Video Processing

Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution.

Build AI applications with OpenAI Agents SDK - text agents, voice agents (realtime), multi-agent workflows with handoffs, tools with Zod schemas, input/output guardrails, structured outputs, and streaming. Deploy to Cloudflare Workers, Next.js, or React with human-in-the-loop patterns. Use when: building text-based agents with tools and Zod schemas, creating realtime voice agents with WebRTC/WebSocket, implementing multi-agent workflows with handoffs between specialists, setting up input/output guardrails for safety, requiring human approval for critical actions, streaming agent responses, deploying agents to Cloudflare Workers or Next.js, or troubleshooting Zod schema type errors, MCP tracing failures, infinite loops (MaxTurnsExceededError), tool call failures, schema mismatches, or voice agent handoff constraints.

Process expert sources (videos, podcasts, articles, books) into structured insights. Use when ingesting new knowledge sources for extraction and analysis.

Complete pre-production workflow that chains research, project creation, script generation, and presentation in one seamless flow. Use when starting a new video from competitor research all the way through to a ready-to-record script.

Craft effective prompts for VEO single-clip video generation - READ before any generate_video_clip call

Unified content extraction and action planning. Use when user says "tapestry <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly.

Complete curation and streaming economics including playlists, radio, mixed content, revenue calculations, and the two-economy system (creation vs curation)

Build gRPC services with Go - protobuf, streaming, interceptors

Fetch YouTube video transcripts and save them as markdown files. Use when user provides YouTube URLs and wants transcripts, captions, subtitles, or video text content. Supports youtube.com/watch, youtu.be, and embed URLs.

Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).

Analyze your uploaded YouTube videos' performance against competitor benchmarks using Playwright MCP. Use when asked to review video analytics, compare performance, check how a video is doing, or reflect on a video's success.

Foundation skill for integrating OpenAI ChatKit framework with custom backends. This skill should be used for initial ChatKit setup including server implementation, React component integration, authentication, context injection, and database persistence. For streaming UI patterns use chatkit-streaming. For interactive widgets and actions use chatkit-actions.

Creates a new YouTube video project with comprehensive research, competitor analysis, folder structure, and todo.md for progress tracking. Uses Playwright MCP to fetch vidIQ stats, analyze competitors, and gather research automatically. Use when starting a new YouTube video, saying "new video", "start a video project", or "I want to create a YouTube video".

Extract subtitles/transcripts from a YouTube video URL and save as a local file. Use when you need to extract subtitles from a YouTube video.

Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.

Create vertical (9:16) interactive presentations optimized for YouTube Shorts, TikTok, and Instagram Reels. Takes YouTube video URLs to extract facts via Playwright MCP and web research, then generates animated slides you can screen record and narrate. Perfect for quick educational content, fact-reveals, and viral short-form videos.

AuViMa视频自动化制作专家。当用户需要收集视频资料、制作视频素材(clip)、生成声音克隆配音或合成最终视频时使用此skill。涵盖Chrome CDP操作、屏幕录制、声音克隆API调用和视频合成流程。

Create compelling social media bios for any platform. Use when the user needs bios for Twitter/X, Instagram, LinkedIn, TikTok, YouTube, or any social platform.

Platform color palette with semantic meanings, hex codes, accessibility notes, and usage patterns for all content types including loops, songs, playlists, video, and radio

Cut video segments by timestamp, split videos into chunks, trim start/end, and extract specific scenes with precise frame control.