Media AI Skills

Generate a complete set of multi-angle product shots — front, side, back, top-down, and 45-degree perspective — for comprehensive product visualization.

视频脚本洗稿和二创脚本工作流。Use when the user provides an existing transcript, oral draft, viral script, competitor video text, rough topic notes, or wants 洗稿, 二创改写, 爆款视频脚本重写, 逐字稿改成短视频脚本, rewrite with ra-人话, and…

Generate Chinese / Japanese speech with StepFun's Contextual TTS — default `stepaudio-2.5-tts` (blind-judged better on neutral/emotive preset voices), `stepaudio-3-tts` for whisper & inline-prosody…

Implement, review, or improve photo picking, camera capture, and media handling in iOS apps using PhotoKit and AVFoundation. Use when working with PhotosPicker, PHPickerViewController, camera capture…

ElevenLabs text-to-speech with mac-style say UX.

Map the dark funnel attribution misses: communities, AI citations, podcasts, word of mouth. "map our dark funnel"

Transforms reading-oriented prose into listening-optimized text for flat, neutral vocal delivery — TTS, podcasts, audiobooks, CLE audio. Carries a legal layer: case citations, section symbols,…

Plan, produce, and market a podcast. Use when the user says "podcast strategy", "start a podcast", "podcast marketing", "podcast growth", "podcast SEO", "show notes", "podcast monetization", "guest…

一两个人对着镜头说话的录音要剪成能发布的视频时用：去掉口癖、长停顿、录废重来的部分和离题的话，在几遍重录里挑一遍，收紧句间停顿，把最有力的原话挪到开头，再按需要加放大强调、B-roll、竖屏取景和配乐闪避。需要视频的转写。只想从长视频里挑几段短视频时用切短视频。

Create and maintain Karpathy KB topics from YouTube channels through scaffolding, bulk transcript ingestion, validation, and indexing. Excludes single videos, general summaries, and other sources.

Use when an editor or videographer needs production direction — beat-by-beat storyboard, footage to shoot, b-roll, text overlays, music and pacing, transitions, CTA end frame, and per-channel export…

Reference data, not a reviewer. Video/audio accessibility: WebVTT/SRT/TTML captions, audio descriptions, accessible media player ARIA, and WCAG 1.2.x compliance.

Collects videos from public social accounts. Use to download or scrape from Twitter, TikTok, YouTube, Instagram, or Facebook.

Use when generating talking, singing, or presentation videos from a single character image and audio with Alibaba Cloud Model Studio digital-human model `wan2.2-s2v`. Use when creating narrated avatar…

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud,…

The generative-video producer for native 4K, multi-shot storyboarding, and motion-transfer (Kling-led). Use when someone wants "native 4K video," "a multi-shot sequence / several cuts in one clip,"…

Proven narrative arc templates for product videos and ads. Use when: 'write script', 'video structure', 'narrative arc', 'scene plan', 'storyboard', '15 second video', '30 second video', '60 second…

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in…

Plan new YouTube videos with optimized titles, thumbnails, and hooks. Use when planning a video, writing or reviewing opening hooks, generating title and thumbnail concepts, or creating a…

Make a finished, postable video of your game, cut per platform and saved for review.

ComfyUI REST video: Wan 2.2 TI2V, HunyuanVideo, LTX.

Génération de rushes vidéo IA pour {{COMPANY_NAME}}, texte vers vidéo ou image vers vidéo, via un MCP multi-modèles (Seedance, Kling, Hailuo, Veo...). Spécification d'un plan en cinq aspects (sujet,…

ElevenLabs voice changer - transform any voice to a different voice while preserving speech content and emotion via inference.sh CLI. Models: eleven_multilingual_sts_v2 (70+ languages),…

电商运营在开展跨境电商或闲鱼捡漏业务时，若需解决选品难、上架繁琐等痛点，必用此技能！一键打通“爆品挖掘→1688采集→多平台上架→推广文案→短视频生成”全自动流水线，轻松实现端到端自动化，让开店运营效率翻倍。

选题全生命周期调度：记录选题、深化选题、选题推荐、立项分发（视频/图文/文章/实操长片/多形态）、发布归档。 Use when the user says 灵感xx, 想法xx, 记录选题, 这个可以做个选题, 先存着这个链接, 深化选题/深化一下xx, 给我N个选题, 帮我出选题, 选题推荐, 立项, 做成视频, 制作视频, 做成文章, 制作文章, 做成图文, 制作图文, 做成实操长片,…

Corrects speech-to-text transcription errors with dictionary rules and Claude's built-in AI (no external API key required); Native AI Correction is the default, Stage 1 alone is incomplete, and Stage…

用户要为准备发布的视频起标题、要几个标题候选、再来一批或照某个再来几个，或要写视频简介（视频页标题下的说明文字、章节列表、标签）时用。写给发布视频的人：吸引人，并且每句都由视频兑现。需要视频的转写。不用于给文章起标题等与视频无关的写作。

Download YouTube videos or extract audio using yt-dlp + ffmpeg in the Linux shell. Trigger when the user shares a YouTube URL and wants to download, save, rip, extract, or convert it — to video or…

Find, compare, and share details on physical places near the user or in a specified area, including restaurants, cafes, bars, hotels, parks, attractions, shops, and businesses with local services. Not…

Plan, script and review short-form videos (Instagram Reels, TikTok, YouTube Shorts) so they actually get watched, with hooks that do something extraordinary in the first 3 seconds. Use when the user…

Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master…

Optimize mobile app listings for discovery and conversion in Apple App Store and Google Play. Use when tasks involve ASO keyword research, title and subtitle optimization, screenshot and preview video…

Research YouTube topics, analyze competitor videos, deconstruct viral content, and query the YouTube Data API. Use when researching a video topic before planning, analyzing video transcripts for viral…

Fetches web articles/essays, extracts main text content, converts to speech using edge-tts (local, no API key needed), and concatenates into a single MP3 audiobook. Use when you need to convert online…

When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing…

Détourage vidéo local pour {{COMPANY_NAME}} — isole une personne d'une vidéo et produit un calque alpha exploitable au montage (remplacement de décor, incrustation sur fond généré). S'appuie sur…

ElevenLabs voice isolator - remove background noise and isolate vocals from audio via inference.sh CLI. Capabilities: noise removal, voice extraction, audio cleanup, background removal. Use for:…

Use the September 2026 image, video, speech and Avatar V adapters with explicit model/host contracts.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M…

Generate a pack of professional or aesthetic photos from a single reference image while preserving the exact identity of the person.

Use when evaluating macro trends through Shi Hanbing's interest-analysis (利益分析法) lens: trace who benefits from what policy, follow the money, and predict macro direction from incentive structures.

视频内容逐字稿提取专用 skill。Use when the user provides a 抖音 or 小红书 URL and asks for逐字稿、视频转文字、听写视频或提取口播内容。Only extract transcript content; do not use this skill as the production subtitle clock, and do not…

Local text-to-speech via sherpa-onnx (offline, no cloud)

Handle the comments under the user's own reels and posts - draft replies to the ones worth answering, sorted by which ones are. Use when the user pastes their comments, says "reply to these", "handle…

Generates In-App Event metadata templates for App Store Connect — event names, descriptions, badge types, image specs, and deep link configuration. Use when creating events for App Store visibility,…

Scan social platforms for top-performing content by engagement before you create anything. Use this skill when the user wants to see what content is winning in a niche, find viral content patterns,…

用户要把视频的转写或字幕翻译成另一种语言、做双语字幕，或更新原文改动后过期的译文时用：逐句翻译写成视频里的译文文档，再放到画面上、按需导出。有媒体时「翻译」默认指字幕翻译。不用于翻译与视频无关的文章、文档或一段纯文本；对话里没有视频或字幕、又看不出指的是什么时先问一次。

Read and write YouTube Music data using Python + ytmusicapi, authenticated via browser cookies obtained automatically with browser_use get_cookies — no manual copying required. Supports fetching…

Use when generating videos from images with DashScope Wan 2.7 image-to-video model (wan2.7-i2v). Use when implementing first-frame video generation, first+last frame interpolation, video continuation,…

Add voice & video calling to any iOS app FROM SCRATCH with the headless CometChat Calls SDK v5 (`CometChatCallsSDK`, via Swift Package Manager) — no UI Kit. init→login→generateToken→joinSession into a…

Find animation and video references on 1human, consult a human-agent shared library, and contribute public creations only with prior owner permission.