Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
⚠️ This implementation stores OAuth credentials in ./mnt/mcp-creds/ which are currently committed to the repository. Proper OAuth flow for MCP servers is coming soon to the Agencii platform.
Open security engineering for code written by humans and AI agents. Discover. Repair. Verify.
A starting point for Claude Code to Codex collaboration
AI-powered penetration testing MCP server
OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.
MCP server for FreeCAD — 32 tools for AI-assisted 3D CAD modeling
Shared MCP server for the Upvote.club Public API.
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.
Roblox Studio MCP server & plugin for Claude Code, Cursor, Codex, and Gemini. AI-powered scripts, terrain, assets, lighting, and bidirectional project sync.
Chat with AI, run tasks on autopilot, and manage your projects — all from one tab.
ChatCrystal is a local-first AI PKM app for developers who solve real problems with Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot.
Stop rewriting your tools. Just adapt them.
Agent Skills
A set of skills for Kotlin, Jetpack Compose, and Android development.
Reproduce any website — from a single-file static page to a WebGL-heavy interactive demo — without faking it from AI hallucinations. 把任何一个网站(从单文件静态页到 WebGL 重前端 demo)忠实复刻出来 —— 不靠 AI 臆测代码硬抄。
Enterprise-grade research engine for Claude Code. Produces citation-backed reports with source credibility scoring, multi-provider search, and automated validation.
Open-source, agent-agnostic CLI that gives AI coding agents eyes. Your agent builds a feature — ProofShot records video proof it works.
Ported from the TypeScript reference implementation and extended with a Python-native runtime
Professional white-box code security audit skill with 55+ vulnerability types, dual-track audit model, and multi-agent deep analysis.
This skill removes 20+ patterns of AI slop from your writing and it can also help you detect slop as well.
1. 对话 skill 模式：在聊天中按 SKILL.md 约束执行单轮改写；安装本仓库作为 skill 后即可直接使用。 2. 脚本 API 模式：通过 scripts/run_aigc_round.py 执行单轮分段处理，并按需调用外部 OpenAI 兼容接口。 3. Web 模式：启动本地后端和前端页面，在浏览器中完成上传、配置、执行和导出。 4. app：安装app可直接使用
Linear Chain-of-Thought anchors on whatever it says first. Tree-of-Thought widens the search but still walks a single shared context, so the anchoring persists across branches.
本项目把传统术数相关的 AI skill 拆成可审计、可复用、可逐步扩展的工程模块。目标不是把模型包装成“更会玄学”，而是尽量减少它在排盘、流派口径、步骤顺序和解释链路上的幻觉。
This repository contains sample prompts and agent instructions for Microsoft Copilot, GitHub Copilot, and Microsoft 365 Copilot.
A skill collection for creators who want to streamline writing, X Articles draft publishing, WeChat digital-asset capture, and local workflows with Claude Code and Codex.