. Good for team-like workflows.
11. AutoGPT:
Full autonomous agent platform for long-running tasks. The OG agent framework. Matured significantly since early days.
12. Dify:
Open-source LLM app builder. Combines workflows, RAG, agents, and model management in one platform. Good for non-developers building AI apps.
13. OWL:
Multi-agent cooperation framework. Tops the GAIA benchmark for agent coordination. Cutting edge research turned into usable code.
14. CopilotKit:
Embed AI copilots directly into React applications. Ship AI features in your product, not just your workflow.
15. pydantic-ai:
Type-safe agent framework built on Pydantic. For Python developers who want structured, validated agent outputs.
Part 3: MCP Servers & Tool Integration 🔗
MCP (Model Context Protocol) gives AI access to the outside world. Skills teach it HOW. MCP gives it ACCESS.
16. Tavily:
Search engine built for AI agents. Not blue links - clean, structured, LLM-ready data. Four tools: search, extract, crawl, map. Connects as remote MCP in one minute.
17. Context7:
Injects up-to-date library documentation into your LLM's context. No more hallucinated APIs or deprecated methods. Add "use context7" to your prompt and it pulls current docs. Supports thousands of libraries.
18. Task Master AI:
Your AI's project manager. Feed it a PRD and it generates structured tasks with dependencies. Claude executes them one by one. Turns chaotic sessions into organized pipelines.
19. MCP Playwright:
Browser automation for LLMs. Control a real browser through natural language. Testing, scraping, interaction.
20. fastmcp:
Build MCP servers in minimal Python. The fastest way to create custom tool integrations for Claude or any MCP-compatible model.
21. markdownify-mcp:
Convert PDFs, images, and audio into Markdown. Feed any document type into your AI workflow.
22. MCPHub:
Manage multiple MCP servers via HTTP. One dashboard for all your tool connections.
Part 4: Claude Skills (Top Picks) 🧠
Skills teach Claude specialized workflows. There are 80,000+ community skills. These are the ones worth installing.
23. PDF Processing (Official):
Read, extract tables, fill forms, merge and split PDFs. The highest-utility skill for knowledge workers.
24. Frontend Design (Official): Build real design systems, bold typography, production-grade UI. Escape the "AI slop" aesthetic. 277,000+ installs.
25. Skill Creator (Official):
The meta-skill. Describe a workflow in plain English and get a complete SKILL.md back in five minutes. Build new skills without writing any configuration.
26. Marketing Skills by Corey Haines:
20+ skills covering CRO, copywriting, SEO, email sequences, growth strategy. Everything a marketing team needs in skill form.
27. Claude SEO:
Full-site audits, schema validation, keyword analysis. 12 sub-skills covering the complete SEO workflow.
28. Obsidian Skills:
Built by Obsidian's CEO. Auto-tagging, auto-linking, vault-native operations. If you use Obsidian, this is essential.
29. Context Optimization:
Reduce token costs and improve KV-cache efficiency. Makes expensive API workflows significantly cheaper. 13,900+ stars.
30. Deep Research Skill:
8-phase research with auto-continuation. For when you need Claude to go deep on a topic, not just skim the surface.
Part 5: Local AI & Model Running 🖥️
Run models on your own hardware. Privacy, speed, zero API costs.
31. Ollama:
Run open-source LLMs locally with one terminal command. Supports Llama, Mistral, Gemma, and dozens more. The fastest path from zero to local AI.
32. Open WebUI:
Self-hosted ChatGPT-like interface. Clean, fast, full-featured. Pairs perfectly with Ollama for a private AI setup.
33. LlamaFile:
Package an entire LLM as a single executable file. Zero dependencies. Download and run. Absurdly simple.
34. Unsloth:
Fine-tune models 2x faster with 70% less memory. If you need a custom model trained on your data, start here.
35. vLLM:
High-throughput inference engine. 2 to 4x faster than naive serving. The standard for production deployment of open-source models.
Part 6: Workflow & Automation ⚡
Connect AI to your existing tools and processes.
36. n8n:
Open-source workflow automation with 400+ integrations and AI nodes. Self-hostable. The best visual builder for AI-powered automations.
37. Langflow:
Visual drag-and-drop for agent pipelines. 140,000+ stars. Build complex agent workflows without writing code.
38. Huginn:
Self-hosted web agents for monitoring, alerts, and data collection. Privacy-first automation that runs on your server.
39. DSPy:
Program (not prompt) foundation models. Stanford research turned framework. For when prompting is not deterministic enough.
40. Temporal:
Durable workflow engine for long-running processes. When your automation needs to survive crashes, retries, and timeouts.
Part 7: Search, Data & RAG 🔍
Get information into and out of AI systems.
41. GPT Researcher:
Autonomous research agent that produces compiled reports. Give it a topic, get back a thorough analysis with sources.
42. Firecrawl:
Turn any website into LLM-ready data. Web scraping designed specifically for AI pipelines.
43. Vanna AI:
Natural language to SQL. Ask questions in English, get database queries back. For anyone who needs data from databases without writing SQL.
44. Instructor:
Get structured JSON outputs from any LLM using Pydantic models. Works with OpenAI, Anthropic, Google, and 15+ providers. What production AI engineers actually use.
45. Chroma:
Open-source vector database. The simplest way to add semantic search and long-term memory to your AI applications.
46. dlt:
LLM-native data pipelines from 5,000+ sources. Get data from anywhere into your AI workflow.
47. ExtractThinker:
ORM for document intelligence. Extract structured data from any document type.
Part 8: API & Infrastructure 🏗️
The plumbing that makes everything work in production.
48. FastAPI:
The Python web framework for serving AI applications. Exceptional documentation. Pydantic validation built in.
49. Portkey Gateway:
Route requests to 250+ LLMs through one API. Switch models without changing code.
50. OmniRoute:
API proxy for 44+ AI providers. Load balancing, fallbacks, and cost optimization.
51. lmnr:
Trace and evaluate agent behavior. See exactly what your agents are doing and measure whether they are doing it well.
52. Codebase Memory MCP:
Convert your codebase into a persistent knowledge graph. Claude remembers your entire project structure across sessions.
Part 9: Curated Collections & Learning 📚
Where to find more and keep learning.
53. Awesome Claude Skills:
The best curated skill list. 22,000+ stars. Start here when looking for new skills to install.
54. Anthropic Skills Repo:
Official reference implementations from Anthropic. The gold standard for how skills should be built.
55. Awesome Agents:
100+ open-source agent tools in one curated list.
56. PromptingGuide:
Comprehensive prompt engineering reference covering every technique from basics to advanced agent prompting.
57. Anthropic Prompt Engineering Tutorial:
9 chapters of hands-on exercises with Jupyter notebooks. The best structured way to learn prompting.
58. SkillsMP:
Marketplace with 80,000+ community skills. The largest catalog for discovering Claude skills.
59. MAGI//ARCHIVE:
Daily feed of fresh AI repos. Stay on top of what is shipping.
60. Anthropic Official Docs:
Covers the API, prompting best practices, tool use, agents, and everything else. Read this cover to cover before building anything serious.
How to Actually Use This List
Do not try to install all 60 tools at once. That is a recipe for overwhelm and wasted time.
Here is the order I recommend:
If you are a developer:
Start with Claude Code (01) + Superpowers (05) + Context7 (17) + Tavily (16). This gives you a powerful AI coding setup with search and documentation access.
If you are a creator or knowledge worker:
Start with OpenClaw (08) + Obsidian Skills (28) + PDF Processing (23) + Frontend Design (24). This gives you an AI assistant with file management, document processing, and content creation capabilities.
If you are building a product:
Start with FastAPI (48) + Instructor (44) + Chroma (45) + LangGraph (09). This gives you the backend framework, structured outputs, memory, and agent orchestration for a production AI application.
If you want to learn:
Start with the Anthropic Tutorial (57) + PromptingGuide (56) + Anthropic Docs (60). Build the foundation before you stack tools.
Pick one path. Go deep. Add more tools as your needs grow.
TL;DR
Skills = teach AI HOW to do things better. MCP = give AI ACCESS to external tools and data. Repos = the open-source engines powering it all.
Combine all three and you have an AI workflow that is genuinely powerful, not just impressive in demos.
That is it. 60 tools. Now go build something.
This list took me a long time to compile - testing tools, reading docs, filtering out the hype from the useful. If it saved you time, you know what to do.
I post stuff like this regularly - AI tools, workflows, techniques, and things I actually use. No fluff, no hype, just what works.
Follow @eng_khairallah1 so you do not miss the next one.
hope this was useful for you, Khairallah ❤️
