Agent Skills tools for MCP

MIT source for the reverse-engineer-anything skill - evidence-led native, managed, JavaScript/Electron, packaged, and browser investigations with explicit provider limits

by Jesse Vincent - A strong bundle of core competencies for software engineering, with good coverage of a large portion of the SDLC - from planning, reviewing, testing, debugging... Well written, well organized, and adaptable. The author refers to them as "superpowers", but many of them are just consolidating engineering best practices - which sometimes does feel like a superpower when working wit

by Affaan Mustafa - Top-notch, well-written resources covering "just about everything" from core engineering domains. What's nice about this "everything-" store is most of the resources have significant standalone value and unlike some all-encompassing frameworks, although you can opt in to the author's own specific workflow patterns if you choose, the individual resources offer exemplary patterns

by Anthropic - Anthropic's official repository for Agent Skills — the SKILL.md format, a skill template, and example skills, the same format Claude Code loads natively

Skill that makes coding agents behave like a "lazy senior dev": prefer built-in solutions, avoid new dependencies, and write the minimum code that works. Benchmarked on real Claude Code sessions with ~54% fewer lines, ~20% lower cost, and preserved safety guards — a rare harness-level incentive that fights over-engineering rather than just adding capability

Production-grade engineering skills for AI coding agents, packaged as 24 reusable skills covering the full development lifecycle from /spec to /ship. The slash-command interface and context-aware auto-activation make it a concrete reference for turning senior-engineering judgment into agent-executable harness artifacts

Multi-platform search CLI for 17 sites including Chinese platforms

Write videos as HTML and render them to MP4: launch films, explainers, captions, charts and 450+ ready-made blocks, by HeyGen

Installable library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, and more. The largest community-driven skill catalog with an npm installer and role-based bundles — a concrete reference for treating skills as versioned harness artifacts rather than ad-hoc prompts

17 directives blocking the most common LLM coding honesty failures: hallucinated APIs, invented signatures, false-confidence validation, manufactured-urgency capitulation, authority-driven softening, and self-referential comments. Drop the .mdc in .cursor/rules/

Arm Cloud Migration Assistant accelerates moving x86 workloads to Arm infrastructure. It scans the repository for architecture assumptions, portability issues, container base image and dependency incompatibilities, and recommends Arm-optimized changes. It can drive multi-arch container builds, validate performance, and guide optimization, enabling smooth cross-platform deployment directly inside G

753 cybersecurity skills across 38 domains: cloud security, pentesting, red teaming, DFIR, malware analysis, threat intel, and more (MITRE ATT&CK mapped)

Wraps 250+ SaaS APIs (GitHub, Slack, Linear, Notion, etc.) as agent-ready actions with managed OAuth, so tool integration becomes a one-line import rather than a custom harness component per service. The fastest path from "the agent needs to call an external API" to a production-grade, authenticated tool

Official skills catalog: .system, .curated, and .experimental skills. The authoritative upstream source

Healthcare administration specialist with 51 sub-agents covering revenue cycle, compliance, quality, clinical ops, health IT, and payer relations

by NVIDIA - Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks

Microsoft's skill optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits and validation-gated updates, producing deployable best_skill.md artifacts. The key harness insight is that skills should be treated as optimizable parameters that improve with execution feedback, not static prompt fragments written once and forgotten

Markdown-first research workflows for Claude Code and other agents, centered on autonomous literature review, experiments, paper iteration, and cross-model critique

Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector databases like Qdrant

(13.9k ⭐) - Personal memory for agents with fast retrieval, self-evolving skills, and lower context cost

(5.0k ⭐) - Skills and tools for investigating, building, testing, and documenting mods for PC games with Claude Code

(6.0k ⭐) - A library of Agent Skills designed to work with the Stitch MCP server

(2.6k ⭐) - SEO and GEO skills for Claude Code, with a Ryze MCP connector for Search Console, Analytics, ads, rankings, and backlinks

🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活

Composable indirect-prompt-injection research toolkit spanning 13 attacks, 16 channels (text and file), and 12 defenses/detectors via a decorator-based registry and unified craft() API, auto-logging prompts, event traces, transcripts, and verdicts for reproducibility

7 complementary skills for building production-ready n8n workflows. Covers 525+ nodes, 2,653+ templates. 3,400+ stars

(1.6k ⭐) - 48 free Claude marketing skills for Google Ads, Meta Ads, SEO, and AI visibility, plus Ryze MCP

(5.5k ⭐) - Claude skill for processing WeChat articles, web pages, YouTube videos, PDFs, Markdown, and search queries into NotebookLM-ready materials

On-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.

Identify and remove AI watermarks and provenance metadata (Gemini and Veo marks, SynthID, C2PA, EXIF) in images and video you generated yourself, plus provenance metadata in audio. Runs as uvx remove-ai-watermarks mcp

(1.1k ⭐) - A Claude Code toolkit with agents, skills, hooks, commands, rules, and MCP configurations for day-to-day development

The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.

(4.0k ⭐) - Extract a website's complete design system into design tokens, UI themes, component anatomy, and platform-specific code

An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的 AI 社交媒体智能体——发现热点趋势、创作内容、一键发布至各大平台，并学习分析哪些内容真正有效，覆盖小红书、抖音、知乎、哔哩哔哩等平台。

(3.8k ⭐) - Deep research skill for Claude Code and Codex that saves web findings in a persistent, searchable wiki

(919 ⭐) - Local FFmpeg Agent Skill for Claude Code, Cursor, and Codex with structured video and audio editing tools

Open-source Claude Code skills for SEO, GEO, Google Ads, and Meta Ads. Connects to live data via Google Ads MCP, Meta Ads MCP, Google Search Console MCP, and Google Analytics (GA4) MCP. Includes a /notfair:gemini cross-model review skill that runs Gemini as a second-opinion gate on ad campaigns, SEO metadata, and schema markup. MIT, ~2.9k stars

(1.9k ⭐) - Agent skills that turn top-grossing app patterns into native-quality mobile screens

A Python library for building AI agents that leverage the full power of Google Antigravity.

(3,555 ⭐) - Reverse-engineering skill that guides agents through native binaries, Electron apps, Android packages, and firmware with standard command-line tools

Official AWS-supported MCP servers, skills, and plugins that let AI agents provision, query, and manage AWS resources through a standardized protocol interface. Worth including as the reference for how a major cloud provider productizes infrastructure access into agent-ready harness primitives rather than leaving teams to hand-roll IAM-scoped tool definitions

Resumable long-running task workflow and Skill platform for coding that turns skill creation, evaluation, and release into a single lifecycle with Rubric, Pass@k, and Pass^k scoring. The Native/Classic dual-workflow model is a concrete reference for matching harness constraint strength to model capability rather than using one loop for every task

Deploy and manage Workers, KV, R2, D1, Vectorize, Queues, Workflows

Qwen's official multimodal plugin suite packages vision, video, document, 3D, and CAD capabilities as portable skills and MCP servers across Claude Code, Codex, OpenCode, and other harnesses. It shows how to make a text-first coding harness multimodal-native without rebuilding the agent loop

Standardized framework for defining, versioning, and distributing agent skills. Enables skill reuse across Claude Code, Copilot, VS Code, Gemini, and other platforms — a harness-level abstraction that makes skills first-class deployment artifacts rather than ad-hoc tool definitions

nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.

(2.4k ⭐) - 270+ Claude Code plugins with 739 agent skills

Korean document (HWP/HWPX/PDF) to Markdown conversion, form filling, and HWPX generation Skill

CLI to sync skills across 55+ AI CLI tools from a single source. Security-audited Go binary

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

(2.3k ⭐) - A Claude Code marketplace with plugins, agents, skills, commands, hooks, rules, templates, and MCP configurations

⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣！超级智能体派对 = 自托管neuro sama + openclaw!

(2.0k ⭐) - MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync

Company-department skills (legal, finance, security, ops and more) for Claude Code and ChatGPT, each installable on its own and citing the standards or regulators it relies on

(2.1k ⭐) - Production-grade web scraping and automation skills for AI coding agents

Provider-neutral Agent Skill for designing, auditing, and refactoring agentic harnesses across domains. Distills the full runtime discipline — loop budgets, typed tools, permission gates, compaction-aware memory, prompt-caching layout, and launch checklists — into an interactive reference that works for Codex, Claude Code, and any agent needing rigorous scaffolding

Codex computer use, decoupled from the app, for usage inside any harness.

Portable .agent/ folder that externalizes memory, skills, and protocols from any specific coding agent into a cross-tool harness layer. Adapters translate the same configuration into Claude Code's CLAUDE.md, Cursor's rules, OpenCode's AGENTS.md, and more — the first practical answer to harness vendor lock-in at the configuration level

30+ App Store Optimization skills for keyword research, metadata optimization, competitor analysis, creative optimization, and mobile growth strategies via Appeeky API

(2.1k ⭐) - Skills for MCP development, model inference and training, research, and security, with AI Gateway setup for request logs and token tracking

Turn meetings into live agent loops. Record, transcribe, and analyze meetings with real-time AI intelligence — before, during, and after calls.

Best practices for building Stripe integrations

Spots new AI model, product and repo names on X, Hugging Face, GitHub and sitemaps, then ranks the search terms behind them by Google Ads volume and DataForSEO Trends (an estimate of Google search interest). Three skills and an MCP server; needs an AIsa API key, and an optional GoAnyAPI key adds Google Trends related queries and country-level trend series

(1,478 ⭐) - Blender skills for modeling, technical art, scene production, and game-engine export through Blender MCP

(1.2k ⭐) - Microsoft agent plugin with skills and MCP server configurations for Azure development scenarios

Open-source (MIT) library of 1,153 Agent Skills as plain-markdown SKILL.md files, covering PRDs, incident postmortems, code review checklists, RFCs, and 35 professions. Installs into Claude Code, Cursor, Windsurf, Zed and 10 more tools with one command, ships an MCP server, and runs free in a browser playground. Install: npx pm-claude-skills add

by klaudworks - Enables users to prompt codex from claude code. Unlike the raw codex mcp server, this skill infers parameters such as model, reasoning effort, sandboxing from your prompt or asks you to specify them. It also simplifies continuing prior codex sessions so that codex can continue with the prior context

(1.4k ⭐) - Skill, MCP server, and CLI for finding and retrieving icons from a large collection of icon libraries

Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.

AI-assisted PCB design for KiCAD 10. Native KiCAD plugin — a single Rust binary exposing 217 schematic, layout, routing, placement, design-review, and manufacturing tools to Claude, or the LLM of your choosing

(1.1k ⭐) - iOS Simulator skill for Claude Code that helps agents build, run, and interact with apps while preserving token context

(632 ⭐) - Skills and MCP systems for using Microsoft Fabric from CLI, VS Code, Claude, and related agent workflows

The Simulink Agentic Toolkit gives your AI agent both the tools and the expertise to work effectively with Simulink and Model-Based Design.

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

14 skills for ingesting Chinese content (Douyin, Bilibili, Xiaohongshu, WeChat, X/Twitter, podcasts) into a personal knowledge base — auto image/video routing, subtitle-first transcription, RSS/YouTube subscription scheduling, and a knowledge-base MCP server

Source for the competitor-ad-intelligence and ad-campaign-analyzer skills - evidence-labeled public ad research plus uncertainty-aware campaign diagnostics and bounded budget tests (MIT)

Security audit platform for AI agent skills and MCP servers. Five-tier detection pipeline (core rules, dynamic rules, LLM analysis, Firecracker sandbox, LLM review), continuous rule evolution, and automated vulnerability reports

Local-first runtime firewall for AI coding agents: intercepts shell, secrets, MCP config changes, and package installs before execution

Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.

Source-available (FSL-1.1-ALv2) QA agent for natural-language web and mobile tests. Run agent-qa mcp for authoring, execution, artifacts, and failure triage; dashboard-backed tools need a running dashboard and dashboardUrl. Model and infrastructure costs are separate

AI agents, integrations, maker tools, and other production-grade skill packs

CLI that turns agent skill verification into repeatable unit tests: it generates task and grader pairs from a SKILL.md, runs multi-trial evals against Claude, Codex, Gemini, or OpenCode, and reports pass rates with a CI-ready threshold. Fills the gap between shipping a skill and knowing an agent actually discovers and invokes it correctly

Local-first RAG knowledge vault and MCP server. Compiles raw sources (books, notes, transcripts, exports, datasets, slide decks, files, URLs, code) into a durable markdown wiki with a knowledge graph and a hybrid SQLite FTS plus embeddings index. The bundled MCP server (npx -y @swarmvaultai/cli mcp) gives Claude Code, Codex, OpenCode, and any MCP client page search, page reads, source listing, que

Comprehensive framework for creating, evaluating, and sharing agent skills with 86-task benchmark across 11 domains. Demonstrates the harness problem of skill fragmentation and provides infrastructure for standardized skill evaluation across frameworks

Scrape, crawl, search, and map the web via CLI

企业级 AI 智能体 Agent 平台，覆盖智能对话、文档知识问答、联网搜索、RAG 检索、MCP 工具协议、Skills 扩展等完整能力。三层执行器体系、双通道混合检索、组合式切块引擎、会话记忆管理、全链路可观测，每个环节都经过深 度设计和工程化打磨。

Public-data MCP and KOL pricing Skills for Codex, Claude Code, Cursor, and other agents

(502 ⭐) - Plugin suite and bundled MCP servers for delivery workflows, codebase audits, documentation, performance optimization, and remote SSH work

55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.

Build and review interfaces with Better Design design systems

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

一次构建视频模板，多次复用：给 Claude Code、Codex 等 25+ 个 Agent 的开源可编辑婚礼视频模板与 Agent Skill。Build a video template once, reuse it across coding agents.

371 tax classification skills across 134 countries. Classify bank statement transactions into VAT/GST, income tax, and social contribution categories with conservative defaults

Official plugin distribution for the hosted Zapier MCP server. Connects Claude to thousands of apps — send messages, pull data, trigger workflows

Skills distribution via CLI or MCP

by sanderbz - A nice package of Claude Skills focused on SEO workflows: page audits, content briefs, article writing, E-E-A-T audits, semantic gap analysis, and more. Each skill fetches the target page and reads the top-ranking competitors itself, so users don't paste in keyword exports or crawl reports

Academic Paper Search：中文科研用户的 Codex / Claude Code / DeepSeek Harness Skill + MCP；跨 CrossRef、PubMed、arXiv、OpenAlex、Europe PMC 检索去重，支持 MeSH、引用核验、引文图谱、试验检索与审计导出。

Official Email Marketing Bible source for the email-marketing-bible skill - data-backed email marketing for agents: automation flows, deliverability triage, copy de-slopping, AI email design, compliance and 19 industry playbooks, with ESP control via MCP behind explicit send-approval gates (MIT)

Official source for the video-router skill - choose and lock generation, deterministic composition, supplied-footage editing, or an automatic cross-modal production plan (MIT)

Open-source BYOK AI agent for Android. Full phone control, native Shell & Python 3, with Skills and MCP support. Built with Material 3 Expressive. Works via Shizuku (root optional). Bring any provider: OpenRouter, Ollma, and more.