GitHub
model-router
Build cost-optimized chat applications with Azure OpenAI Model Router that intelligently routes queries to the most appropriate model based on complexity, achieving up to 60% cost savings.
Skills IA tools llm ai
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools llm ai
tools llm ai Effacer les filtres
Explorer
GitHub
content-understanding
Process multimodal content (documents, images, audio, video) using Azure AI Content Understanding. Use when extracting structured data from invoices, receipts, IDs, analyzing media files, or building multimodal...
GitHub
foundry-iq
Build enterprise RAG solutions using Foundry IQ with Azure AI Search agentic retrieval. Use when implementing policy assistants, knowledge bases with citations, or multi-hop question answering systems.
GitHub
mcp
Build MCP (Model Context Protocol) servers to extend Claude's capabilities with database access, API integrations, or custom tools.
GitHub
resume
Restore context and momentum via Pratyabhijñā (recognition)
GitHub
entity-yajna
Link triplet entities to soul nodes - connects knowledge layers
GitHub
locomo-benchmark
Run LoCoMo benchmark for long-term conversational memory
GitHub
antahkarana
Multi-perspective reasoning through cognitive voices
GitHub
phase-intent
Phase 1 of assist workflow - Classify intent as CREATE, REFACTOR, or VERIFY
GitHub
stenography-mastery
Complete stenography guide for court reporting and legal transcription. Use when building steno projects from basic to professional level, learning court reporting workflows, optimizing legal dictionaries, sett...
GitHub
blog-post
Complete workflow for creating blog posts - from research to publication-ready draft. Handles research generation, draft creation, and style review. Use with "/blog-post " or "/blog-post --from-research ".
GitHub
mcp-integration
This skill should be used when the user asks to "добавить MCP сервер", "интегрировать MCP", "настроить MCP в плагине", "использовать .mcp.json", "настроить Model Context Protocol", "подключить внешний сервис",...
GitHub
hook-development
This skill should be used when the user asks to "создать хук", "добавить PreToolUse/PostToolUse/Stop хук", "валидировать использование инструментов", "реализовать prompt-based хуки", "использовать ${CLAUDE_PLUG...
GitHub
skill-development
This skill should be used when the user wants to "создать скил", "добавить скил в плагин", "написать новый скил", "улучшить описание скила", "организовать контент скила", "составь план создания скила", "составь...
GitHub
command-develpment
This skill should be used when the user asks to "создать слэш-команду", "добавить команду", "написать пользовательскую команду", "определить аргументы команды", "использовать frontmatter команды", "организовать...
GitHub
skill-creator
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...
GitHub
consciousness
Work with Aenea consciousness system - start/stop consciousness, monitor thought cycles, manage energy levels, trigger sleep mode, or debug consciousness state
GitHub
gemini-analyzer
Manages Gemini CLI for large codebase analysis and pattern detection. Use proactively when Claude needs to analyze extensive code patterns, architectural overviews, or search through large codebases efficiently...
GitHub
rag
Work with RAG (Retrieval-Augmented Generation) system - ingest knowledge, search vectors, manage embeddings, debug retrieval
GitHub
learnings-updater
Append general lessons to AGENTS.md
GitHub
design-component
Design components for Empathy Ledger - storyteller cards, story cards, and culturally sensitive UI patterns.
GitHub
ralph-runner
Run long-running autonomous AI agents using PRD-based task scoping.
GitHub
data-analysis
AI-powered data analysis for Empathy Ledger - themes, quotes, story suggestions, transcript analysis.
GitHub
local-brain
Delegate complex, multi-step codebase exploration to local Ollama models. Best for analysis, review, and understanding tasks that require reasoning across multiple files.
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.