Media skills

视频去重工具。使用精确匹配（MD5哈希）在文档级别删除重复视频样本。 当用户提到视频去重、删除重复视频、清理重复视频等需求时使用此skill。 即使用户没有明确说出"视频去重"，只要任务涉及从包含视频的数据中删除重复视频， 就应该使用此skill。

The English summary is being prepared. Showing the original description.

Ray分布式视频去重工具。使用精确匹配（MD5哈希）在文档级别删除重复视频，基于Ray分布式框架。 当用户提到视频去重、删除重复视频、分布式去重、大规模视频去重等需求时使用此skill。 即使用户没有明确说出"Ray"或"分布式"，只要任务涉及大规模视频去重处理， 就应该使用此skill。

The English summary is being prepared. Showing the original description.

图像NSFW内容检测过滤器。过滤器保留图像具有低nsfw分数的样本。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到图片安全检测、NSFW过滤、不良内容过滤、图片审核、图像内容过滤等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像对相似度过滤器。过滤器将图像之间具有相似性的图像对保持在特定范围内。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到图像相似度检测、图像对过滤、双图相似度、图片相似度筛选、图像pair过滤等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像人脸面积比例过滤器。过滤以保持面面积比在特定范围内的样本。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到过滤图片、人脸占比、面部面积比例、图片人脸区域筛选、按人脸占比过滤等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像文件大小过滤器。保留图像大小 (以字节/KB/MB/... 为单位) 在特定范围内的数据样本。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到图像文件大小过滤、图片大小筛选、图像尺寸KB/MB过滤、按文件大小过滤等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像形状过滤器。过滤器保持样品的图像形状 (w，h) 在特定范围内。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到图像尺寸过滤、图片宽高筛选、图像分辨率过滤、按图片大小过滤、图像形状限制等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像去重工具。使用图像哈希精确匹配在文档级别删除包含重复图像的样本。 当用户提到图像去重、删除重复图片、图片去重、清理重复图像等需求时使用此skill。 即使用户没有明确说出"图像去重"，只要任务涉及从包含图像的数据中删除重复图片， 就应该使用此skill。

The English summary is being prepared. Showing the original description.

图像人脸数量过滤器。过滤以保持样本的面数在特定范围内。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到过滤图片、识别人脸、人脸数量检测、图片人脸筛选、按人脸数量过滤等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像美学过滤器。过滤美学评分不在指定范围内的图像样本。 当用户提到图像美学、图像质量过滤、图片评分筛选、图像质量评估、过滤低质量图像等需求时使用此skill。 即使用户没有明确说出"美学评分"，只要任务涉及根据图像美学质量来筛选数据， 就应该使用此skill。

The English summary is being prepared. Showing the original description.

图像长宽比过滤器。过滤图像长宽比不在指定范围内的样本。 当用户提到图像长宽比、图片比例过滤、图像尺寸筛选、图像宽高比等需求时使用此skill。 即使用户没有明确说出"长宽比"，只要任务涉及根据图像宽高比来筛选数据， 就应该使用此skill。

The English summary is being prepared. Showing the original description.

图像文本相似度过滤器。过滤器将图像和文本之间的相似性保持在特定范围内。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到图像文本相似度过滤、图片文字相似度、文图相似度检测、图文相关性过滤等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像文本匹配过滤器。过滤器将图像和文本之间的匹配分数保持在特定范围内。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到图像文本匹配过滤、图片文字匹配度、文图匹配检测、图像文本相关性过滤等需求时使用此skill。

The English summary is being prepared. Showing the original description.

图像水印过滤器。过滤器以保持其图像没有水印的样本具有高概率。 本SKILL使用依赖data_juicer，请在调用前安装好python环境并安装data_juicer，你可用以下指令进行安装： pip install py-data-juicer 当用户提到图像水印检测、图片无水印过滤、水印去除、检测图片水印等需求时使用此skill。

The English summary is being prepared. Showing the original description.

LinkedIn 岗位发现与匹配排序。根据用户给的一份种子 JD 和简历，提取目标岗位画像，自动生成多组 LinkedIn Jobs 搜索，采集、去重并按证据给岗位分层，最终输出可直接投递的 shortlist。用户说‘帮我找工作’、‘在 LinkedIn 搜适合我的岗位’、‘找相似职位’、‘根据简历推荐岗位’、‘job search’、‘find jobs like this’时必须使用。只搜索和推荐，不自动投递、不代替用户登录、不绕过验证码。

The English summary is being prepared. Showing the original description.

Implements media and file management components including file upload (drag-drop, multi-file, resumable), image galleries (lightbox, carousel, masonry), video players (custom controls, captions, adaptive streaming), audio players (waveform, playlists), document viewers (PDF, Office), and optimization strategies (compression, responsive images, lazy loading, CDN). Use when handling files, displaying media, or building rich content experiences.

The English summary is being prepared. Showing the original description.

Generate HeyGen presenter videos via the v3 Video Agent pipeline — handles Frame Check (aspect ratio correction), prompt engineering, avatar resolution, and voice selection. Required for any HeyGen video generation. Replaces deprecated endpoints with v3. Use when: (1) generating any HeyGen video (via API or otherwise), (2) sending a personalized video message (outreach, update, announcement, pitch, knowledge), (3) creating a HeyGen presenter-led explainer, tutorial, or product demo with a human face, (4) "make a video of me saying...", "send a video to my leads", "record an update for my team", "create a video pitch", "make a loom-style message", "I want to appear in this video", "generate a HeyGen video", "make a talking head video". Accepts avatar_id from heygen-avatar for identity-first HeyGen videos, or uses a stock presenter. Returns video share URL + HeyGen session URL for iteration. Chain signal: when the user wants to create/design an avatar AND make a video in the same request, run heygen-avatar first, then return here. Conjunctions to watch: "and then", "and immediately", "first...then", "X and make a video", "design [presenter] and record" = always CHAIN. If the user provides a photo AND wants a video, route to heygen-avatar first. NOT for: avatar creation or identity setup (use heygen-avatar first), cinematic footage or b-roll without a presenter, translating videos, TTS-only, or streaming avatars.

The English summary is being prepared. Showing the original description.

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

The English summary is being prepared. Showing the original description.

Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.

The English summary is being prepared. Showing the original description.

Plan short-form video, vlog, travel, lifestyle, documentary, or cinematic social video scripts by negotiating duration, choosing a story arc and visual style, then splitting the film into timed scenes of 4-15 seconds. Use this skill whenever the user asks for a video plan, short video plan, scene breakdown, montage plan, travel video script, TikTok/Reels/Shorts storyboard, or cinematic short-form narrative, even if they only describe a loose theme or destination.

The English summary is being prepared. Showing the original description.

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

The English summary is being prepared. Showing the original description.

Use when the user wants to turn bullet points, rough notes, research findings, or a page outline into an image-only consulting-grade PPT deck, especially standalone report exhibits, live-presentation concept slides, full-slide PNGs, or PNG plus image-only PPTX. Use when editable PPTX or code-rendered slide pages are not allowed.

The English summary is being prepared. Showing the original description.

MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native image_generation server tool vs the generate_image tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.

The English summary is being prepared. Showing the original description.

Create 3D models with Meshy AI from text or images, then texture, remesh, rig, animate, convert, resize, or prepare them for 3D printing (printability repair, multicolor 3MF, split into parts, slicer handoff). Use when the user asks for a 3D model, game asset, rigged character, animation, AR/USDZ file or 3D print, or wants to view, convert, download another format of, or optimize (Blender) a Meshy model they already have.

The English summary is being prepared. Showing the original description.