A comprehensive security auditing skill for Cairo/StarkNet smart contracts. It systematically scans for 6 critical vulnerability patterns including arithmetic overflow, L1-L2 messaging issues, signature replay attacks, and unchecked access control, providing detailed remediation guidance and integration with the Caracal static analyzer.

This skill helps developers prepare their codebase for professional security audits using Trail of Bits' checklist methodology. It runs static analysis tools appropriate to your platform (Solidity, Rust, Go), analyzes test coverage, identifies dead code, and generates comprehensive documentation including flowcharts, user stories, and glossaries.

A security auditing skill for Algorand blockchain smart contracts. It guides users through scanning TEAL and PyTeal code for 11 critical vulnerability patterns including rekeying attacks, unchecked transaction fees, and access control issues, with detailed detection patterns and mitigation strategies.

This skill enables deep, line-by-line code analysis for security audits and architecture reviews. It provides structured frameworks including First Principles, 5 Whys, and 5 Hows methodologies to build comprehensive understanding of codebases before vulnerability hunting. The skill focuses purely on context building and explicitly excludes vulnerability findings or exploit reasoning.

This skill helps ensure requirements are properly understood before implementation begins. It provides a structured workflow for identifying when requests are underspecified, asking targeted clarifying questions (1-5 at a time), and confirming interpretation before proceeding with work. Useful for avoiding wasted effort on misunderstood requirements.

Humanizer-zh is a Chinese-language skill for editing and improving AI-generated text to make it sound more natural and human-written. It identifies 24 common AI writing patterns across content, language, style, and communication categories, then provides guidance for rewriting text to remove these patterns while maintaining the core message.

MCP Agent Mail enables multiple AI coding agents to coordinate asynchronously through a mail-like system. It provides inbox/outbox messaging, file reservations to prevent conflicts, and contact management, with all communications stored in Git for human auditability.

Claudeception enables Claude Code to build persistent knowledge by extracting reusable skills from debugging sessions and problem-solving. When you discover a non-obvious solution, workaround, or debugging technique, it captures that knowledge as a new skill that can be automatically retrieved in future sessions facing similar problems.

This skill provides AI assistants with deep knowledge about the Addax open-source ETL tool. It covers the project's architecture, plugin system for 20+ data sources (MySQL, PostgreSQL, MongoDB, Kafka, HDFS, etc.), job configuration format, data transformation capabilities, and development guidelines for building custom reader/writer plugins.

This skill enables Claude to give spoken voice updates to the user using text-to-speech. It's triggered by Stop hooks or explicit user requests to provide audio summaries of completed tasks in a conversational tone.

A comprehensive reference guide for the Langroid multi-agent LLM framework. Provides design patterns and code examples for agent configuration, stateful tool handlers, task control with done_sequences, batch processing, MCP tool integration, and quiet mode output control.

A documentation helper that records and organizes design patterns for the Langroid multi-agent framework. When you learn a new pattern, this skill guides you to add a description to the patterns catalog and create detailed reference documentation with code examples.

This skill provides instructions for using the tmux-cli command to communicate with other CLI agents or scripts running in different tmux panes. It enables executing commands in specific panes with exit code detection, useful for multi-step automation and agent coordination. Requires separate installation of the claude-code-tools package.

Stripe's official AI integration toolkit that enables AI agents to interact with Stripe APIs for payments, subscriptions, and billing. Supports popular frameworks like LangChain, Vercel AI SDK, and CrewAI, and includes utilities for metering LLM token usage through Stripe's billing infrastructure.

This skill sets up Geoffrey Huntley's 'Ralph Wiggum' autonomous coding technique - a bash loop that feeds prompts to Claude CLI for automated code generation. It supports planning mode (gap analysis) and building mode (implementation), with Docker isolation as an option for safer execution.

This skill guides the creation of Model Context Protocol (MCP) servers that extend Claude's capabilities. It supports both Python and TypeScript implementations with patterns for API integration, OAuth authentication, and response optimization. The skill handles the full workflow from project setup to installation in Claude Code and Claude Desktop.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Beads Viewer (bv) is a sophisticated terminal UI application for exploring and analyzing issues tracked in the Beads issue tracking system. It provides graph theory-based insights like PageRank and critical path analysis, and includes robot mode flags specifically designed for AI coding agent integration.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Execute Hugging Face Hub operations using the hf CLI. Download models and datasets, upload files to Hub repositories, create repos, manage local cache, and run compute jobs on HF infrastructure. Supports authentication, file transfers, and cloud compute management.

A comprehensive reference guide for working with textures in Three.js. Covers texture loading, configuration options, UV mapping, cube textures, HDR environments, render targets, and performance optimization. Ideal for developers building 3D web applications who need quick access to texture-related patterns and best practices.

A comprehensive reference guide for Three.js shader programming. Covers ShaderMaterial and RawShaderMaterial usage, uniform types, varyings, common shader patterns like fresnel effects, noise, gradients, and rim lighting, plus performance optimization tips.

A comprehensive reference guide for Three.js post-processing effects. Covers EffectComposer setup, common effects like bloom, depth of field, anti-aliasing, and ambient occlusion, plus custom shader development and performance optimization tips.

A comprehensive Three.js materials reference guide covering all material types (Basic, Lambert, Phong, Standard, Physical, Toon, Shader), their properties, and usage patterns. Includes code examples for glass, car paint, environment maps, and custom GLSL shaders.

A reference skill for Three.js developers that provides comprehensive documentation on loading 3D models (GLTF, FBX, OBJ), textures (including HDR/EXR), and managing loading progress. Includes examples for async loading patterns, caching strategies, and error handling.

A comprehensive Three.js lighting reference covering all light types (AmbientLight, HemisphereLight, DirectionalLight, PointLight, SpotLight, RectAreaLight), shadow setup and optimization, image-based lighting with HDR environments, and common lighting patterns like three-point and studio setups.

A reference guide for implementing user interactions in Three.js 3D applications. Covers raycasting for click detection, various camera controls (Orbit, Fly, FirstPerson, PointerLock), drag controls, selection systems, keyboard input handling, and coordinate conversions between world and screen space.

A comprehensive reference guide for Three.js geometry creation. Covers built-in shapes (box, sphere, cylinder, etc.), custom BufferGeometry with typed arrays, InstancedMesh for efficient rendering of many objects, and geometry utilities for merging and optimization.

A comprehensive reference guide for Three.js fundamentals including scene setup, camera types (Perspective, Orthographic, Cube, Array), WebGL renderer configuration, Object3D hierarchy, and essential math utilities. Provides ready-to-use code snippets for common 3D graphics tasks like animation loops, responsive canvas handling, and proper resource cleanup.

A comprehensive reference guide for Three.js animation systems including keyframe animations, skeletal animation, morph targets, and animation blending. Provides code examples and best practices for creating smooth 3D animations in web applications.