Media AI Skills

Google Text-to-Speech (gTTS) for converting text to audio. Use when creating audiobooks, podcasts, or speech synthesis from text. Handles long text by chunking at sentence boundaries and concatenating…

Analyze, recreate, align, and verify reference-video motion. Use when the user asks to recreate, copy, match, align, pixel-align, or compare a video; when a HyperFrames or Remotion remake is judged…

Generate audio replies using TTS. Trigger with "read it to me [URL]" to fetch and read content aloud, or "talk to me [topic]" to generate a spoken response. Also responds to "speak", "say it", "voice…

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

Create a Seedance 2.0 prompt for a rough hand-drawn luminous entity that physically contacts a live-action space, continuously transforms while remaining traceable, escapes through adjacent geography,…

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

从 YouTube 视频链接提取字幕并转换为中文文字稿。支持自动生成字幕和手动字幕。 使用场景：(1) 用户提供 YouTube 链接并要求提取字幕/文字稿，(2) 用户要求将 YouTube 视频内容转为文字， (3) 用户说"帮我把这个 YouTube 视频转成文字"或类似请求。 触发词：YouTube 字幕、视频转文字、提取字幕、YouTube transcript、视频文字稿。

Analyze candidate models before adapter implementation. Determine model implementation source (transformers or model-local), structural features, layer-by-layer loading requirements, and MoE fused…

Generate images with Google Gemini native image models via inference.sh CLI. Models: Gemini 3 Pro Image, Gemini 2.5 Flash Image. Capabilities: text-to-image, image editing, multi-image input.…

Generate speech audio from text using HeyGen's Starfish TTS model. Use when: (1) Generating standalone speech audio files from text, (2) Converting text to speech with voice selection, speed, and…

OpenAI Text-to-Speech API for high-quality speech synthesis. Use for generating natural-sounding audio from text with customizable voices and tones.

Render, preview, validate, and burn consistent production subtitles from QC-passed real-timestamp caption artifacts. Use for AI-video production, washed-video production, IndexTTS2 explainers,…

绿幕抠像 / 换背景 / 合成：把绿幕（或蓝幕/指定色）拍摄的前景人物抠出来，合成到新背景——图片、视频、纯色或前景自身模糊。当用户说 绿幕、抠像、抠图换背景、去绿幕、chromakey、绿幕合成、换背景、蓝幕、把绿幕背景换掉、人物抠出来、绿布 时使用。基于 shared/scripts/chromakey.py（ffmpeg chromakey + despill）。与…

Create a Seedance 2.0 prompt for a rough hand-drawn luminous entity that physically contacts a live-action space, continuously transforms while remaining traceable, escapes through adjacent geography,…

The OpusClip craft skill — turn long video (podcasts, webinars, interviews, streams) into publishable short clips with AI candidate-finding, honest triage, and a human-reviewed pipeline. Use when…

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

When the user needs TikTok ad video concepts, formats, hooks, or a 6-ad testing matrix for app install campaigns. Use when the user mentions "TikTok ad ideas", "what videos should I run", "UGC ad…

Use quando o usuário entrega um vídeo, stream, gravação de tela ou reunião, pergunta sobre um momento ou vídeo já indexado, precisa de OCR/transcrição com timestamps, quer extrair estrutura ou bug…

Generate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Capabilities: text-to-image, image editing, LoRA styles, multi-image…

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for image, audio, video, document, and container steganography. Use when the user asks to inspect metadata, alpha or…

Save ideas, observations, content topics, projects, and convictions in ~/code/ideas. Use when the user asks to capture an idea or insight. Adds to idea backlogs, not reminders or tasks.

Extract frames or short clips from videos using ffmpeg.

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

Plan Seedance 2.0 music-video clips where performance, camera, scene changes, spatial lyric typography, and transitions respond to a locked music window. Use for 4–15 second hooks or longer multi-clip…

Generate cloned narration for the content workspace. Use local IndexTTS2 with the canonical lossless Pluviobyte reference for every local video, voice audition, digital-human narration, and…

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow,…

使用阿里云通义听悟进行云端音频/视频转录。本技能应在用户需要云端语音转文字、长音频转录、本地 ASR 不可用或需要更高精度时使用。不适用于无网络环境或需要完全离线的场景。

Search and download GIFs from Tenor using curl. No dependencies beyond curl and jq. Useful for finding reaction GIFs, creating visual content, and sending GIFs in chat.

Plan Seedance 2.0 music-video clips where performance, camera, scene changes, spatial lyric typography, and transitions respond to a locked music window. Use for 4–15 second hooks or longer multi-clip…

The Pinterest pin design skill -- the visual half that pairs with pinterest-seo's keyword layer. Use when someone wants to design a pin, a Pinterest pin image, a pin text overlay, fresh pin variations…

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

Turn a narration line, knowledge point, opinion, story beat, or abstract concept into a Seedance 2.0 editorial paper-collage clip with a clear visual metaphor, approved final composition, tactile…

Extract key frames (I-frames) from video files using FFmpeg to identify scene changes and important moments.

影片与视频编辑及自媒体创作者在处理多媒体素材时，当需批量转换音视频或图像格式、调整分辨率及压缩文件时必用。一键调用底层工具自动完成转换与压缩，高效输出符合预期的媒体文件，大幅节省手动处理时间。

Transcribe audio segments to text using Whisper models. Use larger models (small, base, medium, large-v3) for better accuracy, or faster-whisper for optimized performance. Always align transcription…

Audit PowerPoint (.pptx) decks for slide count, text density, embedded images and fonts, hidden slides, speaker notes, and animation density. Use when reviewing a board deck, sales deck, or conference…

When you want to capture into, compile, query, lint, or connect your personal Second Brain. Wraps the Karpathy LLM Wiki schema (Obsidian or any markdown vault) — raw/ (unprocessed sources), wiki/…

Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration.…

Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

Guided setup of the tools the design harness can use — image/video generation channels, browser, encoders. Detects what the user already has, explains pros/cons/costs, asks instead of instructing, and…

Use when improving Xiaohongshu shop conversion rates, optimizing product pages for sales, increasing purchase completion rates, reducing cart abandonment, or analyzing and improving the purchase…

基于 Seedance 2.0 模型的 AI 视频生成器，输入关键词/描述文案即可生成 MP4 视频。支持文生视频、分辨率/比例/时长控制、预置虚拟人像引用。使用 Seedance 视频生成、AI 视频、text-to-video 时调用此 Skill。

Use to design, run, and synthesize customer feedback programs tied to journey stages.

Turn a narration line, knowledge point, opinion, story beat, or abstract concept into a Seedance 2.0 editorial paper-collage clip with a clear visual metaphor, approved final composition, tactile…

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

When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn…

Use when designing or testing accessible gameplay, remapping, visual/audio alternatives, difficulty assists, localisation/internationalisation, cultural review, chat/community safety, reporting,…

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…

Advanced Content Security Policy bypass techniques. Use when XSS or data exfiltration is blocked by CSP and you need to find policy weaknesses, trusted endpoint abuse, nonce leakage, or exfiltration…

Combine visual features (face detection, lip movement analysis) with audio features to improve speaker diarization accuracy in video files. Use OpenCV for face detection and lip movement tracking,…

Convert text to spoken audio and transcribe audio to text, across multiple speech providers (OpenAI, ElevenLabs, Deepgram, Groq, Sarvam AI).