Write and run custom Playwright browser automation on demand
Project overview
This skill lets Claude create and execute Playwright automation for page tests, multi-step flows, and browser validation instead of relying on fixed scripts. The browser is visible by default, common interactions have helpers, and a universal executor handles module resolution; it can be installed as a Claude Code plugin or standalone skill.
Distill books, long videos, and podcasts into callable, testable agent skills.
Project overview
Cangjie Skill turns books, courses, long videos, podcasts, interviews, and other transcripts with reusable methods into modular agent skill packages rather than ordinary summaries. Its workflow maps the source, extracts frameworks, principles, examples, counterexamples, and terminology in parallel, filters weak candidates, and stress-tests the remaining skills. Deliverables can include an overview, skill index, reader digest, glossary, individual SKILL.md modules, and test prompts, making it best suited to structured reuse instead of simple content compression.
Browse more than 23,000 agent skills for empirical social-science research.
Project overview
Auto-Empirical Research Skills curates more than 23,000 reusable skills across eight social-science disciplines, giving researchers and agents a large catalog of empirical methods and workflows. The repository also includes numeric benchmark tasks and behavioral evaluation scenarios intended to test reproducibility and methodological rigor.
Build stateful agents with memory, identity, and long-term learning
Project overview
Letta Code is a stateful agent harness built around persistent memory, identity, and experience over time. Agents can revise their own memory, skills, and prompts as they learn, while remaining accessible through a CLI, desktop app, browser, or messaging channels. Message search, subagents, and schedules support work that continues across sessions.
Manage parallel coding-agent sessions from a terminal dashboard or mobile browser.
Project overview
Agent of Empires runs multiple coding agents in isolated Git worktrees, with optional Docker sandboxes and tmux-backed sessions that survive terminal closure. Its TUI and web dashboard show which agents are active, blocked, or waiting for input, while exposing terminals and diffs from a laptop, phone, or tablet. It is designed for Linux and macOS.
Scan local agents, MCP servers, and skills for security risks.
Project overview
Snyk Agent Scan finds MCP configurations and Agent Skills used by tools such as Claude, Cursor, Windsurf, and Gemini CLI, then checks for prompt injection, tool poisoning, tool shadowing, malicious payloads, unsafe credential handling, and hardcoded secrets. It runs directly through uvx. Scanning a stdio MCP server executes its configured command, so review the command and approve it only through the consent prompt.
Run a persistent personal agent with sandboxed tools, memory, and multiple channels.
Project overview
Moltis is a self-hosted personal-agent server written in Rust that connects to multiple model providers and stays available through the web, Telegram, Signal, Discord, Teams, and voice. Tool execution can be isolated with Docker, Apple Container, or WASM, while memory, MCP, scheduling, authentication, and an encrypted vault are built in. Release installs run as a single Rust binary on hardware you control.
Collection or directorySecurity and privacyClaude Code
ctf-skills
@ljagiello·Python
Give Agent Skills-compatible coding agents reusable workflows for diverse CTF challenges.
Project overview
Use this collection to give Agent Skills-compatible coding agents structured workflows for web exploitation, pwn, cryptography, reverse engineering, forensics, OSINT, and other CTF categories. You can install the whole library or work by category, with a bundled setup script for preinstalling and verifying common challenge tools.
Guide AI coding agents through Vue 3 patterns, testing, routing, and debugging.
Project overview
Add focused skills for Vue 3 Composition API and Options API work, Vue Router, Pinia, component and end-to-end testing, JSX, debugging, and adaptable composables. You can install the bundle or selected skills, and explicitly asking the agent to use a Vue skill improves activation reliability; the maintainer labels the project an early community experiment whose guidance may be incomplete or inaccurate.
Load specialized Claude skills for authorized offensive security testing.
Project overview
claude-red is a library of on-demand SKILL.md files for web, identity, wireless, cloud, mobile, exploit development, red-team infrastructure, and other attack surfaces. Each skill supplies focused methodology, tooling, edge cases, and escalation paths without loading the entire library into context. It is intended for penetration testers and researchers working on systems they are explicitly authorized to assess.
Collection or directoryFinance, legal and complianceClaude Code
Awesome-finance-skills
@RKiding·Python
Add reusable financial analysis skills to your AI agent.
Project overview
Use this collection to equip coding and general-purpose agents with workflows for financial news, stock data, sentiment analysis, forecasting, signal tracking, visualization, and report generation. Individual skills can be installed with npx or copied into supported agent directories for Claude Code, Codex, OpenCode, and related tools. It is a modular skill pack rather than a standalone investment research application.
Combines AI coding CLIs into reusable, parallel, and long-running workflows.
Project overview
CodeMachine is an orchestration layer for AI coding CLIs such as Claude Code, Codex, and Cursor. Define a workflow once and it handles step execution, context passing, and agent coordination. Workflows can range from interactive to fully autonomous, divide work among multiple agents, run tasks in parallel, and persist for hours or days. The underlying coding CLIs must be available separately.
Collection or directoryCode review and qualityClaude Code
web-quality-skills
@addyosmani·Shell
Audit web performance, accessibility, SEO, and Core Web Vitals with an AI agent.
Project overview
Use an AI coding agent to review and improve web projects against Lighthouse guidance, Core Web Vitals patterns, WCAG 2.2 accessibility practices, SEO requirements, and modern browser standards. The skills work across major frameworks or plain HTML and can be invoked by topic, but this is an unofficial collection intended as structured engineering guidance rather than an official certification tool.
Install reusable agent skills for coding, research, content, and workflow tasks.
Project overview
davidondrej-skills is a categorized library of reusable workflows for AI coding, research, and general workflow agents. Each skill lives in its own folder with a SKILL.md entry point that explains when and how it should be used. The collection covers areas such as codebase improvement, idea research, content preparation, presentation review, transcript work, skill authoring, and agent orchestration.
Collection or directorySoftware developmentClaude Code
skills
@NVIDIA·Python
Install NVIDIA-verified agent skills for CUDA-X, AI Blueprints, and platform tools.
Project overview
NVIDIA Agent Skills is an official catalog of portable guidance for NVIDIA software, installable selectively through the skills CLI for clients such as Claude Code, Codex, and Cursor. Entries are mirrored from product repositories and must include signatures, governance cards, evaluation data, and benchmark reports, giving developers a traceable way to add NVIDIA-specific workflows to their agents.
Run a local personal AI with persistent memory and a peer-to-peer skill economy.
Project overview
Bitterbot is a local-first personal AI system with a browser control interface for chat, sessions, memory, skills, and scheduled work. Its dream engine periodically reorganizes stored knowledge, while optional integrations connect messaging channels, a peer-to-peer skills network, and an agent wallet using Base and USDC. Setup is substantial: it requires Node 22, pnpm, several local dependencies, and onboarding for model authentication, embeddings, search, channels, and optional wallet features, making it best suited to users comfortable maintaining an experimental agent environment.
Sync, audit, and share skills across dozens of AI CLI tools from one source.
Project overview
skillshare keeps skills, custom agents, rules, commands, prompts, and other file-based resources in one local source and syncs them to Claude, Codex, Cursor, OpenClaw, and more than 60 targets. It installs from common Git hosts, supports team and project repositories, and audits content for prompt injection and data-exfiltration risks before use, without a registry or telemetry.
Coordinate multiple local skills to complete composite agent tasks.
Project overview
VibeSkills is a workflow runtime that takes one request, turns it into bounded stages, and binds the relevant locally installed skills for planning, implementation, testing, documentation, research, or review. It records verification evidence and preserves workspace context for later sessions. The runtime is invoked through the host application's Skills entrypoint rather than as a standalone CLI.