Skill rating

Create realtime **passthrough** AI avatar sessions (LiveKit WebRTC — you bring STT/LLM/TTS and publish audio), view-only viewer tokens for multi-viewer watch, and offline lip-sync avatar videos using

Use when the user needs video/audio/subtitle translation, material and task management, script editing, or export via VMEG in an AI coding assistant or OpenClaw agent. Requires VMEG Remote MCP (OAuth

Fix slides that are documents in landscape mode — the one-point-per-slide rule, the projection-vs-reading fork that decides density, the text diet (headlines and evidence, prose to notes), and the gla

📐 詹明明·口播稿写作 ——口播稿协作写作技能（知识付费口播为主形态）。三类脚本选型 + 从内容单元装配 + 逐段共创，不一键成稿。 触发方式：/zmm-script、/写口播、/写稿、/zmm-写稿、「写个口播稿」「帮我把这个题写出来」「知识付费口播」「写条视频文案」 Collaborative koubo (talking-head) script writing: script-type

Integrate Shengwang products: ConvoAI voice agents, RTC audio/video, RTM messaging, Cloud Recording, and token generation. Use when the user mentions Shengwang, 声网, ConvoAI, RTC, RTM, voice agent, AI

Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.

Chanjing AI creation Open API client: submit image/video tasks, poll task status, list and get tasks, and optionally download outputs when the user runs download_result.py. Reads and writes local cred

Capture product tour video segments using browser automation and screen recording. Coordinates timing between UI interactions and narration cues for demo and walkthrough videos.

This skill should be used when the user wants to compress a PowerPoint (.pptx) file by reducing the size of embedded videos and large images. It handles the complete workflow of extracting media from

Re-skin any everyday clip concept into neon-drenched, high-tech, augmented urban futures using WeryAI Seedance 2.0 only. Use when you need TikTok-style vertical cyber aesthetics, holographic UI, chrom

Use when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a time-aligned TTS voice dub. Routes by voice ID — Volcano (豆包) TTS for Chinese, e

Search 699pic enterprise photo/video assets, check whether an asset was already downloaded, inspect download records, and generate download links through the local 699pic OpenAPI integration. Use when

Turn a product image into a short ad or promo video, the highest-polish commercial outcome: a hero product still in motion. Use when the user says "make a video ad for this product", "turn this produc

Tell a short story across several cuts in one video call, not one continuous take. Use when the user says "a reel that cuts between shots", "a few beats in one clip", "wide then close-up then end on…"

Fetch YouTube video transcripts, subtitles, and generate summaries. Use when the user wants to extract text from a YouTube video, download subtitles (similar to downsub.com), get timestamped transcrip

Upscale ordinary beats into trailer-scale drama: anamorphic mood in vertical, bold contrast, heroic pacing—WeryAI Seedance 2.0 only. Use when you need hype reels, faux movie poster motion, or image-to

Helps choose the right fal.ai model before API calls. Provides quick decision matrix for video generation (text-to-video, image-to-video), image editing (object removal, relighting, style transfer, vi

Track YouTube creators and analyze video content. Paste a YouTube link to get an AI-powered breakdown (summary, key points, why it matters), then optionally follow the creator for new upload notificat

When the user asks to 策划/构思/设计/写脚本/画分镜 for a video project — e.g. '帮我策划一个广告创意' '这个产品演示视频怎么拍' '帮我写科幻短片的分镜脚本' '给我这个品牌TVC的美术方向'。Not for actual video rendering/compositing or AI image/video generation.

Generate images and videos via WangYi Banana API (nano-banana, SORA2). Supports text-to-image, image-to-image, text-to-video, image-to-video, and character creation for short video production.

Transform any everyday scene, action, or subject into a fantastical, magical, ritual-rich vertical video using WeryAI Seedance 2.0 only. Use when you need festival wonder, fairy-tale spectacle, otherw

Push any scene toward gothic mystery: low key light, candles, smoke, black-gold-crimson palette, ceremonial poses—WeryAI Seedance 2.0 only. Use when you need suspense shorts, cult-ritual vibe, castle

Bathe any moment in sacred celebration: gold-white light, confetti blessings, coronation slow-mo—WeryAI Seedance 2.0 only. Use when you need wedding-grade uplift, award-show glow, or gratitude vertica

Soften any idea into creamy pastel dreamscapes: gentle bloom, cute proportion cues, sugar-glow particles—WeryAI Seedance 2.0 only. Use when you need healing cute fantasy, cotton-candy skies, or wholes

Download podcast audio from RSS feeds and transcribe to text using AuralWise API. This skill should be used when the user wants to download podcast episodes, convert podcast audio to text transcripts,