Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not a framework. Just pro
in the skill textReality Check You're a solo dev. You don't have: - A QA team - A code reviewer - A DevOps engineer - Time to waste on AI agents
SkillMIT★ 149No key
AI agent task board for Claude Code, Codex, Gemini CLI and Grok Build: plan, approve, build and review inside JetBrains or VS Code, with state in .moe/ in your repo
in the readmeclear roles, review their plans, and follow the work through implementation and QA.  Platforms Works with ** Get started · See the workflow · Features
SkillMIT★ 33No key
IncarnaMind is a free, open-source desktop app for macOS, Windows and Linux where you write with AI and ask questions about your own documents (PDF, Word, PowerPoint, Excel and more). It can check eve
SkillApache-2.0★ 814No key
AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude
in the readmeagent needing to stay awake and wait. ### Events Events are named signals — `qa_passed`, `deploy_finished`, `blog_published` — that any task can fire when it completes
SkillAGPL-3.0★ 1.2kNo key
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
in the readmewhere work is stuck, and who reviewed or approved it across developers, QA, PMs, tools, machines, and environments. 📚 **Documentation:** https://docs.forkflux.ai/ > 🎥 **ForkFlux in action** ## Why ForkFlux
PythonApache-2.0★ 6Needs a key
MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a verdict, and the agent iterates until approved.
Node.jsMIT★ 128No key
A lively Capybara Lulu desktop pet for Codex, with smooth expressive animation, task-aware reactions, 16-direction gaze, and complete source frames.
in the skill textacross the nine real Codex triggers; the static atlas remains available for QA, editing, and reduced-motion fallback. | Lulu's behavior | What ships | | :--- | :--- | | 🌿 **Expressive idle
SkillApache-2.0★ 25No key
Give AI coding agents product, spec, task, QA, and release workflows in one command.
SkillMIT★ 20No key
MCP servers for Microsoft Office — Excel, Outlook, PowerPoint, Word. Local-first, governed, developer-controlled.
in the readmeinstall mcp-office` | 51 | | `wordmcp` | Template assembly, tracked-changes support, and structural QA for Word documents | `pip install mcp-office` | 50 | ### 🚧 Coming next | Package | Status | |---|---| | `mailmcp
PythonMIT★ 8No key
Free GTM diagnostic skills for Claude by Growth Cab: cold email domain check, cold email grader, lead list QA, B2B meeting show rate benchmark
SkillMIT★ 1Few starsNo key
驱动的项目管理 MCP 服务器,50 个工具覆盖任务管理、Spec 驱动开发、多 Agent 协作、自动驾驶引擎|AI-powered project management MCP server — 50 tools for Claude Code / Cursor / Windsurf / Codex. Task tracking, spec-driven devAI elopment, mul
in the readme对 AI 说"帮我做个代码评审"** → qflow 召唤 12 个 Agent 角色(PM / 架构师 / QA / 安全 / DBA / DevOps),多视角对抗性评审 🎨 **对 AI 说"生成一个加载动画"** → qflow 从 34 种模板中选择,输出标准
Node.jsMIT★ 9No key
Disposable email (temp mail) CLI + MCP server for AI agents. Spawn a throwaway inbox, wait for the OTP verification code, toss it. --json on every command, exit codes 0-4, no sign-up, no API keys. Nod
in the readmewhen you are done — server-side and locally. Use it for signups, QA email flows, and test automation — or let your **AI agent** do all
Node.jsMIT★ 1Few starsNo key
AI-powered marketing skills, templates & resources for Claude Code and Cowork — 90-day content tracker, 230+ tweets, reply templates, curated tools
in the skill textfor opportunity threads, target account lists, search keywords, media production queue, and QA validation. All customized to your product. | ✅ Ready | ### Resources — Browse all → Curated collection
SkillMIT★ 3Few starsNo key
MCP server for building brand-styled HTML email campaigns from a website URL
in the readmebrand website, build an email design system from it, assemble responsive campaigns, QA the rendering and export production HTML. **Remote MCP endpoint** ``` ``` Transport: streamable HTTP. Authentication
SkillMITFew starsNo key
Claude Code, fixed for everyone. Memory that survives sessions, agents that finish what they start, QA gates before 'done', the right model for each job. 235+ skills, 35+ agents. Installs to ~/.claude
SkillLink only★ 5
Orchestrate Claude Code sub-agents across long-running, single- or multi-repo projects. Artifact-first state, task lifecycle, cross-repo dependencies and QA gates that survive every session - not buri
SkillLink only★ 4Few stars
Persistent, verifiable identities for AI agents with SES-backed email mailboxes (client + MCP server)
in the readmeplaceholder, because there's no S3 locally. ### Side-by-side PR QA `pnpm qa` lets a reviewer try a pull request against real fleet data before
Node.jsMIT★ 1Few starsNo key
MCP server + Claude Code plugin: multi-agent advisory squad with PRD-decomposed tasks, persistent learnings, weighted rubric scorecard, and PR posting.
in the readmefiles and prints something like `work_type: Feature, risk: Low, agents: [developer, qa]`. 2. **Depth resolution.** It also picks an execution depth — `quick`, `normal`, or `deep
Node.jsApache-2.0★ 4Few starsNo key
Who stands behind it
Who stands behind it