Media & Creative · For designers

Build and maintain a persistent visual identity for your agent using Flux Kontext Pro.

letta-ai/skills

Use this whenever the user is on a machine running k4 — the Dynamic Island-style bar for Hyprland — and wants to change what the bar does, write a plugin for it, or debug one.

k4ditano/k4

YouTube 영상에서 쇼츠 클립 3개를 자동 제작합니다. An agent skill from uxjoseph/content-marketing-team.

uxjoseph/content-marketing-team

要在视频上加一段动效图形时用：下横栏（姓名职务）、关键词字幕、大数字与图表、标注与引导、品牌贴片与片尾、倒计时与进度。不选模板，按规则写一个自包含的 HTML 画面（时间的纯函数），打包成代码包导入后放上时间线。只加静态文字、贴纸或已有的文字动画预设时不用；整条成片的规划看「从简报到成片」。

JimLiu/baocut

定期审计代码库的工程设计问题（高心智复杂度、单一真相源被破坏、catch-all 胖接口、死代码、散落魔法字面量、泄漏抽象、资源生命周期靠环形缓冲）与可优化点，范围限定为自上次审计以来的 git churn，每条发现都落到 file:line 并对照本项目自己的 VISION.md / 各级 AGENTS.md / memory…

UniClipboard/UniClipboard

Distill stable art-generation patterns from a completed project, so future projects produce comparable assets without re-discovering the prompts.

tettethu/VibeGame

Writes seek-safe 2D and 3D keyframes for HyperFrames video compositions, covering punch-ins, zooms, reframes and camera moves without touching clip assembly.

heygen-com/hyperframes

Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an…

Orkas-AI/Orkas-VideoStudio

Builds marketing and explainer videos in Remotion from rendered scenes, with one real product capture as proof, and cuts them for each platform's formats.

ooiyeefei/ccc

把用户提供的品牌或产品 brief、参考素材和成片反馈整理为 TVC 创意方案、15 秒、30 秒或自定义时长的导演执行单、可复制的视频提示词，以及可选的无文字九宫格分镜；能分别配置视频模型、生成段数、节奏与镜头密度。适用于 TVC、品牌广告、产品广告、商业短片、Seedance 2.5、广告分镜、旁白设计和生成结果复盘；不用于纯社媒口播、直播切片或与 TVC 无关的视频参数咨询。

nutllwhy/seedance-tvc-director

Production pipeline for interactive and generative visual art using p5.js.

Tommy-yw/RunbookHermes

AI image generation and editing for blog content powered by Gemini via MCP.

AgriciDaniel/claude-blog

Helps design, write and verify hash-seeded long-form generative art for onchain mint platforms and screen-based venues, covering determinism, rarity and plotter output.

camilleroux/genart-skill

Generate images through the ChatGPT web app (chatgpt.com) via a local infinite-canvas board — queued jobs, scheduled batches, annotate-to-edit, style-reference generation, lineage.

ManiacMike/chatgpt-endless-canvas

Create free Agnes video generation tasks and retrieve video results through Agnes-Video-V2.0, including text-to-video, image-to-video, multi-image video, keyframe animation, async polling, and video…

kangarooking/agnes-free-model-skills

Design and edit COROS watch faces in CorosLink Watch Face Studio through its editor tools (applycommands, renderpreview, validate) and the generateimage tool.

JunAkerBuilds/CorosLink

为 Qwen-Image 编写和改写生图提示词，区分局部编辑与参考主体创作，处理同人物系列、画幅及原图验收；用户要求生成时连接其已有的 Qwen 图像工作流。不用于下载权重、通用模型运维或其他图像模型。

ZSeven-W/craft-skills

L1 × AI 设计评审：对已完成的单页、局部 UI 设计稿进行小型迭代评审，识别影响面、状态遗漏、文案与一致性风险，并给出 P0/P1/P2 建议和验收清单。用户提供 Figma 链接、截图、前后设计稿或可评审原型，并要求设计走查、风险评审或开发前 UI 检查时使用；不用于设计前方案预检、完整多页面流程或 L2 开发交付。

PaperMoonuu/Design-workflow-skills

Converts a report or other document into a business story and then an infographic image, pausing for your review after each step.

TyrealQ/q-skills

Convert text posts into visual carousel images or presentations for Threads, Instagram, LinkedIn, TikTok, YouTube.

itchernetski/threads-carousel-claude-skill

Generate 3D CGI and rendered video prompts for Seedance 2.0 on Higgsfield.

beshuaxian/higgsfield-seedance2-jineng

Make a promo / motion video for a software product with HyperFrames, using the saas-motion-kit 7-stage process (brief → components → theme → storyboard → build → sound → deliver), the…

tugrawork-creator/saas-motion-kit

Generates or edits raster images through OpenAI's Image API.

iurysza/module-graph

Build agent-friendly motion-graphics videos with Hyperframes (HTML-to-MP4).

robonuggets/hyperframes-helper

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background…

nexus-research-lab/nexus

Generate and process media — images, video, audio, music — and read text from images (OCR).

hi5jeff/deepclonewebsite

Create dark cinematic SaaS/product motion videos in the Presenton-like "magic UI" style: black starfield stage, bottom purple glow, large kinetic type, cyan-to-magenta CTA buttons, prompt cards…

Pluviobyte/video-production-skills

A skill your agent uses when working on tools/imggen avatar image generation, OpenAI-compatible image API config, human or yaoguai portrait prompts, qi-refining base generation, image-to-image realm…

4thfever/cultivation-world-simulator

Transcribing, displaying and animating captions. An agent skill from remotion-dev/remotion.

remotion-dev/remotion

把一个 Spec 的全部子 issue（或一组显式 issue）组建团队无人值守跑到全部合并或明确暂停. An agent skill from ArcReel/ArcReel.

ArcReel/ArcReel

Develop video direction, typography, color, visual mechanisms, storyboards, and asset prompts.

waker240/FullVideoProductionSkill

Multi-slide carousel design for Instagram, LinkedIn, and Twitter/X with layout rules and hooks.

danielmeppiel/agentic-sdlc-handbook

Extract, reverse-engineer, and codify transferable visual-style systems from images, animation, illustration, live-action film, television, commercials, or video.

ajinnaaa/extract-visual-style-2

Generate Nano Banana Pro (Gemini 3 Pro Image) prompts for e-commerce product photography.

MagicCube/agentara

Builds consistent characters, reference and expression sheets, outfit variations and character-to-video shots with the genmedia CLI while keeping identity stable.

fal-ai-community/skills

A skill your agent uses when Codex needs native image generation, editing, or engineered multi-image composition, especially sets, material kits, grids, storyboards, carousels, presentations…

zrt-ai-lab/opencode-skills

Coordinates nine creative roles, from brief analyst to project manager, so a brand, content or design task reaches the right specialist in a sensible order.

jinggreen15/ai-design-team

MUST use when the user wants to RENDER or GENERATE an actual video / MP4 from a description, or ANIMATE a local image.

Kiyoraka/Project-AI-MemoryCore

The normative Design Guides for GPUI Kit desktop applications.

StudentWeis/ropy

根据用户给出的城市、地点列表、地址表或已有 POI JSON，生成 GIS/OSM 城市导览地图、打卡地图、街区指南、小酒馆/咖啡/餐饮点位地图，并可选用 GPT Image 做风格化。用户要求“出一张地图”“生成城市点位图”“检查点位对齐”“用高德解析地址”“做 OSM/GIS 底图”“风格化地图海报”时使用。

Hatari130/map-creator

Guides React animation work with GSAP, Motion, Anime.js and Lenis for scroll effects, page transitions, text effects and generative visuals, with a library decision table.

Hainrixz/editor-pro-max

Daily pipeline that picks one long video from a folder, transcribes it with Whisper, uses Gemini 3 Flash multimodal to find every viral short-form moment, cuts each candidate with FFmpeg, adds a…

Upload-Post/skill-autoshorts

Find and install brand SVG logos via SVGL (https://svgl.app/) and Wikimedia Commons fallbacks into any project's static asset folder.

scott-fryxell/brayness

Drives the BananaTape CLI to create, launch, list and delete local AI image editing projects from an agent, including headless smoke tests.

NomaDamas/bananatape

Guide an installing agent through a staged PPT or slide workflow without constraining its implementation choices.

mucsbr/ppt-agent-workflow-san

Designs typography-driven video covers and thumbnails in HTML/CSS and screenshots them with Chrome DevTools at 16:9, 16:10, 9:16 and 3:4.

sugarforever/01coder-agent-skills

将剧本、分镜脚本及人物或场景设定转化为电影级九宫格分镜图和时间线镜头表，并在分镜完成后询问是否依据已确认分镜与用户素材制作独立的成片关键帧。适用于叙事影片、广告、MV、短剧的镜头拆解、画面调度、运镜、转场、分镜单格放大与关键帧美术呈现；严格区分只表达运镜、构图和光影设计的分镜图，与由用户人物、场景及风格素材决定最终美术的关键帧。

TanShilongMario/clipshot

Generate a single image from a text prompt using the MiniMax image generation API.

Sma1lboy/rove