Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
A mcp server that bridges Dune Analytics data to AI agents.
Local academic paper tool MCP server — , multi-source download, AI-powered analysis, citation graph, code-based paper recommendation.
The MCP ecosystem has grown to 10,000+ servers, but discovering and installing them remains painful. Existing directories — Glama, PulseMCP, mcp.so — are all closed source.
The polished public release — native ComfyUI design system, live activity cards for every agent edit, and multi-tab support. Search in ComfyUI-Manager to install, or see the docs.
An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Video Search, Image Search, News Search and LLM Context Search capabilities
SpringAI和SpringAI-alibaba都发布了最新依赖稳定版本（之前基于快照版本需要设置Repository 如今已经不需要设置），如果遇到依赖下载不下来请按照最新的官方文档修改依赖版本，官网快照版本更新很快可能出现API冲突的情况 请以最新版本的API设计为准 推荐参考文档：https://java2ai.com/docs/1.0.0.
A powerful Clojure-based MCP server built for querying DataScript and integrating with AI workflows.
Agent Skills
把 Taiji / TAAC 训练与评估平台变成任何人和任何 agent 都能读取、比较、归档、提交训练、发布模型和收集线上评估证据的实验命令行工具。
An open agentic prompt-expansion harness for image and video generation. Turn everyday intent into validated, model-ready prompts through a bounded AI-agent workflow.
Podcast to Course 专治这种「听过 ≈ 学会」的错觉：它把播客变成**，让洞见不再从左耳朵进、右耳朵拿着离职证明出去。
A Claude skill that checks whether your idea already exists before you build it.
✨ - Type #snippet anywhere in your message and watch it transform.
Drop in a PNG, JPEG or BMP. Get back SVG, EPS, DXF, PDF or PNG. No account, no credits, no subscription. Offline by default.
同一個問題，多幾種看法。涵蓋十大領域的思考輔助 skill，幫你換角度理解問題、找出其他解釋與選項，並檢查成立條件。適用於 ChatGPT、Claude 與 Codex。
The is an open standard that defines what "AI-ready" actually means — six factors, 62 measurable requirements, and five workload profiles that apply to any data platform.
基于 huobao-drama 参考设计，使用 Next.js 16 + 多AI供应商架构 构建。
First human cognitive framework integrated into an LLM. Claude learns to detect if you're assessing, deciding, or doing—and responds appropriately.
AI가 쓴 한국어 초안을 한 사람의 실제 문체로 재작성하는 Claude Code 스킬입니다. 문체를 느낌이 아니라 측정값으로 다루죠
Don't make LLMs honest. Make every factual claim auditable. Do not gag the model. Strip its hallucinations sentence by sentence.