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.
Internal implementation skill invoked by /add-native for camera, image picker, barcode scanner, QR scanner, and camera/gallery Dataverse artifact workflows.
in the skill textThis skill **only writes JS files under `src/native/`**. It does not install modules or touch `package.json` / `app.config.js`. Only the modules required by the approved artifact set
OfficialSkillMIT★ 1.0k in collectionNo key
Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-sp
in the skill textBefore making framework changes, read the bundled Optimizing prefetching guide at `node_modules/next/dist/docs/01-app/02-guides/optimizing-prefetching.md`. If the bundled guide is unavailable, use the online guide . It is the
OfficialSkillMIT★ 143k in collectionNo key
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwri
in the skill textthe route, read the bundled **Optimizing the static shell** guide at `node_modules/next/dist/docs/01-app/02-guides/optimizing-the-static-shell.md`. If it is unavailable, use the online guide . The guide owns the framework
OfficialSkillMIT★ 143k in collectionNo key
Public entry point for native device capabilities and native controls — camera, image picker, barcode/QR scanner, document picker, file picker, secure storage, file system, sharing, haptic feedback, P
in the skill textupstream template already ships. Screens import the wrapper instead of touching Expo modules directly, so the discriminated-union result contract stays consistent. ## Hard rules — do NOT
OfficialSkillMIT★ 1.0k in collectionNo key
🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security work
in the readmeSuite 🌐 Web Demo • 📚 Project Website • 💬 Community Chat Website Navigation: Home • Updates • Downloads • Modules 🧠 Conceptual Overview AI Security Tool is an open-source, cross-platform ecosystem designed
SkillMIT★ 567No key
Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。
in the skill textalways do: ``` > Explain the TCP three-way handshake > Map out how the modules in this repo fit together > Redis or Memcached for our cache? ``` The agent
SkillMIT★ 3.3kNo key
Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, reads draft_content.json and draft_info.jso
in the skill textyour first editable draft **Prerequisites:** Node ≥ 18 (built-ins only — no native modules). Optional tools unlock specific commands: Whisper for `caption`, FFmpeg for `render`, ffprobe for
SkillMIT★ 886No key
Generate well architected monorepo libraries based on Effect and Nx monorepos. Based on design architectures like Repository, Infrastructure Domain Driven Design, Contract, Adapter, and Feature librar
in the readmegenerate data-access --contract order order mlg generate data-access --contract form --modules form-state,marketing/campaign,marketing/subscriber form mlg generate feature --modules cart,payment --data-access
Node.jsMIT★ 17No key
Local-first Canvas LMS MCP server. Stdio transport, ~125 lines of Python.
in the readmePyPI ]( , interactive states, WCAG accessibility, detached instances, naming quality
SkillMIT★ 53No key
ESP for AI Coding — Agent skills on the philosophy on software design, grounded in decades of engineering experience.
in the readmeUse `/clairvoyance:red-flags` to trigger a design smell scan, `/clairvoyance:deep-modules` to check interface depth and `/clairvoyance:design-it-twice` to compare alternatives before
Hosted by authorMIT★ 12No key
Claude Agent Skill that eliminates generic AI-generated design. Stop your AI shipping the same purple-gradient, Inter-font, three-feature-card website as everyone else.
in the skill textthe same purple-gradient website as everyone else.** Web and mobile. 20 modules.  , files, users, groups, enrollments, discussions, modules, pages, calendar, conversations, peer reviews, accounts, analytics, outcomes, grading standards, grade projection, link
Node.jsMIT★ 9No key
A Model Context Protocol server that validates and renders Mermaid diagrams.
in the readmemain application ├── src/ # TypeScript source code │ └── main.ts # Main application entry point ├── node_modules/ # Dependencies ├── package.json # Project dependencies and scripts ├── package-lock.json # Dependency lock file ├── tsconfig.json # TypeScript configuration
Node.jsMIT★ 57No key
Local, typed MCP server for controlling Autodesk Maya via commandPort
in the readmemodeling, shading, skinning, animation, curves, scripts, and viewport capture without importing Maya modules in the server process. This project is unofficial and is not affiliated with
PythonMIT★ 25No key
Agent Skill (html-prototype-build): generate, annotate, review & deliver native HTML prototypes for Claude Code, Cursor & Codex — real-DOM notes, AI-ready selectors, UI packs, multi-state screenshots.
in the skill textbrowse them, switch page states, and follow SVG connectors to the matching modules — same page, not a separate spec. Formal notes on the live page: browse
SkillMIT★ 22No key
An AI beat maker and music-production engine — an MCP server for Claude Code, a REST API and a browser DAW. Generate grooves, progressions and full arrangements from Python, and drive it from FL Studi
in the readmemixer, and export — no backend required. > **Status:** Pre-Release v8.0 — 100+ Python modules, 20/20 core tests passing, all systems operational. --- ## Features (What Works Today) ### Beat & Track
SkillMIT★ 9No key
Full-coverage MCP server for DaVinci Resolve: 334 tools for editing, media, color, Fusion, Fairlight, AI, rendering, and offline workflows.
in the readmeyour own agent). 334 tools — **316 live** tools across 22 domain modules that drive a running Resolve instance via its scripting API, plus **18 offline** tools
Node.jsMIT★ 4Few starsNo key
Senior Architect Agent: AI architecture skill for existing system mapping, software architecture documentation, Mermaid diagrams, and AI agent handoff.
in the skill textworkflow, หรือ boundary ที่ชัดเจน | 1-3 artifacts | | **Full** | Whole-system, handoff, 3+ modules interacting, persistence, security, integrations | Full output package | เริ่มที่ Scan เสมอ — เลื่อนขึ้นเมื่อ scope, evidence
SkillMIT★ 23No key
MCP server for Canvas LMS and Ed Discussion integration
in the readmecanvas_get_file_content` · `canvas_list_pages` · `canvas_get_page` · `canvas_list_modules` · `canvas_list_module_items` · `canvas_get_unit_outline_url` · `fetch_unit_outline` (USYD
SkillMIT★ 18No key
E2E encrypted AI agent platform — Python, native MCP, multi-agent delegation, live browser canvas, saved templates for govt appointments. Works on Claude, MiniMax, OpenAI, Ollama, or Claude CLI.
in the readmeplus** a native Flutter mobile app. ~225K LOC first-party · 440+ Python modules · ~280 builtin skills · 13 bundled MCP servers · 3,000+ tests · AES-256-GCM
PythonMIT★ 4Few starsNo key
Download videos and audio from the internet! Out of the box A2A Server and MCP Server
in the readmetool bloat in LLM contexts by grouping methods into optimized, togglable tool modules. - **Enterprise-Grade Security:** Complete support for Eunomia policies, OIDC token delegation, and granular
PythonMIT★ 4Few starsNo key
Open-source Codex skills for clean IM2 image generation, material realism, negative-prompt hygiene, and grounded scene mass.
in the skill textloss; - clean rendering and anti-artifact controls; - targeted negative-prompt hygiene. Conditional modules add structural mass for heavy scenes, evidence-preserving photo repair, and real-scene
SkillMIT★ 10No key
An AI skill pack for culture design, leadership, feedback, and high-talent teams, organized into reusable management modules.
SkillMIT★ 14No key
54-tool MCP server for multimodal automation the only open-source MCP with full PPTX/DOCX/PDF lifecycle, plus FFmpeg, GIMP, Inkscape, Blender, FreeCAD, MATLAB, Godot integration. 7 MCP services orches
in the readmeCode Copilot Agent. - **Custom layer**: `omni_mcp.py` implements 54 tools across 15 modules in a single Python file, covering office documents, image processing, video transcoding, 3D modeling
SkillMIT★ 9No key
🎬 AI Video Creator – Open-source video automation toolkit. Tell Claude Code what you want, get an MP4 back. No accounts, no API keys, fully local. Multilingual helper.
in the skill textgenerator tools to AI agents └── shared/ # brand config + TypeScript types shared across modules ``` --- ## ✨ Vision A single tool that lets non-technical creators: 1. **Generate** ready
SkillMIT★ 3Few starsNo key
GraalVM Native Image expert that adds native image support to Java applications, builds the project, analyzes build errors, applies fixes, and iterates until successful compilation using Oracle best p
in the skill textregisterPattern("logback-spring.xml"); hints.resources().registerPattern("org/springframework/boot/logging/logback/*.xml"); ``` 2. **Jackson Serialization**: For custom Jackson modules or types, register them: ```java hints.serialization().registerType(MyDto.class); hints.reflection().registerType
OfficialSkillMIT★ 40k in collectionNo key
Reference architecture for agentic AI chatbots with Strands Agents and Amazon Bedrock AgentCore
in the readmeinfra/environments/dev/terraform.tfvars # Edit terraform.tfvars with your settings # Deploy all ./infra/scripts/deploy.sh apply # Deploy specific modules ./infra/scripts/deploy.sh apply -target=module.chat ./infra/scripts/deploy.sh apply -target=module.runtime_orchestrator ``` See DEPLOYMENT.md fo
OfficialSkillMIT★ 195No key
An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询
in the readmemcp/antd-components-mcp extract [ant design repo path]` ## Architecture ```mermaid graph TD %% Main modules Server[MCP Server] --> Tools Server[MCP Server] --> Prompts %% Prompt modules subgraph Prompts[Prompt
Node.jsMIT★ 245No key
Build and deploy a full-stack RAG app on AWS with Terraform, using free tier Gemini Pro, real-time web search using Remote MCP server and Streamlit UI with token based authentication.
in the readmefor the environment │ ├── providers.tf # Terraform provider configurations │ └── variables.tf # Environment-specific variable definitions ├── modules/ # Reusable Terraform modules │ ├── api/ # API Gateway configuration │ ├── auth/ # Cognito authentication │ ├── compute/ # Lambda functions
SkillMIT★ 62No key
Evidence-based instructional design skills for Claude Code. 11 AI skills that check alignment, accessibility, cognitive load, and evidence strength. Import from any LMS or authoring tool.
in the skill textCanvas URL and access token. idstack: Connected. Pulling course data... Found: 12 modules, 8 assignments, 4 discussions, 6 outcomes. ## Import Quality Triage Found 4 flags during
SkillMIT★ 27No key
A recipe-driven WaaS platform for ComfyUI that turns complex workflows (Image, Audio, Video, 3D) into intuitive Gradio UIs, high-level semantic APIs, and MCP tools for LLMs & AI Agents.
in the readmerepository: **`comfy-webui-core`**. This version strips away all specific UI feature modules (such as ImageGen, VideoGen, etc.) and retains only the essential architecture skeleton: - The
SkillMIT★ 120No key
Free, open-source MCP server that gives AI coding agents (Claude Code, Codex, Cursor, OpenCode, ZCode…) design inspiration from award-winning websites — search with real screenshots, pull design DNA,
in the readmedirectory: ```bash npm install awwwards-mcp mkdir -p ~/.agents/skills && cp -r node_modules/awwwards-mcp/skills/awwwards-inspiration node_modules/awwwards-mcp/skills/awwwards-setup node_modules/awwwards-mcp/skills/awwwards-doctor node_modules/awwwards-mcp/skills/awwwards-motion-study ~/.agen
Node.jsMIT★ 105No key
MCP server giving AI agents (Claude, Cursor, Windsurf) full control over Rhinoceros 3D v8 — 105 tools for geometry, surfaces, booleans, Grasshopper, viewport capture, and script execution
in the readmestdio, JSON-RPC) v +---------------------------+ | GOLEM MCP Server | | Python 3.10+ | | FastMCP + 9 tool | | modules | +---------------------------+ | | TCP 127.0.0.1:9876 | Length-prefixed JSON v +---------------------------+ | Rhino Plugin | | Python 3.9 (embedded) | | TCP
PythonMIT★ 14No key
Evidence-aware Bilibili video research MCP for language, vision, and multimodal analysis.
in the readmeUsers\you\projects\Bilibili-Video-Research`. ```toml [mcp_servers.bilibili_video_research] command = " \\node_modules\\.bin\\tsx.cmd" args = [" \\src\\index.ts"] startup_timeout_sec = 120 tool_timeout_sec
SkillMIT★ 18No key
Universal AI agent skill that turns any material into learning-science-based self-study courses with retrieval practice, spaced repetition, and tutor mode.
in the skill textpractice before reading answers. ``` You get a course package with a syllabus, modules, lessons, hidden answer files, checkpoints, and a review schedule: ```text sql-for-analysts
SkillMIT★ 24No key
Connect Claude, Cursor, Codex & other AI assistants to Canvas LMS with your normal login — no access token needed. Read-only MCP server.
in the readmeburied. | | *"Download everything for Linear Algebra."* | Found 12 files spread across modules, announcements and assignment pages, saved 8 unique PDFs (questions *and* solutions) into `Canvas/MATH1012/…`, and
Node.jsMIT★ 4Few starsNo key
Production-ready Python 3.13+ CLI/API system with Adaptive RAG, multi-engine TTS, OpenRouter key rotation, FastAPI backend, and Next.js dashboard
in the readmeLEVEL=INFO ``` ## 🏗️ Architecture ### System Overview ``` youtube_chat_cli_main/ ├── services/ # 33 service modules │ ├── llm/ # LLM implementations │ ├── tts/ # TTS orchestrator & engines │ ├── rag/ # RAG engine │ ├── content/ # Content processing
PythonMIT★ 9No key
Who stands behind it
Who stands behind it