Découvrez les skills testing security llm ai, comparez leurs dépôts et consultez leurs instructions.
Orchestrates multi-agent AI systems with task delegation, agent communication, shared memory, and workflow coordination. Use when users request "multi-agent system", "agent orchestration", "AI agents", "agent c...
Compares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and fix suggestions. Use for "prompt testing", "A/B testing prompts", "prompt versioning", or "quality re...
Designs multi-step agent workflows with tool usage, retry logic, state management, and budget controls. Provides orchestration diagrams, tool execution order, fallback strategies, and cost limits. Use for "AI a...
Diagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Provides root cause classification, prompt fixes, tool improvements, and new test cases. Use f...
Builds Model Context Protocol (MCP) servers for Claude with tools, resources, and prompts. Use when users request "create MCP server", "build Claude tool", "MCP integration", or "custom Claude tools".
Sets up vector databases for semantic search including Pinecone, Chroma, pgvector, and Qdrant with embedding generation and similarity search. Use when users request "vector database", "semantic search", "embed...
Recursive Language Model for processing large contexts (>50KB). Use for complex analysis tasks where token efficiency matters. Achieves 40% token savings by letting the LLM programmatically explore context via...
Share the current Claude Code session to claudereview.com for code review. Use this when the user wants to share their session, get a link to the conversation, or create a shareable review of the work done.
Route AI/ML tasks to correct Yzmir pack - frameworks, training, RL, LLMs, architectures, production
Router skill directing to deployment, optimization, MLOps, and monitoring guides.
Routes to appropriate PyTorch specialist skill based on symptoms and problem type
Routes to appropriate deep-RL skills based on problem type and algorithm family
LLM specialist router to prompt engineering, fine-tuning, RAG, evaluation, and safety skills.
Routes to appropriate Python specialist skill based on symptoms and problem type
Customize the retail agent for different use cases. Use when adapting for different business types, industries, or output formats, or when modifying prompts, adding verticals, or changing the analysis focus.
Learn ADK concepts and understand the retail agent pipeline. Use when asking how the agent works, what ADK is, wanting to understand the architecture, state flow, or individual agent purposes.
Guide for creating custom ADK tools. Use when adding new function tools, working with ToolContext, saving artifacts, or integrating external APIs into the agent pipeline.
Guide for adding new agents to the ADK pipeline. Use when creating a new LlmAgent, SequentialAgent, or ParallelAgent, or when extending the pipeline with additional processing stages.
Persistent memory system for AI agents running on Cloudflare's edge network. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when yo...
Write technical Q&A responses as markdown files to Claude Overflow. Use for programming questions, code explanations, debugging help, API usage. The response becomes a permanent archived answer viewable in a we...
Frontend development skill for Quest Keeper AI Tauri application. Use when working on React components, Zustand stores, Three.js battlemaps, TailwindCSS styling, or Tauri shell integration. Triggers on mentions...
Master orchestration skill for Quest Keeper AI development. Use when working on ANY part of Quest Keeper AI - coordinates between frontend (Tauri/React), backend (rpg-mcp), and documentation. Triggers on any me...
Deep attachment analysis with extraction, importance classification, and content analysis for emails and threads.
A simple skill that echoes a message with the current timestamp. Use when asked to echo or repeat a message with a timestamp, get the current time along with a message, or demonstrate basic skill functionality.
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.