发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Research-powered creative strategy with visual previews. Use when you need to figure out WHAT to create before creating it. Researches competitors, captures references, generates visual direction previews, and...
Specialized skill for AI talking head and lip-sync video generation. Use when you need presenter videos, UGC-style content, or lip-synced avatars. Triggers on: talking head, presenter video, lip sync, UGC video...
Execute AI image generation with optimal quality. Use when you need to generate images via Replicate API. Triggers on: generate image, create visual, product shot. Outputs generated images for feedback and iter...
Data analyst for hiring market insights. Use when asked to create reports, analyze trends, generate content for LinkedIn/blog posts, answer marketplace questions, or produce data visualizations.
This skill should be used when the user asks about "AIP rules", "API Improvement Proposals", "Google API guidelines", "AIP-158", "AIP-193", or any specific AIP number. Also use when user asks "how should I impl...
Control Sonos speakers through MCP tools - search and play music, manage queue and playlists, adjust volume. Use when users request music playback, mention artists/songs/albums, want to control Sonos speakers,...
Generate AI images using fal.ai Nano Banana Pro model. Use this skill when (1) User requests image generation or creation, (2) User wants AI-generated visuals for websites, products, or marketing, (3) User asks...
Understand natural language descriptions and generate bash commands for macOS/Linux with explanation.
Create a new Claude Code skill with proper directory structure and SKILL.md format.
Persistent semantic memory for AI agents. Ingest, search, consolidate context across sessions. Manages Qdrant + Ollama infrastructure and background daemon.
A simple example skill that demonstrates Claude Code skill structure
Use immediately when user mentions: "処理フロー", "processing flow", "フロー図", "flow diagram", "Mermaid", "アーキテクチャ", "architecture", "理解負債", "understanding debt", "なぜ", "why", "数式", "理論", "可...
Create CLI entrypoints for pipeline execution with local/SageMaker environment support and parallel processing. Use when user requests "CLI作成", "エントリーポイント", "entrypoint", "scripts/entrypoint.py", "コ...
Use immediately when user mentions: "実装して", "implement", "機能追加", "feature", "作って", "create", "バグ修正", "fix", "実験", "experiment", "統合", "integrate", "ワークフロー", "workflow", "パイプライン",...
Creates comprehensive specifications through deep technical interviews. Use when asked to create a spec, define requirements, interview for a config, or refine an existing specification document.
Create high-quality Claude Code skills with proper structure, effective descriptions, and best practices. Use when creating a new skill, writing SKILL.md files, setting up skill directories, or asking how to ma...
Create new AI agent implementations for the Yui Protocol system. Use when adding agents like Yui, Eiro, Kanshi.
Manage RAG (Retrieval-Augmented Generation) indexes. Use for indexing outputs, sessions, or checking RAG statistics.
Create multi-platform explainer videos (YouTube, Shorts, TikTok, Instagram, LinkedIn) with intelligent orchestration, Brand × Platform × Style configuration, and learning memory
Use when creating explainer videos, video content for YouTube/TikTok/Instagram/LinkedIn, or when user mentions /video command. Creates multi-platform explainer videos with intelligent orchestration, learning me...
Start iterative requirement clarification loop. Use this skill when the user has a vague requirement and wants to clarify it through structured questioning. Transforms unclear requirements into precise, actiona...
Execute NPM packages as AI agent tools - a flexible alternative to MCPs
Demonstrates how skills can include executable scripts for automation, calculations, transformations, or system interactions. Use when needing to execute Python, Bash, Node.js, or other scripts.
Auto-triggered skill that responds warmly when users greet the assistant. Activates when user says hello, hi, hey, greetings, good morning, good afternoon, or good evening.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。