Best customer support skills for AI agents

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Excellent quality, 78K stars, and a 19 use-case fit score.

Open-source LLM-friendly web crawler and scraper

Excellent quality, 66K stars, and a 19 use-case fit score.

A curated list of resources and tools for enhancing Claude AI workflows.

Excellent quality, 61K stars, and a 18 use-case fit score.

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

Excellent quality, 52K stars, and a 18 use-case fit score.

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Excellent quality, 36K stars, and a 18 use-case fit score.

Build Real-Time Knowledge Graphs for AI Agents

Excellent quality, 26K stars, and a 18 use-case fit score.

A comprehensive set of agent skills designed for various scientific and analytical applications.

Excellent quality, 25K stars, and a 18 use-case fit score.

A comprehensive collection of ready-to-use scientific and research skills for AI agents.

Excellent quality, 25K stars, and a 18 use-case fit score.

NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.

Excellent quality, 22K stars, and a 17 use-case fit score.

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

Excellent quality, 38K stars, and a 17 use-case fit score.

A skill for implementing persistent markdown planning workflows inspired by a successful AI agent acquisition.

Excellent quality, 22K stars, and a 17 use-case fit score.

280+ free n8n automation templates — ready-to-use workflows for Gmail, Telegram, Slack, Discord, WhatsApp, Google Drive, Notion, OpenAI, and more. AI agents, RAG chatbots, email automation, social media, DevOps, and document processing. The largest open-source n8n template collection.

Excellent quality, 22K stars, and a 17 use-case fit score.

A repository of skills designed to enhance daily work efficiency with Claude Code.

Excellent quality, 19K stars, and a 17 use-case fit score.

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

Excellent quality, 18K stars, and a 17 use-case fit score.

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Excellent quality, 18K stars, and a 17 use-case fit score.

Pre-indexed code knowledge graph for Claude Code, Codex, Cursor, OpenCode, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

Excellent quality, 18K stars, and a 17 use-case fit score.

A comprehensive library of skills and plugins for various AI coding tools, enhancing productivity and functionality.

Excellent quality, 16K stars, and a 17 use-case fit score.

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Excellent quality, 16K stars, and a 17 use-case fit score.

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Excellent quality, 15K stars, and a 17 use-case fit score.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

Excellent quality, 22K stars, and a 17 use-case fit score.

A comprehensive marketplace for AI-driven product management skills and workflows.

Excellent quality, 12K stars, and a 17 use-case fit score.

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

Excellent quality, 11K stars, and a 17 use-case fit score.

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.

Excellent quality, 7.9K stars, and a 16 use-case fit score.

Pocket Flow: Codebase to Tutorial

Excellent quality, 12K stars, and a 16 use-case fit score.

Plano is an AI-native proxy and data plane for agentic apps — with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic.

Excellent quality, 6.5K stars, and a 16 use-case fit score.

Build and run autonomous AI agents for open-ended tasks

Excellent quality, 184K stars, and a 16 use-case fit score.

Agent engineering primitives for tools, memory, and RAG

Excellent quality, 137K stars, and a 16 use-case fit score.

Convert documents into Markdown for agent-readable context

Excellent quality, 125K stars, and a 16 use-case fit score.

Bring a coding agent directly into the terminal

Excellent quality, 105K stars, and a 16 use-case fit score.

ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.

Excellent quality, 5.7K stars, and a 16 use-case fit score.