影片處理

Transform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework. Use when user wants to turn advice, lessons, or educational content into concrete action steps, reps, or a learning quest.

Workflow for acquiring historical Ethereum blockchain data using Google BigQuery free tier. Empirically validated for cost estimation, streaming downloads, and DuckDB integration. Use when planning bulk historical data acquisition or comparing data source options for blockchain network metrics.

合并多个视频文件为一个视频。Use when user wants to 合并视频, 拼接视频, 视频合并, 视频拼接, 把视频合在一起, 连接视频, join videos, merge videos, combine videos, concatenate videos.

Video editing via FFmpeg with git-like staging workflow and platform presets.Use when the user asks to: (1) cut/trim/edit videos, (2) convert formats or codecs,(3) optimize for platforms (WhatsApp, Instagram, YouTube, Twitter, Telegram),(4) extract audio or create GIFs, (5) get video info/metadata, (6) rotate/resize/crop,(7) speed up/slow down videos, (8) compress videos, (9) concatenate multiple videos.All operations go to staging before final approval. Supports operation history,replay, batch processing, and undo/redo.

Build Claude agents using TypeScript with the @anthropic-ai/claude-agent-sdk. Use this skill when implementing conversational agents, building tools for agents, setting up streaming responses, or debugging agent implementations. Covers the tool wrapping pattern, SDK initialization, agent architecture, and best practices.

Process multiple content items from a batch list file. Use when the user wants to analyze multiple videos, articles, or papers at once, mentions batch processing, or has a list of items to process.

Craft LinkedIn posts (text, carousels, documents, video) optimized for the December 2025algorithm. Use when creating individual LinkedIn posts, writing hooks, designing carouselcontent, or adapting newsletter content for LinkedIn. Includes algorithm signals, formatselection, external link workarounds, and templates for thought leadership content.

Downloads YouTube video transcripts (subtitles/captions) using yt-dlp, with a fallback to Whisper transcription if no subtitles are available. Use when a user provides a YouTube URL and asks for a transcript, captions, or subtitles.

Navigate web-based trainings that gate progress via timers/videos/disabled Next buttons.

Rust development patterns for video processing, trait abstractions, error handling, and Linux device interaction

Gaming ecosystem for Bazzite. Steam fixes, Proton troubleshooting, EmuDeck emulation,Decky Loader plugins, Sunshine game streaming, frame generation, and media apps.Use when users need help with gaming on Bazzite.

Summarize YouTube videos. Check if transcript exists at `youtube/{Channel Name}/transcript-{Video Title}.md`. If exists, skip to summarization. If not, download first. Create summary at `youtube/{Channel Name}/summary-{Video Title}.md` with topics and clickable timestamp links.

AI video generation with Sora, Veo, and Kling. Use when creating Reels, video prompts, or handling video generation workflows.

Integrates Anthropic Claude API for chat, tool use, and vision capabilities. Use when building AI-powered features with Claude models including streaming, extended thinking, and multi-turn conversations.

Extract transcripts and metadata from YouTube videos

Multimodal AI processing using Google Gemini. Use for analyzing PDFs, images, videos, YouTube links, and other large documents. Ideal when you need to extract information from files that require vision or multimodal understanding.

Automatically applies when building LLM applications. Ensures proper async patterns for LLM calls, streaming responses, token management, retry logic, and error handling.

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).

Strategy for creating efficient short-form video prompts. Use when creating filler shots, atmospheric scenes, or quick video clips that don't require full Production Brief methodology. Covers when to go short vs long, format+style upfront rule, and two approaches (Descriptive vs Directive) for compact yet coherent results.

Design and implement React Server Components with Next.js 15 App Router. Master server-first architecture, streaming SSR, Server Actions, React 19 patterns, and modern data fetching for 2025+ development.