В каталоге 185 367 навыков в 14 категориях.
将图片/截图/扫描件/PDF/图片型PPT还原为可编辑的 PowerPoint (.pptx)。当用户说"转成可编辑PPT""图片转PPT""PDF转PPT""还原幻灯片"时触发。
Use this skill when designers, e-commerce operators, advertisers, brand teams, social-commerce teams, and content creato...
End-to-end workflow for converting a 2D concept image into a parametric 3D CAD model when manual outline tracing is unre...
Extract creative intent from images into executable build specs. Activates on images + build intent, "image to mission",...
Turn any still image into a professional motion graphic through the Novoads API on Seedance 2.5. Covers how to read a re...
将图片、PDF、图片版 PPTX 或含原生对象的混合 PPTX 转换为严格质量校验、分层可编辑的 PowerPoint;保留既有原生文字、形状、表格和图表,并使用宿主视觉 Agent 完成组件决策。用于截图、设计稿、科研图和幻灯片页面的组件...
将一张或多张图片转换为经过严格质量校验的分层 PSD;自动准备运行环境,通过当前 Agent 执行转换。输出修复背景、独立透明视觉组件和可编辑 Photoshop 文字图层。仅支持图片输入,不用于 PDF 或 PPTX。
Convert a generated image's original prompt (Yilin ink paintings, Records card plates) into a motion prompt for image-to...
Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uplo...
Convert a raster image (PNG, JPEG, WebP, GIF) or local image file into SVG with the QuiverAI vectorization API. Use when...
Recreate an image, screenshot, or mockup as a 1:1 UI implementation. Match the reference rather than redesigning it, the...
视频质量诊断助手适合市场营销、运营、内容媒体、电商在用户提出“这段视频够发布吗”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, F...
Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model...
Generate short videos from a static image using the Kling AI image-to-video API. Use this skill whenever the user wants...
FFmpeg-based video creation from image and audio.
Generate videos from static images using FAL AI models — Kling V2.6 Pro for premium quality with audio, Wan V2.6 for fas...
Use this skill when creators, video editors, advertisers, e-commerce teams, social-commerce teams, and short-form story...
主图转视频:把一张或几张商品主图/白底图/场景图,写成可直接喂给图生视频模型的镜头提示词(运镜、主体动作、光线、时长、负面约束),并保证商品不变形。Use when the user has product images and wants...
Transform images with resize, crop, smart crop, upscale, remove background, and 20+ operations.
Grab an image from the clipboard and analyze it. Use when the user says image upload, paste, screenshot, clipboard, or a...
Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Ther...
Classic image manipulation with Python Pillow - resize, crop, composite, format conversion, watermarks, brightness/contr...
Validate images against tacosdedatos illustration style guide. Use this skill when reviewing generated images, checking...
Unified cookbook for TeamDay's AI image + video production stack. Models (Seedream 5, Seedream 4, Flux 2, Kling, Wan, Se...
Verify media loading and failure states.
Use this skill for image/video metadata, alt strategy, thumbnails, transcripts, media indexing, performance. Trigger whe...
Search and download images from 12 APIs in parallel (Openverse, Pexels, Pixabay, Met Museum, NASA, Rijksmuseum, Wikimedi...
Create and execute image workflows using floimg. Use when the user needs to generate AI images, transform existing image...
Generate AI images and videos with the imageat API. Use when the user asks to create, edit or animate images, remove a b...
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, text...
"Use for visual deliverable routing and image generation/editing tasks, including new images, image edits, image upscali...
Generate brand, website or mobile design images from a visual brief. Triggers on "brand kit", "logo 设计".
Generate and edit images using OpenAI's Image API for project assets — UI mockups, icons, illustrations, social cards, a...
Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/ma...
当用户要求生成图片、配图、插图、logo、吉祥物、封面、海报、og 图、favicon 源图、真人场景图,或建站时页面缺图、仍有占位图时使用。包括“画一张”“出一套图”“网站需要配图”“image gen”。本 Skill 负责提示词、生成...
Generate premium frontend design reference images for mobile apps and websites. Use for mobile screen concepts, app flow...
Moved to github.com/Leonxlnx/imagegen-skills. Runs only when called by name.
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, An...
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT...
Automate Imagekit IO tasks via Rube MCP (Composio). Always search tools first for current schemas.
Upload images to ImageKit from file paths or clipboard, returning the CDN URL for easy sharing and embedding
Use ImageMagick 7 for deterministic still-image and image-sequence conversion, geometry, composition, masking, color, te...
Guide for using ImageMagick command-line tools to perform advanced image processing tasks including format conversion, r...
Comprehensive ImageMagick 7 command-line image processing for inspecting, converting, resizing, cropping, compositing, m...
Generates images using Google Gemini's image generation model for frontend UIs, documentation, and visual representation...
This skill generates images using Google Gemini's image generation model (gemini-3-pro-image-preview). It enables seamle...
AI image generation skill powered by Google Gemini, enabling seamless visual content creation for UI placeholders, docum...
Generate images using Google Gemini API. Use this skill when the user says /imagen, asks to generate an image, create ar...
Imagen - AI Image Generation Skill workflow skill. Use this skill when the user needs AI image generation skill powered...
Skill: imagen
Explicit Vertex AI Image Generation Skill using Imagen (Supports Brand Guidelines & Versions)
Generate images using Google Gemini's image generation API for UI mockups, icons, illustrations, and visual assets.
Imagen - AI Image Generation Skill
Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, gener...
画像生成AIに最適化されたプロンプトを作成。Nano Banana Pro (Gemini 3 Pro)、Imagen 3、DALL-E向けのプロンプトを生成する。
Use when generating images with Alibaba Cloud Bailian API, especially for Chinese text rendering or photorealistic image...
Generate optimized image prompts for Nano (Google) with 6-component structure. Analyzes vague ideas, auto-detects use ca...
Generate blog post thumbnails for Skill Stack using the brand aesthetic. Follows an iterative workflow - brainstorm conc...
Add, edit, generate, or organize image assets under src/jg/coop/images. Use for avatars, logos, posters, thumbnails, int...
Umbrella coordinator for image handling. Coordinates responsive-images, placeholder-images, and automation scripts. Use...
Responsive image generation and audit through a deterministic hook. It encodes every declared master into AVIF and WebP...
USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.
Guidance for SixLabors ImageSharp cross-platform image processing library. USE FOR: image resizing, cropping, format con...
Generate optimized image prompts for Nano (Google) with 8-component structure. Supports two modes: text-only (Mode A) an...
description: Imagine (Idea Intake) — Start or refine an idea. If given free-form text, create a new IDEA-XXXX folder,...
Generate or edit images with Codex. Use this skill whenever the user says "imagine ...", asks to create an image from a...
body elided by portability-corpus-gen.py
Generate AI images via Replicate or Gemini. Use to create illustrations, photos, or graphics from a text prompt.
Prepare detailed, professional prompts for Google Imagen 3/4 image generation. Supports character, environment, and obje...
인디 게임·소설·TTRPG용 **게임 캐릭터 일러스트**를 **같은 캐릭터로 반복 생성**하도록 설계된 스킬. Character Card(JSON)를 기준으로 이름/종족/연령/헤어/눈/의상/구별 특징/아트 스타일/팔...
UI 엠프티 스테이트·에러·로딩·온보딩 일러스트를 **라이트/다크 쌍**으로 생성한다. 같은 모티프를 두 모드에 걸쳐 자연스럽게 보이게 하되, **단순 색 반전이 아니라 라이트·다크를 각각 별도 프롬프트로 분리 생성...
SaaS · 개인 사이드 프로젝트의 **랜딩 페이지 히어로 이미지**를 3:2(1536×1024) 전용 프리셋으로 생성한다. 이미지 내부에 텍스트를 넣지 않고(모든 copy는 HTML이 담당), 한쪽 40%를 세이프...
모바일 앱·웹 앱 **아이콘 세트 일괄 생성기**. AI로 1024×1024 마스터 아이콘을 뽑고, 플랫폼별 다중 해상도(iOS 1024 / Android adaptive 전경·배경 / Web favicon·PWA·...
회사·개인 프로젝트·팀의 **로고 시안 탐색기**. 마크(심볼)만 Codex 이미지 모델로 생성하고 워드마크(회사명 글자)는 `scripts/lib/compose-text.js`로 합성한다. 회사명 텍스트는 AI 프...
블로그·랜딩 글의 **OG 이미지 / 소셜 카드**(Twitter / Instagram / LinkedIn)를 플랫폼 프리셋에 맞춰 자동 생성한다. 배경 일러스트만 Codex 이미지 모델로 뽑고, 제목·태그 같은 글...
YouTube 썸네일 전용 생성기. 배경/인물 일러스트는 Codex 이미지 모델로 뽑고, 제목 텍스트는 **AI가 아니라 Node 후처리**(`scripts/lib/compose-text.js`)로 합성한다. 한국어...
모바일 앱 화면의 **스타일 레퍼런스 이미지**를 빠르게 뽑는다. 실제 픽셀 퍼펙트 UI·구현 가능한 디자인이 아니라, Figma를 켜기 전에 "대충 이런 느낌인가?"를 여러 장 나열해보기 위한 **무드 보드**다....
Fan out MANY candidate interactive concepts from the data + narrative — the ideation pool the Editor curates a hero + su...
Use when preparing a medical-imaging dataset (DICOM/NIfTI) for modelling. Profiles spacing, orientation, intensity, labe...
Query and download NCI Imaging Data Commons (IDC) cancer radiology and pathology datasets via the idc-index Python clien...
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-sca...
Runs Loxihart/[CLIENT] endpoint imaging and deployment as a ten-gate, evidence-producing, resumable workflow: BIOS stora...
Workflow for multiplexed imaging or IMC segmentation, phenotyping, and spatial summarization.
Virtual Imam that leads the five daily Islamic prayers via voice, delivers Friday Jumu'ah khutbahs, and interacts with m...
Create iMandalArt 2.2 pure-text 3x3 Mandala index cards with a five-character center axis, eight orthogonal surrounding...