时地方
This commit is contained in:
+456
@@ -0,0 +1,456 @@
|
||||
---
|
||||
title: "Top 60 Claude Skills, Workflows, and GitHub Repos for AI — The Complete List."
|
||||
source: "https://x.com/eng_khairallah1/status/2037816689665147355"
|
||||
author:
|
||||
- "[[Unknown]]"
|
||||
published: 2026-03-28
|
||||
created: 2026-03-28
|
||||
description:
|
||||
tags:
|
||||
- "clippings"
|
||||
---
|
||||
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.
|
||||
|
||||
🔗 [https://docs.anthropic.com/en/docs/claude-code](https://docs.anthropic.com/en/docs/claude-code)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://www.cursor.com](https://www.cursor.com/)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://github.com/openai/codex](https://github.com/openai/codex)
|
||||
|
||||
**04\. Windsurf:**
|
||||
|
||||
AI coding IDE by Codeium. Cascade agent for multi-file editing, deep codebase understanding, and flow-state coding. Growing fast.
|
||||
|
||||
🔗 [https://codeium.com/windsurf](https://codeium.com/windsurf)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://github.com/obra/superpowers](https://github.com/obra/superpowers)
|
||||
|
||||
**06\. Spec Kit (GitHub):**
|
||||
|
||||
Spec-driven development. Write specifications, AI generates code from them. Forces you to think before you build. 50,000+ stars.
|
||||
|
||||
🔗 [https://github.com/github/spec-kit](https://github.com/github/spec-kit)
|
||||
|
||||
**07\. Aider:**
|
||||
|
||||
AI pair programming in your terminal. Works with any LLM. Strong at working with existing codebases. 30,000+ stars.
|
||||
|
||||
🔗 [https://github.com/paul-gauthier/aider](https://github.com/paul-gauthier/aider)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/openclaw/openclaw](https://github.com/openclaw/openclaw)
|
||||
|
||||
**09\. LangGraph:**
|
||||
|
||||
Multi-agent orchestration as code. Build agents as graphs with branching logic, human-in-the-loop, and persistent state. 26,000+ stars.
|
||||
|
||||
🔗 [https://github.com/langchain-ai/langgraph](https://github.com/langchain-ai/langgraph)
|
||||
|
||||
**10\. CrewAI:**
|
||||
|
||||
Multi-agent framework with roles, goals, and backstories. Each agent has a defined persona and responsibility. Good for team-like workflows.
|
||||
|
||||
🔗 [https://github.com/crewAIInc/crewAI](https://github.com/crewAIInc/crewAI)
|
||||
|
||||
**11\. AutoGPT:**
|
||||
|
||||
Full autonomous agent platform for long-running tasks. The OG agent framework. Matured significantly since early days.
|
||||
|
||||
🔗 [https://github.com/Significant-Gravitas/AutoGPT](https://github.com/Significant-Gravitas/AutoGPT)
|
||||
|
||||
**12\. Dify:**
|
||||
|
||||
Open-source LLM app builder. Combines workflows, RAG, agents, and model management in one platform. Good for non-developers building AI apps.
|
||||
|
||||
🔗 [https://github.com/langgenius/dify](https://github.com/langgenius/dify)
|
||||
|
||||
**13\. OWL:**
|
||||
|
||||
Multi-agent cooperation framework. Tops the GAIA benchmark for agent coordination. Cutting edge research turned into usable code.
|
||||
|
||||
🔗 [https://github.com/camel-ai/owl](https://github.com/camel-ai/owl)
|
||||
|
||||
**14\. CopilotKit:**
|
||||
|
||||
Embed AI copilots directly into React applications. Ship AI features in your product, not just your workflow.
|
||||
|
||||
🔗 [https://github.com/CopilotKit/CopilotKit](https://github.com/CopilotKit/CopilotKit)
|
||||
|
||||
**15\. pydantic-ai:**
|
||||
|
||||
Type-safe agent framework built on Pydantic. For Python developers who want structured, validated agent outputs.
|
||||
|
||||
🔗 [https://github.com/pydantic/pydantic-ai](https://github.com/pydantic/pydantic-ai)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/tavily-ai/tavily-mcp](https://github.com/tavily-ai/tavily-mcp)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://github.com/upstash/context7](https://github.com/upstash/context7)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://github.com/eyaltoledano/claude-task-master](https://github.com/eyaltoledano/claude-task-master)
|
||||
|
||||
**19\. MCP Playwright:**
|
||||
|
||||
Browser automation for LLMs. Control a real browser through natural language. Testing, scraping, interaction.
|
||||
|
||||
🔗 [https://github.com/executeautomation/mcp-playwright](https://github.com/executeautomation/mcp-playwright)
|
||||
|
||||
**20\. fastmcp:**
|
||||
|
||||
Build MCP servers in minimal Python. The fastest way to create custom tool integrations for Claude or any MCP-compatible model.
|
||||
|
||||
🔗 [https://github.com/jlowin/fastmcp](https://github.com/jlowin/fastmcp)
|
||||
|
||||
**21\. markdownify-mcp:**
|
||||
|
||||
Convert PDFs, images, and audio into Markdown. Feed any document type into your AI workflow.
|
||||
|
||||
🔗 [https://github.com/zcaceres/markdownify-mcp](https://github.com/zcaceres/markdownify-mcp)
|
||||
|
||||
**22\. MCPHub:**
|
||||
|
||||
Manage multiple MCP servers via HTTP. One dashboard for all your tool connections.
|
||||
|
||||
🔗 [https://github.com/samanhappy/mcphub](https://github.com/samanhappy/mcphub)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/anthropics/skills/tree/main/skills/pdf](https://github.com/anthropics/skills/tree/main/skills/pdf)
|
||||
|
||||
**24\. Frontend Design (Official):** Build real design systems, bold typography, production-grade UI. Escape the "AI slop" aesthetic. 277,000+ installs.
|
||||
|
||||
🔗 [https://github.com/anthropics/skills/tree/main/skills/frontend-design](https://github.com/anthropics/skills/tree/main/skills/frontend-design)
|
||||
|
||||
**25\. Skill Creator (Official):**
|
||||
|
||||
The meta-skill. Describe a workflow in plain English and get a complete [SKILL.md](http://skill.md/) back in five minutes. Build new skills without writing any configuration.
|
||||
|
||||
🔗 [https://github.com/anthropics/skills/tree/main/skills/skill-creator](https://github.com/anthropics/skills/tree/main/skills/skill-creator)
|
||||
|
||||
**26\. Marketing Skills** by Corey Haines:
|
||||
|
||||
20+ skills covering CRO, copywriting, SEO, email sequences, growth strategy. Everything a marketing team needs in skill form.
|
||||
|
||||
🔗 [https://github.com/coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills)
|
||||
|
||||
**27\. Claude SEO:**
|
||||
|
||||
Full-site audits, schema validation, keyword analysis. 12 sub-skills covering the complete SEO workflow.
|
||||
|
||||
🔗 [https://github.com/AgriciDaniel/claude-seo](https://github.com/AgriciDaniel/claude-seo)
|
||||
|
||||
**28\. Obsidian Skills:**
|
||||
|
||||
Built by Obsidian's CEO. Auto-tagging, auto-linking, vault-native operations. If you use Obsidian, this is essential.
|
||||
|
||||
🔗 [https://github.com/kepano/obsidian-skills](https://github.com/kepano/obsidian-skills)
|
||||
|
||||
**29\. Context Optimization:**
|
||||
|
||||
Reduce token costs and improve KV-cache efficiency. Makes expensive API workflows significantly cheaper. 13,900+ stars.
|
||||
|
||||
🔗 [https://github.com/muratcankoylan/agent-skills-for-context-engineering](https://github.com/muratcankoylan/agent-skills-for-context-engineering)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://github.com/199-biotechnologies/claude-deep-research-skill](https://github.com/199-biotechnologies/claude-deep-research-skill)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/ollama/ollama](https://github.com/ollama/ollama)
|
||||
|
||||
**32\. Open WebUI:**
|
||||
|
||||
Self-hosted ChatGPT-like interface. Clean, fast, full-featured. Pairs perfectly with Ollama for a private AI setup.
|
||||
|
||||
🔗 [https://github.com/open-webui/open-webui](https://github.com/open-webui/open-webui)
|
||||
|
||||
**33\. LlamaFile:**
|
||||
|
||||
Package an entire LLM as a single executable file. Zero dependencies. Download and run. Absurdly simple.
|
||||
|
||||
🔗 [https://github.com/Mozilla-Ocho/llamafile](https://github.com/Mozilla-Ocho/llamafile)
|
||||
|
||||
**34\. Unsloth:**
|
||||
|
||||
Fine-tune models 2x faster with 70% less memory. If you need a custom model trained on your data, start here.
|
||||
|
||||
🔗 [https://github.com/unslothai/unsloth](https://github.com/unslothai/unsloth)
|
||||
|
||||
**35\. vLLM:**
|
||||
|
||||
High-throughput inference engine. 2 to 4x faster than naive serving. The standard for production deployment of open-source models.
|
||||
|
||||
🔗 [https://github.com/vllm-project/vllm](https://github.com/vllm-project/vllm)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/n8n-io/n8n](https://github.com/n8n-io/n8n)
|
||||
|
||||
**37\. Langflow:**
|
||||
|
||||
Visual drag-and-drop for agent pipelines. 140,000+ stars. Build complex agent workflows without writing code.
|
||||
|
||||
🔗 [https://github.com/langflow-ai/langflow](https://github.com/langflow-ai/langflow)
|
||||
|
||||
**38\. Huginn:**
|
||||
|
||||
Self-hosted web agents for monitoring, alerts, and data collection. Privacy-first automation that runs on your server.
|
||||
|
||||
🔗 [https://github.com/huginn/huginn](https://github.com/huginn/huginn)
|
||||
|
||||
**39\. DSPy:**
|
||||
|
||||
Program (not prompt) foundation models. Stanford research turned framework. For when prompting is not deterministic enough.
|
||||
|
||||
🔗 [https://github.com/stanfordnlp/dspy](https://github.com/stanfordnlp/dspy)
|
||||
|
||||
**40\. Temporal:**
|
||||
|
||||
Durable workflow engine for long-running processes. When your automation needs to survive crashes, retries, and timeouts.
|
||||
|
||||
🔗 [https://github.com/temporalio/temporal](https://github.com/temporalio/temporal)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher)
|
||||
|
||||
**42\. Firecrawl:**
|
||||
|
||||
Turn any website into LLM-ready data. Web scraping designed specifically for AI pipelines.
|
||||
|
||||
🔗 [https://github.com/mendableai/firecrawl](https://github.com/mendableai/firecrawl)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://github.com/vanna-ai/vanna](https://github.com/vanna-ai/vanna)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://python.useinstructor.com](https://python.useinstructor.com/)
|
||||
|
||||
**45\. Chroma:**
|
||||
|
||||
Open-source vector database. The simplest way to add semantic search and long-term memory to your AI applications.
|
||||
|
||||
🔗 [https://github.com/chroma-core/chroma](https://github.com/chroma-core/chroma)
|
||||
|
||||
**46\. dlt:**
|
||||
|
||||
LLM-native data pipelines from 5,000+ sources. Get data from anywhere into your AI workflow.
|
||||
|
||||
🔗 [https://github.com/dlt-hub/dlt](https://github.com/dlt-hub/dlt)
|
||||
|
||||
**47\. ExtractThinker:**
|
||||
|
||||
ORM for document intelligence. Extract structured data from any document type.
|
||||
|
||||
🔗 [https://github.com/enoch3712/ExtractThinker](https://github.com/enoch3712/ExtractThinker)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/tiangolo/fastapi](https://github.com/tiangolo/fastapi)
|
||||
|
||||
**49\. Portkey Gateway:**
|
||||
|
||||
Route requests to 250+ LLMs through one API. Switch models without changing code.
|
||||
|
||||
🔗 [https://github.com/Portkey-AI/gateway](https://github.com/Portkey-AI/gateway)
|
||||
|
||||
**50\. OmniRoute:**
|
||||
|
||||
API proxy for 44+ AI providers. Load balancing, fallbacks, and cost optimization.
|
||||
|
||||
🔗 [https://github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute)
|
||||
|
||||
**51\. lmnr:**
|
||||
|
||||
Trace and evaluate agent behavior. See exactly what your agents are doing and measure whether they are doing it well.
|
||||
|
||||
🔗 [https://github.com/lmnr-ai/lmnr](https://github.com/lmnr-ai/lmnr)
|
||||
|
||||
**52\. Codebase Memory MCP:**
|
||||
|
||||
Convert your codebase into a persistent knowledge graph. Claude remembers your entire project structure across sessions.
|
||||
|
||||
🔗 [https://github.com/DeusData/codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp)
|
||||
|
||||
# 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.
|
||||
|
||||
🔗 [https://github.com/travisvn/awesome-claude-skills](https://github.com/travisvn/awesome-claude-skills)
|
||||
|
||||
**54\. Anthropic Skills Repo:**
|
||||
|
||||
Official reference implementations from Anthropic. The gold standard for how skills should be built.
|
||||
|
||||
🔗 [https://github.com/anthropics/skills](https://github.com/anthropics/skills)
|
||||
|
||||
**55\. Awesome Agents:**
|
||||
|
||||
100+ open-source agent tools in one curated list.
|
||||
|
||||
🔗 [https://github.com/kyrolabs/awesome-agents](https://github.com/kyrolabs/awesome-agents)
|
||||
|
||||
**56\. PromptingGuide:**
|
||||
|
||||
Comprehensive prompt engineering reference covering every technique from basics to advanced agent prompting.
|
||||
|
||||
🔗 [https://www.promptingguide.ai](https://www.promptingguide.ai/)
|
||||
|
||||
**57\. Anthropic Prompt Engineering Tutorial:**
|
||||
|
||||
9 chapters of hands-on exercises with Jupyter notebooks. The best structured way to learn prompting.
|
||||
|
||||
🔗 [https://github.com/anthropics/prompt-eng-interactive-tutorial](https://github.com/anthropics/prompt-eng-interactive-tutorial)
|
||||
|
||||
**58\. SkillsMP:**
|
||||
|
||||
Marketplace with 80,000+ community skills. The largest catalog for discovering Claude skills.
|
||||
|
||||
🔗 [https://skillsmp.com](https://skillsmp.com/)
|
||||
|
||||
**59\. MAGI//ARCHIVE:**
|
||||
|
||||
Daily feed of fresh AI repos. Stay on top of what is shipping.
|
||||
|
||||
🔗 [https://tom-doerr.github.io/repo\_posts/](https://tom-doerr.github.io/repo_posts/)
|
||||
|
||||
**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.
|
||||
|
||||
🔗 [https://docs.anthropic.com](https://docs.anthropic.com/)
|
||||
|
||||
# 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](https://x.com/@eng_khairallah1) **so you do not miss the next one.**
|
||||
|
||||
**hope this was useful for you, Khairallah** **❤️**
|
||||
Reference in New Issue
Block a user