Media Claude Skills
3 032 media skills from 496 authors. They create and process images, video and sound. Half of them fit into 1 962 tokens or less — that is what one costs your context window when the agent loads it. 771 ship runnable scripts rather than instructions alone. 30 of them cannot work without an MCP server, most often rube. We also found 321 copies of these same skills sitting in other people's repositories — counted once here, not 321 times.
3 032 unique 496 authors 1 920 updated this month 173 from vendors
Generate attention-grabbing hooks for the first 3 seconds of videos. The hook determines if viewers stay or scroll. Creates multiple hook variations for A/B testing. Use when crafting video openings, improving retention, or creating scroll-stopping content for YouTube, TikTok, or Reels.
将视频脚本转换为更适合实际录制的口语化表达，去除书面化语言，增加自然感和亲和力。当用户提到"视频脚本"、"录制"、"口语化"、"自然一点"、"像说话一样"、"太书面了"时使用此技能。
Write engaging video scripts for YouTube, TikTok, and other platforms. Creates complete scripts with hooks, main content, and CTAs. Supports various formats including tutorials, vlogs, reviews, explainers, and storytelling. Use when creating video scripts, writing YouTube content, or planning video structure.
Optimize video titles for maximum click-through rate (CTR) and YouTube/TikTok SEO. Generates multiple title variations balancing curiosity, keywords, and platform best practices. Use when naming videos, improving CTR, or A/B testing titles.
Convert video clips to optimized GIFs with speed control, cropping, text overlays, and file size optimization. Create perfect GIFs for social media, documentation, and presentations.
Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions. Writes video details and transcription into structured markdown file.
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.createConnection()` / `connect()`, Flux models, and turn events like `TurnInfo`. Use `deepgram-js-speech-to-text` for standard v1 ASR and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", and "listen.v2".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via `client.speak.v1.audio.generate` and streaming WebSocket via `client.speak.v1.createConnection()` / `connect()`. Use `deepgram-js-voice-agent` when you need full-duplex STT + LLM + TTS instead of one-way synthesis. Triggers include "TTS", "text to speech", "speak", "aura", "streaming TTS", and "speak.v1".
Use when writing or reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers `client.agent.v1.createConnection()` / `connect()`, `sendSettings`, `sendMedia`, runtime updates, event handling, and function-call responses. Use `deepgram-js-text-to-speech` for one-way synthesis, `deepgram-js-speech-to-text` or `deepgram-js-conversational-stt` for transcription only, and `deepgram-js-management-api` for project/model admin rather than live agent runtime. Triggers include "voice agent", "agent converse", "full duplex", "barge-in", "function calling", and "agent.v1".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".
Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribeUrl` / `transcribeFile` (REST) plus `client.listen.v1.createConnection()` / `connect()` (WebSocket). Use `deepgram-js-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-js-conversational-stt` for Flux turn-taking on `/v2/listen`, and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "transcribe", "speech to text", "STT", "listen.v1", "nova-3", "live transcription", and "websocket transcription".
| [책임 경계] 상품 이미지·영상 풀스택 파이프라인 오케스트레이터. 캐릭터 일관성(선택) → higgsfield-image(Soul) → higgsfield-video(DOP) → 채널 규격 변환(Pillow 자체 처리) 체인을 단일 자연어 입력으로 자동 호출. 한국 이커머스 셀러가 "상품 이미지·영상 만들어줘" 한 줄로 풀세트 산출. "상품 이미지 만들어줘", "상품 영상 풀세트", "이미지부터 영상까지 한 번에", "상세페이지 이미지·영상 묶음", "비건 세럼 이미지·영상 패키지", "캐릭터 + 이미지 + 영상 한 번에", "이커머스 비주얼 파이프라인", "Higgsfield 풀세트 호출". 페어 스킬 detail-page-image(13섹션 합성 PNG)와 명확히 구분 — 본 스킬은 모델 체인 오케스트레이션, 페어는 단일 합성. ai-slop-reviewer 체이닝 제외 (이미지·영상 산출물).
> 한국 이커머스 상세페이지 13섹션 이미지를 자동 생성하고 1080×12720 단일 PNG로 합성하는 스킬입니다. "상세페이지 이미지 만들어줘", "13섹션 합성 이미지", "상폐 이미지", "1080 12720 합성"처럼 말하면 됩니다. detail-page-copy의 13섹션 카피와 사용자 상품 사진을 받아 섹션별 이미지 프롬프트를 작성하고, Pillow 기반 자체 합성 스크립트(scripts/compose.py)로 1080×12720 세로 합성 PNG를 만듭니다. 외부 패키지 설치 불필요 — 합성 로직은 cowork에 자체 구현되어 있습니다.
> 사용자가 제공한 상품 사진을 분석하여 ProductDNA를 추출하고, 13섹션 상세페이지에 부족한 컷을 식별, 추가 촬영을 위한 구체적인 브리프를 작성해주는 스킬입니다. "상품 사진 분석해줘", "촬영 브리프 만들어줘", "부족한 컷 알려줘", "어떤 사진이 더 필요해?"처럼 말하면 됩니다. 형태·소재·색상·시그니처 앵글·포지셔닝(mass/premium_indie/luxury)을 추출하고, 13섹션별 사용 가능한 컷 매핑 + 추가 촬영 권장 리스트를 산출합니다.
| 통합 오디오 생성 스킬. ElevenLabs MCP 기반 TTS(32개국어), 보이스 클로닝(1분 샘플), 다국어 더빙(립싱크), 효과음 생성을 지원. "목소리 생성", "TTS", "음성 합성", "보이스 클로닝", "더빙", "나레이션", "효과음", "AI 음성" 요청 시 사용.
| OpenAI GPT-image-2 모델 전용 이미지 프롬프트 텍스트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정 라운드로 컨텍스트를 수집하고, OpenAI Cookbook 공식 6-Block 구조(Subject·Action·Scene·Composition·Lighting·Style&Text)에 매핑해 ChatGPT·OpenAI API에 복붙 가능한 프롬프트를 출력합니다. 보너스로 같은 입력에 대한 Gemini 3 Pro Image · Midjourney v8.1 프롬프트도 함께 생성해 모델 간 비교·이식이 즉시 가능합니다. 이미지 자동 생성은 페어 스킬 higgsfield-image(Higgsfield MCP)를 사용하세요. 본 스킬은 프롬프트 텍스트 산출 전용입니다.
| Google Gemini 3 Pro Image (a.k.a. Nano Banana Pro) 전용 이미지 프롬프트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정으로 컨텍스트를 수집해 Google AI Developers 공식 가이드의 5-component 구조([Subject+Adj] doing [Action] in [Location]. [Composition]. [Lighting]. [Style]. [Constraint/Text])로 변환합니다. Google AI Studio · Vertex AI · Gemini 앱에 그대로 복붙 가능. 보너스로 GPT-image-2(6-Block) · Midjourney v8.1(키워드+파라미터) 프롬프트도 동시 출력해 모델 간 비교·이식이 가능합니다. 이미지 자동 생성은 페어 스킬 higgsfield-image(Higgsfield MCP, Nano Banana Pro 포함)를 사용하세요. 본 스킬은 프롬프트 텍스트 산출 전용입니다.
| Higgsfield MCP 기반 AI 이미지를 자연어 요청 한 줄로 생성합니다. Soul·Soul 2.0·Soul Cinema·Nano Banana·Nano Banana Pro·GPT Image·GPT Image 2·Seedream 4.0·Flux Kontext·Wan 2.2 Image·Wan 2.5 11개 공식 이미지 모델과 캐릭터 일관성(Soul Characters), 스타일 프리셋, 해상도(720p/1080p/2K/4K), 시드 고정, 비동기 잡 폴링까지 처리한 완성 이미지를 산출합니다. 실제 이미지 생성 요청 시 Higgsfield MCP가 연결돼 있으면 이 스킬을 사용하세요 (프롬프트만 필요하면 moai-media의 *-prompt 스킬).
| Midjourney v8.1 (2026.03 Alpha) 전용 이미지 프롬프트 빌더. 사용자 자연어 한 줄 + AskUserQuestion 프리셋·미세조정으로 컨텍스트를 수집해 Midjourney 공식 Parameter List 기반 키워드+`--파라미터` 형식으로 변환합니다. Discord `/imagine` 또는 alpha.midjourney.com에 그대로 복붙 가능. `--sref`/`--oref`/`--cw`/`--p`/`--hd`/`--q 4`/`--style raw`/`--no`/`--c`/`--s` 모두 지원. 보너스로 GPT-image-2(6-Block) · Gemini 3 Pro Image(5-component) 프롬프트도 동시 출력합니다. Midjourney는 공식 API 자동화가 제한적이므로 본 스킬은 프롬프트 텍스트만 산출하고, 실제 생성은 사용자가 Discord 또는 web alpha에서 직접 실행합니다.
| Higgsfield MCP 기반 AI 영상을 자연어 요청 한 줄로 생성합니다. Seedance 2.0·Seedance Pro·Cinema Studio 3.5·Kling 2.1 Master·Kling 2.5 Turbo·Kling 3.0·Kling Avatars 2.0·MiniMax Hailuo 02·Google Veo 3·Sora 2·Wan 2.5 11개 공식 영상 모델과 6가지 비디오 프리셋(UGC·Unboxing·Product review·Hyper motion·TV spot·Wild Card), 캐릭터 일관성(Kling Avatars 2.0), 비동기 잡 폴링까지 처리한 완성 영상을 산출합니다. 실제 영상 생성 요청 시 Higgsfield MCP가 연결돼 있으면 이 스킬을 사용하세요.
| 강연·강의·세미나 본문 마크다운을 입력받아 (1) NotebookLM Studio에 그대로 붙여 넣을 슬라이드 데크 생성 프롬프트와 (2) 슬라이드별 나노바나나(Gemini 3 Pro Image, a.k.a. Nano Banana Pro) 5-Component 이미지 프롬프트를 동시 산출하는 prompt-builder 스킬. NotebookLM Studio의 공식 4축(Format/Length/Output language/Prompt)을 정확히 매핑하고, 슬라이드별 시각 자료는 Google DeepMind 공식 가이드의 5-Component 구조(Style·Subject·Setting·Action·Composition)에 따라 작성한다.
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
通过 fal.ai MCP 实现统一的媒体生成——图像、视频和音频。涵盖文本到图像（Nano Banana）、文本/图像到视频（Seedance、Kling、Veo 3）、文本到语音（CSM-1B），以及视频到音频（ThinkSound）。当用户想要使用 AI 生成图像、视频或音频时使用。
AI辅助的视频编辑工作流程，用于剪辑、构建和增强实拍素材。涵盖从原始拍摄到FFmpeg、Remotion、ElevenLabs、fal.ai，再到Descript或CapCut最终润色的完整流程。适用于用户想要编辑视频、剪辑素材、制作vlog或构建视频内容的情况。
视频与音频的查看、理解与行动。查看：从本地文件、URL、RTSP/直播源或实时录制桌面获取内容；返回实时上下文和可播放流链接。理解：提取帧，构建视觉/语义/时间索引，并通过时间戳和自动剪辑搜索片段。行动：转码和标准化（编解码器、帧率、分辨率、宽高比），执行时间线编辑（字幕、文本/图像叠加、品牌化、音频叠加、配音、翻译），生成媒体资源（图像、音频、视频），并为直播流或桌面捕获的事件创建实时警报。
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
Analyze construction site photos to track progress, detect safety issues, and compare against BIM models using computer vision.
Generate images and visualizations from Revit/IFC files without BIM software. Python-based noBIM tool for batch processing.
Analyze field progress photos. Catalog, tag, and compare against planned progress.
Digital punch list management for construction project closeout. Track deficiencies, assign corrections, photo documentation, and completion verification.
Extract data from construction images using AI Vision. Analyze site photos, scanned documents, drawings.
Automate construction photo report generation using n8n with AI-powered image analysis.
Build a complete project management system with Telegram bot, task distribution, and photo reports using n8n. Based on DDC Project Management repository.
Convert voice recordings to structured construction reports. Field workers speak, AI transcribes and formats. Supports daily reports, safety observations, progress updates.
AI-powered construction defect detection using computer vision. Identify cracks, spalling, corrosion, and other defects in concrete, steel, and building components from images and video.