Explore Security-Reviewed AI Skills

Manage multiple local CLI agents via tmux sessions.

Debug systematically, not randomly. Find and fix bugs methodically.

Expert browser automation for cleaning scraping and reliable testing.

Comprehensive UI/UX design intelligence skill for AI coding assistants. Injects structured design tokens, color theory, typography scales, accessibility guidelines, and component patterns into Claude Code, Cursor, and Windsurf.

Framework for testing and evaluating AI agent performance.

Persistent memory system for agents using MCP.

Design patterns for building complex memory architectures.

Rapidly build tools for agents to use.

Community skill with design patterns for agents that plan and act on their own: ReAct, plan-execute, reflection, guardrails, cost control and durable execution, with a long list of failure modes.

Control your computer like a human using AI.

Orchestrate teams of parallel workers.

Build voice-enabled conversational AI.

Expert in the CrewAI agent framework.

Build cyclic agent graphs with LangGraph.

Community skill that makes an agent work test-first: one failing behavioural test, minimal code to pass, then refactor, with a separate guide on mock anti-patterns.

A one-file Clean Code playbook (Robert C. Martin's rules on naming, functions, comments, errors, tests and classes) that AI coding agents follow when writing, reviewing or refactoring code.

Community skill that gives an agent a simplicity-first method for architecture decisions: ask context questions, pick patterns with decision trees, and record the choice as an ADR.

Modern React hooks and patterns.

Advanced types and safety.

Enterprise Node.js applications.

App Router and RSC optimization.

Writing idiomatic Python.

Core JS engine and modern APIs.

Schema design and query optimization.

Web app security testing with Burp.

Detect and prevent SQL injection.

Cross-site scripting protection.

Fixing authentication vulnerabilities.

Community skill that gives an agent a command reference for the Metasploit penetration-testing framework. It is an offensive-security skill: the upstream file is marked risk: offensive and meant for authorised assessments and lab use only.

AWS/GCP/Azure security audits.

Advanced adversary emulation.

Community skill that teaches an agent to analyse a project for vulnerabilities (OWASP Top 10:2025, supply chain, attack surface, risk ranking) and ships a Python script that scans a folder.

Network forensics with Wireshark.

Creative ideation and design thinking.

Detailed implementation blueprints.

No-code and code-based automation.

Continuous improvement of tasks.

Parallel tasking with isolated working dirs.

Checkpoints for task completion.

Collaborative writing with AI.

Refining and polishing text.

Social media and blog content.

High-conversion sales copy.

Corporate announcements and reports.

Schema normalization and optimization.

PostgreSQL performance and features.

Edge-ready Postgres databases.

MongoDB, Redis, and Key-Value stores.

Go-to-market plans for new products.

Instruction-only skill for deciding whether to build SEO pages at scale from templates and data, and for designing the page system if the answer is yes. It scores feasibility first and says to stop below 50.

Community skill with a long reference guide for planning and tuning paid campaigns on Google, Meta, LinkedIn, X and TikTok; it is advice text, it does not connect to any ad account.

Launch lean software products.

Monetization and business models.

Containerization and orchestration.

Community skill with patterns and a list of known pitfalls for deploying Next.js apps to Vercel: environment variables, edge vs serverless, previews, domains and caching.

Realtime DB and Auth.

Building with Lambda and DynamoDB.

CI/CD pipeline automation.

Anthropic's official algorithmic-art skill: a written algorithmic philosophy, then a self-contained p5.js viewer with seeded randomness, parameter sliders and seed navigation.

Anthropic's official canvas-design skill: turns a poster or art request into a written design philosophy, then a one-page PNG or PDF, with 29 bundled font families.

Remotion's official agent skills: a router SKILL.md plus 11 bundled guides for building, previewing and rendering videos in React with Remotion.

Mobile-first design rules for iOS and Android apps (React Native, Flutter, native) from vudovn's AG Kit: touch targets, platform conventions, performance, plus a read-only audit script.

Core loops and mechanics.

Create Model Context Protocol servers.

Tools for creating new AI skills.

Syntax and validation for skill files.

A large open-source toolkit of agent definitions, slash commands, rules, hooks and skills for coding agents. Built for Claude Code; it also has a native Antigravity installer that copies rules, workflows, skills and agents into .agents/.

Open-source context database designed specifically for AI Agents (OpenClaw). Unifies memory, resources, and skills management through a file system paradigm.

AI memory OS for LLM and Agent systems, enabling persistent Skill memory for cross-task skill reuse and evolution.

Byterover Cipher - an open-source memory layer specifically designed for coding agents. Compatible with Cursor, Claude Code, and more through MCP.

Memory for 24/7 proactive agents like OpenClaw (moltbot, clawdbot).

An open-source AI agent that brings the power of Gemini directly into your terminal.

Up-to-date code documentation platform for LLMs and AI code editors.

Chrome DevTools for coding agents.

GitHub's own MCP server: lets an agent read repositories and manage issues, pull requests, Actions runs and security alerts through your GitHub account, as a hosted remote server or a local Docker image.

An autonomous agent that conducts deep research on any data using any LLM providers.

Open-source multimodal AI agent stack connecting models and agent infrastructure.

Agent orchestration platform for Claude with multi-agent swarms and autonomous workflows.

Workflow automation platform with native AI capabilities and broad integration support.

Community skill that gives an agent a measure-first workflow for slow apps: baseline, find the bottleneck, fix one anti-pattern, re-measure, and guard with a budget.

DDD tactical patterns and bounded contexts.

Securing REST and GraphQL APIs.

Security incident handling.

Community skill with a short procedure for handling CI/CD secrets safely: Vault, cloud secret managers, GitHub Actions, workload identity and rotation.

AI-powered meeting summarization.

OpenAPI and doc generation.

Community skill that gives an agent a framework for content planning: pillars and topic clusters, searchable vs shareable content, keyword research by buyer stage and a weighted scoring sheet for ideas.

Infrastructure as Code.

Istio and traffic management.

Anthropic's official frontend-design skill: guidance for distinctive, intentional UI design, typography and copy that avoids templated AI defaults.

Automated design audits.

Unofficial Python MCP server by Andrew Lo (alohc) that lets an AI assistant generate, animate and extend short Google Veo video clips with your Gemini API key and save them as local MP4 files.

Neural web search and code context.

Community skill that fetches a YouTube video's caption transcript with the youtube-transcript-api Python library and has the agent write a long, structured summary.

Unofficial MCP server by Eric Pheterson that lets AI assistants search Apple Music, edit your library and playlists, and control playback through Music.app, Safari, Chrome or the Apple Music API.

Cloudflare's official wrangler skill: tells an AI agent how to deploy, configure and debug existing Wrangler-based Workers projects using current Cloudflare docs.

Snyk's container-security skill: scan Docker images for OS and app vulnerabilities via the Snyk MCP server and fix Dockerfiles.

Anthropic's data-visualization skill: pick the right chart and write clean, accessible Python charts with matplotlib, seaborn and plotly.

DigitalOcean's open-source MCP server: manage Droplets, App Platform, databases, DNS, Kubernetes and more from an AI agent.

Official DuckDB skills: query files and databases with the duckdb CLI, read CSV/Parquet/JSON, search DuckDB docs and install extensions.