Discover content media llm ai skills, compare source repositories and read the instructions for each workflow.
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.
Activates automatically when user greets warmly. Demonstrates the auto-trigger pattern—Claude detects friendly intent and engages accordingly.
OmO multi-agent orchestration skill. This skill should be used when the user invokes /omo or needs multi-agent coordination for complex tasks. Triggers on /omo command. Loads Sisyphus as the primary orchestrato...
Codex 执行者技能包。Claude 通过 codeagent-wrapper 派发任务时，根据任务类型路由到子技能。
Decide between a scripted workflow and an autonomous agent harness, then scaffold the chosen path. Use when scoping new agentic systems or tool integrations.
Design long-running agent harnesses with resumable checkpoints and initializer/coder handoffs. Use when tasks span multiple sessions or require recovery after interruption.
A meta-skill for authoring high-performance, verifiable, long-running MCP skills using Code Mode. This skill blends Anthropic and OpenAI skill-authoring guidance with Code-Mode-first, MCP-backed execution, dyna...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.