Coding & Development

Claude Code skill: fetch X/YouTube/local video → Whisper ASR → style-guided Claude translate → hard or soft subtitle render with frame QA.

Codex skill for terminology-aware video translation, bilingual ASS/SRT typesetting, hard-sub MP4 render, and measurable pixel/timeline QA.

CPU-only video subtitles: faster-whisper ASR → any-language translate → ASS burn or SRT/ASS export. No GPU. Claude/DSH agent skill with install + verify frame QA.

Automated video localization, multi-engine ASR, AI translation, FFmpeg release pipeline

yt-dlp best-quality single mp4 download (YouTube n-challenge + login wall). Companion step 1 before video-subtitle / video-dubbing.

AI-powered video subtitle & text overlay skill for Claude Code — Shorts/TikTok/Reels animated titles.

Chinese voiceover clone dubbing: IndexTTS2 speaker-clone + Demucs BGM keep + bi-directional video retime → cooked/<name>.dubbed.mp4 with bilingual burn. Step 3 of video-cooking.

Time-aligned TTS dub from a target-language SRT: Volcano (豆包) for Chinese, edge-tts for any language, atempo cue fit.

產出 AI 生圖／生影片的提示詞文字（不生成圖片本身）。透過一次一題的問答收斂需求，再依內建的八欄框架、角色一致性前綴、風格配方與負面清單，輸出可直接貼到 Gemini、Midjourney、千問、即夢等工具的完整提示詞。當使用者說「幫我做一張圖」「寫個提示詞」「做一支商品短影音」「這張圖怎麼生出來的」「我要這種感覺」，或丟出一張參考圖要仿作時觸發。即使使用者沒有說「提示詞」三個字，只要意圖是產出視覺素材、需要有人幫忙把想法寫成指令，就應該觸發。不負責呼叫生圖工具，也不做既有圖片的後製編輯。

Claude Code skill: records a product demo video of a real user flow in your own web app — transcribed from the real UI, recorded to mp4/gif with Playwright + ffmpeg.

Claude skills that drive the [Advibly](https://advibly.com) MCP to generate ad creative end to end: on-brand images, UGC-style video ads, talking-actor videos, and carousels.

Agent skill from carveragents/show-n-tell

Agent skill from ninime09/product-video-skill

Use when the user wants an image or video prompt written, improved, fixed, critiqued, converted to JSON, or turned into a brief — or mentions cinematic prompt, prompt bank, realism fix, \"looks fake / too AI\", camera or lighting or color-grade direction, camera movement, Kling, Seedance, Veo, Sora, Midjourney, image-to-video, start/end frame, shot list, continuity, or a UGC / influencer / talking-head prompt. A prompt-creation engine: turns a rough idea into a directed, production-ready prompt.

Video Forger turns plain-English descriptions into production-ready animated MP4s — product demos, pitch decks, social shorts, data visualizations, narrated explainers — via Remotion. Dashboard + sample videos in README.

**Page:** https://toolmonsters.github.io/gtm-skills-from-youtube/

Turn what the agent is currently working on into a short narrated demo video (TTS voice-over + screen/browser captures + lower-third captions → one H.264 .mov). Use when the user asks for a demo clip, walkthrough video, narrated recording, or 'make a video of this'. Interviews the user (audience, story, scenes), writes a scene spec, renders it scene by scene, and optionally posts to Slack.

<h1 align="center">Claude Skill Hub</h1>

> 抖音视频采集 → 转录 → AI 洗稿 → 视频生成，并把内容**自动发布到抖音（图文）与今日头条（文章）**

| Watches any video by URL (YouTube, Loom, a Zoom recording, a direct mp4) — not just the transcript, but what's actually SHOWN on screen. Frames are pulled by scene change (ffmpeg scene detection), not on a timer, so it doesn't miss graphics, demos, edits or b-roll. Audio: subtitles via yt-dlp first, Whisper as a fallback. Use this when the user writes /watch <url> or asks to "watch this video", "go through this recording/call/ lecture", "what's shown on screen". Triggers: /watch, watch this vi

Build or update the creative brief and brand guidelines for a video channel, before any editing or graphics happen. Use when starting a new video project or client channel, onboarding a client's brand, or when the operator says "set up the brief", "update the brand guidelines", "new client channel", "what's our creative direction for X", or asks why videos for a brand do not feel consistent. Interviews rather than guesses, and writes BRAND.md and CREATIVE-BRIEF.md that resolve-ai-edit reads on e

Process and share videos. Optimize for web, transcribe audio, add subtitles, burn captions, and share via S3 or local tunnel with short unique URLs. Triggers on: "process video", "share video", "share latest", "video status", "stop sharing", "copy link", "/video".

Dùng khi viết hoặc sửa prompt tạo video/ảnh AI (Veo 3, Google Flow, Kling, Runway, Sora, Midjourney, Hailuo, Luma): từ vựng chuẩn về góc máy, chuyển động camera, ánh sáng, bố cục, phong cách, màu, cảm xúc và công thức ghép prompt. Use when writing or fixing AI video/image prompts — cinematic camera angles, camera movement, lighting, composition, style, color grading, mood and a prompt formula.

Edit any video in DaVinci Resolve Studio 21.1+ through its native MCP server, build motion graphics as code, and learn from every correction. Handles YouTube long-form, Shorts and Reels, paid ads, testimonials, case studies and screen recordings, with the structure, aspect ratio, caption and loudness spec for each platform it runs on. Use when the operator says "edit this video", "rough cut this", "cut the silences", "make shorts from this", "cut this ad", "edit this testimonial", "make a reel",