Découvrez les skills testing security llm ai, comparez leurs dépôts et consultez leurs instructions.
record context that would help in future sessions. use after learning something, discovering a gotcha, or making a decision worth preserving. test: would a future agent starting fresh benefit from knowing this?
Master coordinator for all creative skills. Use this skill to orchestrate asset generation, manage workflows, and automate creative production. Integrates with nanobanana pro automation system.
Create presenter and UGC-style video content. Use when creating educational videos, testimonials, product demos, or personal brand content.
Research visual direction and develop your creative style. Use when establishing brand aesthetics, finding your visual identity, or planning creative direction for your assets. Integrates with Image Generation...
Generate images using FAL.ai nanobanana pro. Use when creating product shots, social graphics, brand assets, or any visual content. Integrates with automation system for direct asset generation in Claude Code.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
Local LLM operations with Ollama on Apple Silicon, including setup, model pulls, chat launchers, benchmarks, and diagnostics.
LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications
Use multiple Claude agents to investigate and fix independent problems concurrently
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui)
Vercel AI platform guidance covering AI SDK, AI Gateway, Vercel Agent, and MCP. Use when building AI-powered or agentic workloads on Vercel.
AI session compression techniques for managing multi-turn conversations efficiently through summarization, embedding-based retrieval, and intelligent context management.
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers
LangGraph framework for building stateful, multi-agent AI applications with cyclical workflows, human-in-the-loop patterns, and persistent checkpointing.
Official Anthropic SDK for Claude AI with chat, streaming, function calling, and vision capabilities
OpenRouter unified AI API - Access 200+ LLMs through single interface with intelligent routing, streaming, cost optimization, and model fallbacks
DigitalOcean Gradient AI agentic cloud and AI platform for building, training, and deploying AI agents on GPU infrastructure with foundation models, knowledge bases, and agent routes. Use when planning or opera...
Collaborative document writing with structured workflow. Activates for "write document", "draft proposal", "create spec", "documentation", "co-author", "help me write", "RFC", "design doc".
Activates extended reasoning for complex problems. Use when asked to "think harder", "ultrathink", "think deeply", "analyze thoroughly", or when facing architecture decisions, complex debugging, system design,...
Build high-quality MCP servers that enable LLMs to interact with external services. Activates for "MCP server", "MCP tool", "build MCP", "create server", "Model Context Protocol".
Create new Claude Code skills with proper structure and best practices. Activates for "create skill", "new skill", "build skill", "skill template", "SKILL.md".
External API integration patterns for REST, GraphQL, webhooks. Activates for "integrate API", "call API", "webhook", "REST", "GraphQL", "fetch", "axios", "HTTP" requests.
Autonomous p5.js visualization agent. It implements, inspects, critiques design/UX, fixes, and launches the result.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.