Media AI Skills

Find and play music/videos via youtube_search + browser_navigate

用户要总结一个视频、提炼要点、写内容摘要或会议纪要式的回顾时用：挑出这一期最值得带走的两三件事，从读者关心的问题讲起、讲透，其余少说或不说；另附一组带视频时间的要点，方便跳回那一段。适用于访谈、播客、演讲、教程、评测、会议、圆桌等任何有转写的视频。不用于总结与视频无关的文章或纯文本，也不用于写博客文章（那是另一种产出）。

Transcribe audio/video with AssemblyAI (local upload or URL), plus subtitles + paragraph/sentence exports.

Use when one master design has to become every size a campaign needs — feed, story, reel, cover, and ad placements: the standard size matrix, three strategies of scale-and-crop, re-compose, or…

Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays…

海外跨平台热文搜索 — 输入任意关键词（中文/英文），一次搜索 X / TikTok / YouTube 三平台热门内容，每平台 Top N（默认5）统一列表（平台/标题/作者/播放/点赞/评论/发布时间/链接），终端分组表格 + CSV 导出 + 交互式 HTML…

Convert written documents to narrated video scripts with TTS audio and word-level timing. Use when preparing essays, blog posts, or articles for video narration. Outputs scene files, audio, and VTT…

Voice and video calling in the CometChat React Native UI Kit v5 — the RN calls SDK, the native permissions and version floors it needs, and why installing the package is itself the enable switch.…

Design a high-CTR YouTube thumbnail — striking imagery, bold text placement, and emotional face/subject if needed.

ChIP-seq peak calling using MACS3 (or MACS2). Call narrow peaks for transcription factors or broad peaks for histone modifications. Supports input control, fragment size modeling, and various output…

Generate speech or transcribe audio locally with Voicebox. Use for narration, voice assets, dictation, and meeting transcription.

Transcribe speech to text using Apple's Speech framework. Use when implementing live microphone transcription with AVAudioEngine, recognizing recorded audio files, handling speech and microphone…

Generates motion graphics videos (MP4) from a content brief. Multi-scene HTML/CSS animations rendered frame-by-frame in headless Chromium via Playwright, assembled with FFmpeg. 1080×1080 default, 16:9…

Use when paid ad AUDIENCES must be researched and defined before launch — target profile, interest and behavior mapping per platform, audience sizing, cold, warm, and hot tiering, lookalike seeds,…

Create, compose, animate, and render HTML-based video compositions using HyperFrames — an open-source video rendering framework built for AI agents. Covers composition authoring with data attributes,…

Extract video transcripts: yt-dlp subtitles to clean paragraphs.

The live + realtime-format skill -- plan, promote, run, and repurpose livestreams and realtime moments (IG Live, TikTok LIVE, YouTube Live, LinkedIn Live, X, live shopping). Use when someone wants to…

物理层硬件逆向：去封装、裸片分析、探针与 FIB、PCB 电路分析、硬件木马检测。 触发词：芯片逆向、去封装、decapping、PCB、硬件木马、电路分析、裸片、FIB、侧信道、SPA、DPA、故障注入、时钟毛刺、电压毛刺。

Plan and prompt a stylized 3D animated short for Seedance 2.0 with stable character identities, environment continuity, causal story beats, shot-specific performance, camera, sound, and clip handoffs.…

The closed list of CometChat React Native UI Kit v5 components, what each one is for, and how to put custom UI INSIDE a component's view slot instead of stacking it on top. Triggers: which CometChat…

Video content planning. Writes narration scripts, storyboards, shot lists, and asset checklists. Saves plan to marketing/video-plan.md.

Hume AI Octave TTS and EVI speech-to-speech configs: synthesize speech and manage EVI configs. Trigger phrases: hume, hume ai, octave tts, EVI config.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and…

Generates a cinematic product launch video (MP4) from a product description and launch context. 5-section narrative arc — Tease, Build, Reveal, Proof, CTA — rendered as HTML/CSS in headless Chromium…

Discover, search, and manage Spotify music, podcasts, and playlists, including deleting shows or episodes you created with Save to Spotify.

参考動画からプロ品質の Remotion 動画を再現するワークフロースキル。 「参考動画から再現したい」「動画トレース」「PVを作りたい」「Remotion動画を参考動画ベースで作りたい」で発動。

Plan and prompt a stylized 3D animated short for Seedance 2.0 with stable character identities, environment continuity, causal story beats, shot-specific performance, camera, sound, and clip handoffs.…

The Luma Dream Machine craft skill — generate cinematic AI video shots (Ray3: text-to-video, image-to-video, keyframes, character reference, Modify V2V, HDR) with draft-first economics and the right…

UTM Parameter Strategy & Builder — naming conventions, GA4 channel grouping rules, auto-tagging, common mistakes, and BigQuery validation queries

把小宇宙播客链接转成文字稿和文章。实现原理：下载小宇宙音频 → Groq Whisper 转录成文字 → 由 Claude 编写成文章。 触发词："小宇宙转文字"、"播客转文章"、"把这个小宇宙链接转成文章"、"小宇宙文稿"，或用户直接发来 xiaoyuzhoufm.com 的单集链接。 产出两份：逐字文稿（含标点润色）+ 改写后的文章。

Builds a B2B paid social plan across LinkedIn, Meta, and TikTok: platform selection, audience building, creative testing, and budget allocation. Use when the user is launching paid social, planning…

Use when the user asks to publish, update, search, or clean up WordPress pages, posts, or media from the terminal or an AI agent - drives the WordPress REST API and keeps a local SQLite mirror for…

自媒体创作者与内容创作者在制作数字人播报或视频配音时，只需输入单张人像与音频，即可自动生成唇形、表情、动作完美同步的无限时长说话视频。一键打造高质量虚拟主播内容，告别繁琐拍摄，让音视频创作更高效！

Extract subtitles and transcripts from Bilibili and YouTube videos. Use when the user wants to get subtitles from B站 (Bilibili) or YouTube, extract Chinese/Japanese video transcripts, watch…

ElevenLabs Text-to-Speech API for high-quality speech synthesis.

Transcribe audio and video files using the configured speech-to-text provider

Design a pedagogical documentation protocol for making children's learning processes visible and shareable. Use when documenting learning, communicating with families, or planning next steps.

Generates a high-energy sizzle reel or hype video (MP4) from brand assets and key messages. Fast-paced montage format with dynamic cuts, bold text overlays, and optional music. 4-section structure:…

Generate audiobooks, podcasts, or educational audio content on demand. User provides an idea or topic, Claude AI writes a script, and ElevenLabs converts it to high-quality audio. Supports multiple…

OPS on-demand: This skill should be used when the user asks to "make a call", "facetime", or…

The cultural-fluency + meme-craft skill -- participate in internet culture and meme formats as a brand without being cringe, tone-deaf, or legally exposed. Use when someone wants to make a meme, join…

Create, implement, or review gsap core work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on gsap core.

Convert an MP4 (e.g. a HyperFrames render or a screen recording) to a high-quality GIF using FFmpeg's two-pass palette method. Picks the right preset for the target surface —…

获取关注的 YouTube 博主/播客的最新更新。列出最近两天的新视频，包含标题、发布时间和简要描述。 触发词："获取播客更新"、"最近有什么新播客"、"YouTube 更新"、"播客更新"、"有什么新的播客"。 用于每日检查关注的 AI/科技播客是否有新内容更新。

Create new mod content and assets that match the game, using the end user's chosen local or paid tools.

Use Google App Campaigns + Apple Search Ads attribution data to discover winning keywords for Play ASO. Use when the user says 'asa to aso android', 'google app campaigns', 'paid traffic to aso…

Inspect FaceTime internal stages, place an approved call to a configured owner handle, and request hangup through facetime_call.

Summarize a customer interview transcript into a structured template with JTBD, satisfaction signals, and action items. Use when processing interview recordings or transcripts, synthesizing discovery…

自媒体创作者与内容创作者在制作数字人播报或视频重配音时，只需单张人像图片与音频，即可一键生成唇形、头部运动及身体姿态精准同步的无限时长说话视频。轻松搞定虚拟主播内容，大幅节省真人拍摄与后期剪辑时间！

Shape prose so it sounds like Braden, with conversational precision, rhythm, humor, and earned poetic turns. Use for substantial drafting or revision, an ear pass, and explicit voice or tone work in…