Skills — le catalogue de compétences de vos agents

Design concepts and test their application composition

Create or edit books with the Enoch Book Engine, including strict B5 pages, inline SVG diagrams, and mandatory screenshot-based visual QA.

抖音视频蒸馏 Skill。用户提供抖音链接、视频文件或要求把短视频提炼成知识卡片、摘要、时间线、证据、行动项、Wiki 内容或第二大脑资料时使用；也适用于"帮我把这个视频真正变成可检索知识"等未明确说蒸馏的请求。

Turn text, dialog, diary entries, photo notes, or knowledge notes into a comic, picture book, infographic, or hybrid comic+diagram — storyboard and panel plan first, then panel-by-panel rendering, with style presets and consistent characters. 把文字、对话、日记、照片说明或知识内容转成漫画/绘本/信息图，先出分镜再逐格出图，角色一致、可只改单格。Use when 想画故事、对话变漫画、概念变信息图、旅行日记配图、改某一格而不重画整页。Not for 纯文字写作、模仿在世画家的标志性风格、复制受版权保护的素材。

视频分镜演示动画生成技能：每个镜头产出一个独立 HTML（统一播放器底盘+每页不同视觉风格），覆盖风格分配、双角色立绘素材、口播时间轴对齐、批量截图质检与 index 总览的完整工具链。适用于制作技术实测、产品发布、课程、叙事类分镜演示视频。

Turn a feature idea, conversation context, or rough notes into researched, detailed, dependency-ordered checkbox tasks appended to the project's roadmap/backlog file — exactly the format goal-runner consumes, so a fresh unattended session can execute them. Grounds every task in the actual codebase before writing it (grep/read or Explore scouts; think-like-fable rigor if installed), puts what + done-when on the checkbox line with verified files, acceptance criteria, and a verification command in plain sub-bullets, and labels assumptions. Appends to the existing ROADMAP.md/BACKLOG.md/TODO.md; wh

Open Pinterest in the user's Brave browser and take the user to the Pinterest homepage. Use when the user asks to open, visit, or go to Pinterest.

Open 773 LABS to browse and discover ready-made and custom 3D models and 3D printed products. Use when the user wants to find, browse, get, or explore a 3D model or 3D printed product.

Provide a detailed specification for writing YASim XML files.

Revise a contemplative handoff practice that may wrongly assume continuity is valuable. Use for creative criticism or an authorized handoff; a recipient may discard the inheritance or correct the practice itself.

Analyze portrait photos to recommend the most flattering hairstyle based on face shape, facial features, hair texture, and personal style. Use when the user uploads a portrait/headshot photo and asks for hairstyle recommendations, haircut advice, or wants to see how they would look with a suggested

Turn a short video that already worked into your own version. Paste the link and this viral video teardown and short-video remake workflow reads the reference itself on TikTok, Douyin, Xiaohongshu, Instagram, YouTube, or X — caption, author, visible metrics, comments, and on YouTube the full transcript — or work from a file, screenshots, or your own description instead. It breaks the clip into its hook, body beats, and call to action, names the script pattern behind it, scores what carried the performance, then rewrites that structure around your product or topic — delivering a shot list with

Turn a written hall window list into one hall guide voice clip per labeled cue. This window list voice studio records each hall window audio and window cue voice from the list the hall already wrote, then delivers 8 to 20 hall guide voice pack files. Use it for hall guide clip packs that keep one window on each clip.

Turn each photo into a quiet handmade editorial poster

把概念模型映射为模块单体代码：concept→模块、sync→mediator

五维审计存量工程：漂移、边界、判据、组合、依赖，只读输出修复路由

把确认的概念模型转录为 PRD 规格：总体 + 每概念 + 按 flow 的 syncs

Builds targeted journalist and media contact lists from Twitter/X using apidojo's Twitter scrapers on Apify. Triggers when the user asks to: find journalists covering a specific beat or topic on Twitter, build a media outreach list from Twitter, identify reporters writing about an industry, find editors or writers at specific publications on X, create a PR contact list from Twitter, discover freelance journalists in a niche, or compile a list of media contacts for a press release or story pitch. Returns name, handle, publication affiliation from bio, follower count, and recent article topics.

Finds Twitter Spaces hosts in a specific topic area using apidojo's Twitter scrapers. Triggers when the user asks to: find Twitter Spaces hosts in a niche, discover people who run Twitter Spaces about a topic, find Spaces hosts to collaborate with or get featured on, identify active Twitter Spaces communities in an industry, find hosts running regular business or tech Spaces on Twitter, build a Twitter Spaces outreach list for thought leadership, or discover Twitter audio show hosts in a professional category. Returns host handle, Space topic focus, frequency signals, co-host network, and audi

提取抖音音频、云端生成字幕并总结重点与行动项

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "search videos with text".

Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, produce grouped grounding phrases tied to bboxes, run a double-check verification pass on grounding expressions, auto-label traffic / scene images for referring datasets, or run the image_referring_expression pipeline. Triggers include 'referring e

Build an original indie game OST pack of 8 to 15 instrumental tracks for title, explore, battle, shop, and victory. This game soundtrack studio and game BGM generator writes loop-friendly game music you own and can use commercially, then delivers a labeled soundtrack you can audition in-engine. Use it as a game music pack for indie game OST, game background music, game BGM, battle music, explore music, shop music, and original game soundtrack work.

无字幕视频转写兜底方案。当视频（YouTube/Bilibili 等）没有字幕、字幕接口被禁或拉取失败时，用 yt-dlp 下载音频 + faster-whisper 本地转写，输出带时间戳的完整文稿。触发词：视频没字幕、转写视频、字幕被禁、whisper 转写、提取语音内容。