Skills — le catalogue de compétences de vos agents

Compress videos for creators, ecommerce teams, and ad operators while balancing file size, upload compatibility, and visual quality. Use when a video is too...

Generate vertical hydraulic-press crushing shorts (WeryAI): text or object image to flatten/burst motion—destruction aesthetics and material contrast for sho...

Generate Feishu-native voice replies with a playable pause/resume bar by synthesizing text, converting it with ffmpeg to Ogg/Opus, and sending it as a voice...

Detects cats, dogs, and birds appearing in the target area; supports video stream and image detection, suitable for home pet monitoring scenarios. | 宠物检测技能，检测出目标区域内出现的猫、狗、鸟，支持视频流和图片检测，适用于家庭宠物监控场景

Build and test Solidity contracts with Foundry. Use when developing Ethereum contracts, writing Forge tests, deploying with scripts, or debugging with Cast/Anvil. Triggers on forge, cast, anvil, foundry.toml, *.t.sol, or *.s.sol.

Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu...

Design and evaluate A/B tests for different price points, discount levels, and bundle combinations to find the highest-converting offer structure.

Build sustainable creative practice routines for artistic skills. Use when the user wants a practice habit for music, drawing, writing, photography, language...

On-device multilingual text-to-speech using Supertonic (Supertone). Use when the user needs local/offline TTS, voice generation, speech synthesis, or convert...

美术素材生成完整工作流指引。生成游戏 UI 图标、角色概念图、运营海报等素材时使用。包含工具链说明、尺寸选择、提示词规范、工作流步骤。细节工具用法见对应子技能：codex-imggen（生图）、sprite-tools（切图/抠图）。

通用网页视频下载器。输入任意包含视频的网页URL，自动检测视频源（直链MP4/M3U8/分段流/Blob），抓取并下载为完整MP4文件。 支持搜狐、B站、优酷等分段流视频，也支持直接MP4/M3U8链接。 触发词：下载视频、download video、抓取视频、保存视频、视频下载、网页视频下载

Generate images and videos via ComfyUI on local GPU. Supports Flux text-to-image, Wan2.1 text-to-video, and image-to-video.

Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transpa...

Detailed Three.js 3D graphics reference covering scene setup, cameras, geometries, materials, lights, animations, controls, loaders, math utilities, and debu...

Anime.js adapter patterns for HyperFrames. Use when writing Anime.js animations or timelines inside HyperFrames compositions, registering animations on windo...

Polish and improve literature review for students and researchers

Search and analyze your own session logs using jq. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, w...

Control Discord from Clawdbot: send messages, react, post stickers, upload emojis, and more. And also 50+ models for image generation, video generation, text...

Design post-first-purchase onboarding sequences that educate customers, reduce returns, and drive repeat orders.

Expert visual design guidance for UI and UX of GUI apps and websites. Use when asked to design, critique, or improve interface visuals, color palettes, typog...

Use when the user wants to generate a video through the superouter, especially the `seedance-2.0-v1` omni-reference workflow with ordered assets, async submi...

Create, produce, and publish UGC-style short-form video reels at scale. Full pipeline: source UGC reaction hooks from DanSUGC, analyze app demos with Gemini...

Convert bookmarked videos from YouTube, X (Twitter), and other sites into a podcast RSS feed hosted on Cloudflare R2. Use when the user says things like "add...

捕获 iMac 摄像头画面（Photo Booth 窗口）。当用户想查看 iMac 的摄像头、打开摄像头、查看摄像头、打开监控、查看监控时说。