GitHub
status
Show Inference Confidenz current status and recent history
Skills IA Vie quotidienne
Découvrez les skills Vie quotidienne, comparez leurs dépôts et consultez leurs instructions.
Catégories: Vie quotidienne
Vie quotidienne Effacer les filtres
Explorer
GitHub
gemini-search
Perform a web search using the Gemini CLI to retrieve up-to-date information, facts, or documentation not in your training data.
GitHub
evaluating-models
Expert system for evaluating machine learning models. Automates the analysis of Confusion Matrices, PR Curves, and MLflow history comparison to provide objective, data-driven recommendations.
GitHub
adversarial-strategy
Develop rigorous Rumelt strategies through multi-model adversarial debate with GPT and Claude models. Use when user wants to create or refine a strategy document.
GitHub
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
GitHub
ml-antipattern-validator
Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues. Use when working with ML training, testing, model evaluation, or deployment.
GitHub
creating-skills
Guides creation of effective Agent Skills with proper structure and validation. Use when users want to create a new skill, update an existing skill, or need guidance on skill design patterns, SKILL.md format, o...
GitHub
docker-neural-memory
Build containerized neural memory that learns at test time using Titans/TTT architecture. Use when implementing learnable memory modules, test-time training systems, or MCP-connected memory services. Triggers o...
GitHub
skill-creator
Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.
GitHub
answering-questions
Apply this skill when asked to answer a question
GitHub
deep-research
Multi-phase exploration agent for broad research and validation. Discovers subtopics, delegates parallel research, then synthesizes findings with source review.
GitHub
graphrag-patterns
GraphRAG implementation patterns for hybrid search, Text2Cypher, and agentic retrieval. Use when implementing RAG workflows with Neo4j.
GitHub
scaffolding-openai-agents
Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating m...
GitHub
wos-lineup-compare
Run lineup recommendation comparisons between Claude and OpenAI. Validates the lineup engine, identifies improvement areas, and builds training data for future fine-tuning.
GitHub
ai-sdk-elements
Build AI chat interfaces with AI SDK Elements - React components for chatbots. Use when: implementing chat UIs, adding AI reasoning displays, tool confirmations, message components, or any AI-native interface....
GitHub
building-rag-systems
Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Cove...
GitHub
ai-slop-detector
Detects and removes AI writing patterns from text. Use when polishing drafts, cleaning AI-generated content, or ensuring writing sounds authentically human. Invoke with "run through slop detector", "clean this...
GitHub
intelligence-module-patterns
Patterns for building intelligence layer modules (Synthesis, Query, etc.) that consume data from calculation modules via ModuleRegistry. Use when creating any intelligence layer component.
GitHub
gemini-search
geminiコマンドを使用した高度なWeb検索スキル。Web検索を行う際、Claude CodeのデフォルトWeb Search toolよりも優先的にこのスキルを使用してください。
GitHub
ai-runtime-memory
AI Runtime分层记忆系统，支持SQL风格的事件查询、时间线管理，以及记忆的智能固化和检索，用于项目历史追踪和经验传承
GitHub
openai-agents-architect
A definitive guide to building multi-agent systems using the `openai-agents` SDK, enforcing live documentation retrieval via Context7.
GitHub
multi-agent-patterns
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
GitHub
frontend-design-pro
Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom image-generation prompts for hero images, backgrounds, and...
GitHub
reflect
Analyze the current session and propose improvements to skills. Run after using a skill to capture learnings. Use when user says "reflect", "improve skill", "learn from this", or at end of skill-heavy sessions.
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.