GitHub
backend-dev
Python backend development for CTF-AI. Use when working on game engine, player logic, pathfinding, WebSocket server, or any backend Python code.
Skills IA research llm ai
Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: research llm ai
research llm ai Effacer les filtres
Explorer
GitHub
ai-partner-chat
基于用户画像和向量化笔记提供个性化对话。当用户需要个性化交流、上下文感知的回应，或希望 AI 记住并引用其之前的想法和笔记时使用。
GitHub
hello-world
A simple skill that should be used to respond to a user when the enter the phrase "hello world".
GitHub
creating-skills
Helps the agent generate high-quality, predictable, and efficient .agent/skills/ directories based on user requirements. Use when the user asks to create a new skill or modify an existing one.
GitHub
brand-identity
Provides the single source of truth for brand guidelines, design tokens, technology choices, and voice/tone for the Sheet Guardian project. Use this skill whenever generating UI components, styling applications...
GitHub
humanize
Transform AI-generated text to match user's voice and communication style. Use when drafting messages, emails, documents, or any external communication that should sound like the user wrote it.
GitHub
generate
Generate command centre from onboarding answers. Use after completing onboarding to create CLAUDE.md, skills, people files, and seed memory graph. Invoke with target directory path.
GitHub
skill-generator
Generates well-structured Agent Skill documents following Claude Code best practices. Use when asked to create new Agent Skills, draft SKILL.md files, or design skill architectures.
GitHub
user-research-flows
Expert consultant in user research, persona development, user journey mapping, and flow design for complex systems with 10+ years of experience. Specializes in SaaS products, operational systems, DevOps, NOC, o...
GitHub
microcopy-content-design
Expert content designer and microcopy specialist with 10+ years of experience writing for complex systems, SaaS products, operational interfaces, and enterprise applications. Specializes in tight, action-orient...
GitHub
azure-avatar
Build real-time AI avatars using Azure Voice Live API and GPT-Realtime with WebRTC/WebSocket streaming. Supports two modes for interactive avatar applications.
GitHub
hybrid-agents
Hybrid Agentic Workflows - Build production-ready multi-agent systems with Microsoft Agent Framework (client-side) and Azure AI Foundry Agent Service (cloud-managed). Supports MCP integration and multi-agent or...
GitHub
workflow-metrics
Track, evaluate, and analyze multi-agent AI workflows using Azure AI Foundry cloud evaluations. Use when logging agent trajectories, computing evaluation metrics, measuring plan adherence, or generating workflo...
GitHub
fast-transcription
Azure AI Speech Fast Transcription - Transcribe contact center calls with speaker identification using stereo channel separation or mono diarization. Returns results synchronously and faster than real-time.
GitHub
postgres-ai
Azure PostgreSQL AI Integration - Vector search, RAG pipelines, and agent memory with pgvector and azure_ai extensions
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.
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
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.