GitHub
vlm-expert
实现基于视觉的 AI 对话能力，支持分析图像、描述视觉内容并进行多模态交互。
Skills IA devops llm ai
Découvrez les skills devops llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: devops llm ai
devops llm ai Effacer les filtres
Explorer
GitHub
skill-factory
Meta-skill for generating new standard skill modules. Context-aware: analyzes user requirements to select appropriate templates (Basic/Generator/Data) and automatically populates metadata (name, tags, descripti...
GitHub
ai-llm-engineer
设计 AI 架构，编写 Prompt，构建 RAG 系统和 LangChain 应用
GitHub
image-generation-expert
实现 AI 图像生成能力，支持根据文本描述创建高质量图像。
GitHub
strategic-thought-partner
Collaborative strategic thinking for founders, operators, and decision-makers. Use when someone needs help working through business strategy, product direction, positioning, prioritization, or major decisions....
GitHub
skill-author
Creates production-grade Claude Code skills from natural language descriptions. Use when building new skills, requested with "build me a skill that...", "create a skill for...", or "I need a skill to...". Gener...
GitHub
blog-editor
Brutal content editor that tears apart drafts for substance, readability, and voice alignment. Use when reviewing blog posts, articles, or marketing copy. Triggers include "review this draft", "edit my post", "...
GitHub
folk-crm
Connection skill for Folk CRM MCP server. Provides guidance on ID handling, tool selection, and error recovery for AI assistants interacting with Folk CRM.
GitHub
rag
検索増強生成（RAG）Skill。知識ベースへのドキュメント追加、意味検索、LLM 回答生成をサポート。 ドキュメント Q&A、社内知識検索、カスタム知識ベース構築に使用。
GitHub
chatbot
マルチターン対話管理 Skill。会話履歴管理、コンテキスト維持、Agent 連携、RAG 統合をサポート。 チャットボット構築、対話型アシスタント、カスタマーサポートボットに使用。
GitHub
daoagent
本質分析Agent - 問題の本質を見抜き、因果齿轮で構造化し、死穴（禁忌）を明らかにする
GitHub
deepagents
LangChain Deep Agents framework for building autonomous coding agents. Use for agent harness, backends, subagents, human-in-the-loop, long-term memory, middleware, and CLI-based agent development.
GitHub
langgraph
LangGraph Python framework for building stateful, multi-actor LLM applications. Use for agent workflows, persistence, durable execution, streaming, interrupts, time travel, memory, subgraphs, and production dep...
GitHub
process-faq
Process and transform FAQ documents (xlsx, word, pdf, txt) into RAG-optimized format. Use when working with FAQ files, knowledge base documents, or when the user needs to analyze and restructure FAQ content for...
GitHub
langchain
LangChain Python framework for building LLM applications. Use for chains, agents, memory, document loaders, text splitters, vector stores, retrievers, and LLM integrations like OpenAI, Anthropic, and Google.
GitHub
fal-ai-add
fal.aiスキルに新しいモデルを追加するためのスキル
GitHub
fal-ai
fal.ai APIを使って画像生成・画像編集・動画生成を行うワークスペーススキル
GitHub
ai-sdk-v6
Guide for building AI-powered applications using the Vercel AI SDK v6. Use when developing with generateText, streamText, useChat, tool calling, agents, structured output generation, MCP integration, or any LLM...
GitHub
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, rou...
GitHub
reflect
Capture lessons from conversation after Claude made mistakes or needed correction. Trigger phrases include "reflect", "review our mistakes", "learn from this", "capture this lesson", "remember this for next tim...
GitHub
tui
Create distinctive, production-grade terminal user interfaces (TUIs) using OpenTUI. Use this skill when the user asks to build CLI tools, terminal dashboards, interactive console applications, or any interface...
GitHub
memory-checkpoint
Externalize detailed memory to Memory Bank before conversation summarization to prevent context loss. Triggers: CP, checkpoint, save, 存檔, 記一下, 保存, sync memory, dump, 先記著.
GitHub
request-dot-ai-feature
Generate a feature request prompt for another dot-ai project. Use when you need a feature implemented in a sibling project (MCP server, controller, etc.) to unblock work in the current project.
GitHub
req-to-executable-prompt
將使用者的自然語言需求，轉換成「Codex 可直接執行」的工程指令 prompt。 輸出內容包含：背景、明確目標、可驗收條件、操作步驟、不可違反的限制、與交付格式。 適用於任何語言、任何 repo、任何專案階段。
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.