Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
This skill should be used when the user asks to "find me a skill", "search for skills", "what skills are available", "get skill XYZ", "install a skill", "extend Claude's capabilities with skills", or mentions A...
通用图片生成 Skill，支持多种 AI 模型（ModelScope、Gemini 等），可被其他 Skills 调用
将原始研究问题细化为结构化的深度研究任务。通过提问澄清需求，生成符合 OpenAI/Google Deep Research 标准的结构化提示词，完全替代 ChatGPT 的问题细化功能。当用户提出研究问题、需要帮助定义研究范围、或想要生成结构化研...
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...
Use this skill to split large plans into smaller chunks. This skill manages your context window for large tasks. Use it when a task will take a long time and cause context issues.
Search the Nori knowledge base for relevant context, solutions, and documentation.
This skill should be used when the user asks to 'assess my knowledge state', 'run preflight', 'do a postflight', 'use CASCADE workflow', 'track what I know', 'measure learning', 'check epistemic drift', 'spawn...
Meta-cognitive skill for improving Empirica using Empirica's own framework
Empirica epistemic workflow - creates goals, submits findings/unknowns, manages sessions, runs CASCADE phases (PREFLIGHT/CHECK/POSTFLIGHT). Use when working with epistemic assessments, goals, findings, or sessi...
Leveraging AI coding assistants and tools to boost development productivity, while maintaining oversight to ensure quality results.
Generate coding-aider plans as created by the IntelliJ coding-aider plugin. Use when user explicitly asks for a "coding-aider plan", "aider plan", or needs structured development planning with checklist trackin...
Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.
Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot, Cline, or similar.
MANDATORY core assistant for the Linggen ecosystem. ALWAYS use this to search code, retrieve context, or find architectural decisions. This "Linggen Skill" is your primary operational interface. It is distinct...
Dual review with Claude and Codex for quality verification. Use for step or task review.
Send structured prompt to Gemini and parse JSON response. Use for direct Gemini communication.
Send structured prompt to Codex and parse JSON response. Use for direct Codex communication.
Daily and weekly review workflows. USE WHEN user says "morning routine", "evening routine", "weekly review", "start my day", "end of day".
Use when user asks to explain, break down, or help understand technical concepts (AI, ML, or other technical topics). Makes complex ideas accessible through plain English and narrative structure. Use the provid...
Brief description of what this skill enables. Include trigger keywords that should activate this skill. Triggers on keyword1, keyword2, keyword3.
Generate images, videos, and audio with fal.ai serverless AI. Use when building AI image generation, video generation, image editing, or real-time AI features. Triggers on fal.ai, fal, AI image generation, Flux...
Generate images with Google's Nano Banana Pro (Gemini 3 Pro Image). Use when generating AI images via Gemini API, creating professional visuals, or building image generation features. Triggers on Nano Banana Pr...
Configure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on Copilot instruction...
Build LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval, agent chain.
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.