agentsclimarketplace
Sign in

Shelves Media & documents

Images & graphics

1,136 rows from 422 repositories

Making, editing and optimising pictures.

What Images & graphics skills agree on

386 skill files read, by 341 of the 354 authors on this shelf whose files we hold, 2026-09-06

The middle one of the 67 measured here is ~1.7k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Generate images via gemini_generate_image14 of 341 in 10 filesalso worded as Generate via gemini_generate_image; Generate images via gemini_generate_image tool
  2. Set the aspect ratio via set_aspect_ratio14 of 341 in 10 filesalso worded as Set aspect ratio via set_aspect_ratio; Set aspect ratio via set_aspect_ratio tool
  3. Verify MCP image tools are available before generating13 of 341 in 9 filesalso worded as Verify MCP tools are available before generating; Verify MCP server tools are available before generating
  4. Show estimated cost before generating13 of 341 in 9 filesalso worded as Show estimated cost before generating, especially for batch; Show estimated cost before generating, especially batches
  5. Run the post-generation SEO checklist13 of 341 in 9 filesalso worded as Run the post-generation SEO checklist after each generation; Run the post-generation SEO checklist after every generation
  6. Structure prompts as subject, setting, style, lighting, composition10 of 341 in 5 filesalso worded as structure prompts with subject, setting, style, lighting; Structure prompts with subject, context, and style
  7. Infer the brand strategy before generating9 of 341 in 5 files
  8. Use at most two logo concept methods9 of 341 in 5 filesalso worded as Use one or two logo concept methods maximum
  9. Use one dominant palette with repeating accents9 of 341 in 5 filesalso worded as Use one dominant palette.
  10. Extract fileKey and nodeId from the Figma URL9 of 341also worded as Extract the file key from the Figma URL; Parse file key and node ID from the Figma URL
  11. Read product marketing context before asking questions8 of 341 in 3 files
  12. Keep the logo simple, symbolic, and ownable8 of 341 in 4 filesalso worded as Keep the logo simple, symbolic, and scalable
  13. Generate one brand-kit overview image by default8 of 341 in 4 filesalso worded as Generate one brand-kit overview image
  14. Capture real screenshots for product UI mockups8 of 341 in 3 filesalso worded as capture real screenshots for product mockups
  15. Reuse existing components before creating new ones8 of 341also worded as Reuse existing components before building new ones; Reuse existing project components before creating new ones

What they tell it not to do

  1. Do not load all reference docs at startup15 of 341 in 11 filesalso worded as Do not load all references at startup; never load all references at startup
  2. Never auto-generate images during audits11 of 341 in 7 filesalso worded as Never auto-generate during image audits; Never auto-generate during audits
  3. Never use lorem ipsum or fake body copy.10 of 341 in 6 filesalso worded as Avoid lorem ipsum and dense fake text; Never use lorem ipsum or rewritten copy
  4. Do not skip image optimization10 of 341 in 5 filesalso worded as never skip image optimization; do not skip visual inspection of generated images
  5. Never generate generic logos.9 of 341 in 5 filesalso worded as Do not generate generic logos
  6. Never pick symbols randomly.9 of 341 in 5 filesalso worded as Do not pick symbols randomly
  7. Never copy reference logos or slogans exactly9 of 341 in 5 filesalso worded as Do not copy references exactly; Copying reference logos instead of drawing inspiration
  8. Never use AI to generate product UI screenshots8 of 341 in 3 filesalso worded as never use AI for product UI screenshots; never use AI models for product UI screenshots
  9. Do not publish shared pages without OG images8 of 341 in 3 filesalso worded as don't publish pages without OG images; don't publish pages without an OG image
  10. Never generate random mockups or moodboards8 of 341 in 4 filesalso worded as Do not generate random mockups; Never generate random mockups.

What they expect to be installed

  1. curl34 of 341 in 32 files
  2. python326 of 341
  3. get_screenshot24 of 341 in 23 files
  4. Figma23 of 341 in 17 files
  5. get_metadata21 of 341 in 20 files
  6. get_design_context19 of 341
  7. use_figma16 of 341
  8. Figma MCP server16 of 341
  9. magick16 of 341 in 12 files
  10. Figma MCP14 of 341

What they ask it to produce

  1. Generated image file21 of 341 in 16 filesalso worded as Generated image files; generated PNG image file
  2. OG meta tag markup14 of 341 in 7 filesalso worded as OG image meta tags; og:image meta tag markup
  3. ImageObject schema snippet13 of 341 in 9 filesalso worded as ImageObject schema snippets; ImageObject schema markup
  4. Alt text suggestion12 of 341 in 8 filesalso worded as descriptive alt text suggestions; Keyword-rich alt text suggestion
  5. One brand-kit overview image9 of 341 in 5 filesalso worded as a single brand-kit overview image
  6. Design tokens7 of 341 in 5 filesalso worded as Design token summary; design token definitions
  7. DESIGN.md6 of 341also worded as design-system.md
  8. Rendered node images6 of 341 in 3 filesalso worded as rendered images of nodes

When Images & graphics authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 341 authors, with the skills that name each one

How Images & graphics skills are built

1,057 skill directories by 366 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 4 files, 17.2 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill115 of 366 authors, 323 of 1,057 skills
  2. files ship beside it251 of 366 authors, 734 of 1,057 skills
  3. executable scripts ship inside135 of 366 authors, 273 of 1,057 skills

The folders they converge on

  1. references/173 of 366 authors, 397 of 1,057 skills
  2. scripts/118 of 366 authors, 225 of 1,057 skills
  3. assets/56 of 366 authors, 134 of 1,057 skills
  4. agents/53 of 366 authors, 97 of 1,057 skills
  5. evals/27 of 366 authors, 48 of 1,057 skills
  6. examples/19 of 366 authors, 22 of 1,057 skills

  • Figma Context MCP

    GLips/Figma-Context-MCP/io.github.GLips/Figma-Context-MCP MCP server

    in 1 stack15,643★ repo

    Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

  • Gpt image

    wuyoscar/GPT-Image2-Skill/skills/gpt-image Skill

    4,246★ repo

    GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

  • Thesvg

    glincker/thesvg/skills/thesvg Skill

    2,560★ repo

    6,400+ brand SVG icons for developers. Tree-shakeable, typed, open source. npm i thesvg

  • Figma MCP Server

    figma/mcp-server-guide/com.figma.mcp/mcp MCP server

    no license1,875★ repo

    The Figma MCP server brings Figma design context directly into your AI workflow.

  • Figma ui mcp

    TranHoaiHung/figma-ui-mcp/io.github.TranHoaiHung/figma-ui-mcp MCP server

    221★ repo

    Bidirectional Figma MCP — AI draws UI on Figma canvas, reads designs back

  • Skywork design

    SkyworkAI/Skywork-Skills/skywork-design Skill

    199★ repo

    Skywork Agent Skills for AI office suites, including AI PPT, AI Document, AI Excel, AI Image, AI Search/DeepResearch and AI Music. These skills can be used by any skills-compatible agent, including Claude Code, Codex CLI and OpenClaw.

  • Claude image

    jiangmuran/claude-image Skill

    83★

    教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — intent-first prompting, surgical edits, parallel batching, visual self-verification

  • Baseline

    gaearon/woodshed/example/skills/ascii-art/baseline Skill

    70★ repo

    Create, run, rate, and iterate on your Claude Skills

  • Bria ai

    Bria-AI/bria-skill/skills/bria-ai Skill

    no license63★ repo

    Claude Code skills for Bria AI - generate, edit, and transform images with Fibo, RMBG-2.0, and VGL structured prompts

  • Figma to code

    scoobynko/claude-code-design-skills/figma-to-code Skill

    38★ repo

    Claude Code skills for automated design-to-code workflows.

  • Logoloom

    mcpware/logoloom/io.github.mcpware/logoloom MCP server

    27★ repo

    AI logo design → SVG → full brand kit. Text-to-path, optimize, export PNG/ICO/WebP.

  • Ai image editing

    social-media-skills/skills/skills/ai-image-editing Skill

    22★ repo

    106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.

  • Wiggle claude skill

    talknerdytome-labs/wiggle-claude-skill Skill

    no license21★

    Claude Skill for Animating Logos

  • Figma mcp rust

    alvinindra/figma-mcp-rust/io.github.alvinindra/figma-mcp-rust MCP server

    16★ repo

    Figma MCP server in Rust — plugin bridge, no API token, no rate limits, 73 tools.

  • HTML to Figma — Design System

    miapre/html-to-figma-design-system/io.github.miapre/html-to-figma-design-system MCP server

    13★ repo

    Translate HTML prototypes into Figma using your design system's real components and tokens.

  • Analyze component set figma

    southleft/skills-for-figma/skills/analyze-component-set-figma Skill

    12★ repo

    Open-source agent skills for the native Figma MCP server — design tokens, components, accessibility, Slides, and FigJam.

  • Svg character animator

    molauu/svg-character-animator Skill

    10★

    Agent Skill for production-quality SVG character animation — morph state machines, idle motion, SwiftUI export

  • Genpark nano banana photo enhancer

    alphaparkinc/genpark-nano-banana-photo-enhancer Skill

    no license9★

    GenPark Distilled Skill: nano-banana-photo-enhancer

  • Figma edit mcp

    neozhehan/figma-edit-mcp/io.github.neozhehan/figma-edit-mcp MCP server

    9★ repo

    Programmatically read, create, and modify Figma designs via MCP.

  • Figma ios comments integration

    mythkiven/figma-ios-codegen/.cursor/skills/figma-ios-comments-integration Skill

    8★ repo

    Figma to iOS UIKit codegen: deterministic data package + Agent skills (Cursor/Claude) for baseline Swift UI.

  • Figma mcp go

    tunglt1810/figma-mcp-go/io.github.tunglt1810/figma-mcp-go MCP server

    6★ repo

    Figma MCP server with full read/write access via plugin — no API token, no rate limits. 73 tools.

  • Card skill

    KKenny0/card-skill Skill

    5★

    Content in, PNG out. A Claude Code/Codex skill that turns articles, ideas, and arguments into checked Quiet Paper PNGs: cards, posters, whiteboards, and editorial images.

  • Image to SVG

    botmonster/image2svg-mcp/io.github.botmonster/image2svg-mcp MCP server

    5★ repo

    MCP server that converts raster images (PNG/JPG/WEBP) to SVG vector format

  • Figma design.example

    Mfrostbutter/skill-forge/examples/figma-design.example Skill

    4★ repo

    Turn complex AI workflows into reusable Claude skills. Capture the lessons to a tagged journal that survives context resets, then crystallize it into a validated skill.

  • Svg to png

    bgorkem/bgorkem-skills/plugins/image-transform/skills/svg-to-png Skill

    4★ repo

    Claude Code plugin marketplace with Agent Skills for Claude. Install via /plugin marketplace add bgorkem/bgorkem-skills

  • App icon gen

    xzhih/app-icon-skill/skills/app-icon-gen Skill

    no license4★ repo

    Design, generate, package, repair, and verify polished app icons from briefs, brand assets, references, SVGs, existing icons, and generated concepts.

  • Figma Context MCP

    felixAnhalt/Figma-Context-MCP/io.github.felixAnhalt/Figma-Context-MCP MCP server

    4★ repo

    LLM-optimized Figma MCP server.

  • Figma to code mcp

    felixAnhalt/figma-to-code-mcp/io.github.felixAnhalt/figma-to-code-mcp MCP server

    4★ repo

    LLM-optimized Figma MCP server.

  • Figma mcp express

    sunhome243/figma-mcp-express/io.github.sunhome243/figma-mcp-express MCP server

    4★ repo

    Compact Figma MCP with validated batch ops through a local plugin bridge.

  • Image prompt

    veryCoolTimo/imagegen-skills/skills/image-prompt Skill

    3★ repo

    Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-image-2. MIT.

  • Brandkit

    tinhtran24/maestro/.claude/skills/brandkit Skill

    2★ repo

    Maestro is an open-source, multi-agent AI development framework written in Go. It orchestrates specialized AI coding agents across a deterministic software engineering workflow

  • Notebook video

    hyt315/notebook-video Skill

    2★

    Visual-director Agent Skill for 2K Chinese Remotion videos with original imagery, animated text and automated QA.

  • Majia meeting svg

    maojiebc/majia-meeting-svg Skill

    2★

    会议纪要卡片 · 马甲实战版 — 会议逐字稿 → 手机可转发的 SVG/PNG 卡片

  • Tl image

    bob5-tensorslab/skills/skills/tl-image Skill

    no license1★ repo

    TensorLab Skills are AI task definitions for Claude Code, focusing on multimedia generation and processing using TensorsLab's AI models. It provides comprehensive capabilities including text-to-image and image-to-image generation, advanced image editing (avatar generation, watermark removal, object erasure, face replacement), as well as text-to-vid

  • Thumbnail machine

    holy-templar/thumbnail-machine Skill

    no license1★

    Turn any article into ready-to-run thumbnail prompts — 5 formats, 10 styles, your face in every image. Free Claude skill.

  • Camera and photos

    heyimjames/ios-design-skills/plugins/heyimjames/skills/camera-and-photos Skill

    1★ repo

    Four detailed iOS/SwiftUI design-engineering skills for Claude Code, Cursor, Codex, Windsurf, Aider, Continue, and Zed — camera & photos, chat & messaging, interaction primitives (widgets/Live Activities/haptics), and the final 5% of polish.

  • Y2k aesthetic generator

    omactiengartelle/y2k-aesthetic-generator Skill

    no license1★

    Y2K Aesthetic Generator — AI-powered y2k aesthetic photo generator

  • Latex svg skill

    Oneptica/latex-svg-skill Skill

    no license1★

    Render LaTeX formulas to SVG locally in Claude Code, no LaTeX distributions needed

  • Pixel art generator

    blammectrappora/pixel-art-generator Skill

    no license1★

    Pixel Art Generator — AI-powered pixel art generator

  • Fangxin image gen

    metafeng/fangxin-image-gen Skill

    no license1★

    Claude Skills / Codex 中文图片生成 Skill：基于放心 API（fangxinapi.com）的 gpt-image-2，支持文生图、改图、多图合成与 URL 输入

  • Scifig scientific figure

    lilingm963/scifig-ai-scientific-figure-skill/skills/scifig-scientific-figure Skill

    1★ repo

    Scientific figure skill for Codex, Claude Code, and agents. Turn research ideas, paper methods, and grant roadmaps into publication-ready figures. Powered by SciFig (scifig.ai).

  • Ocr

    hec-ovi/ocr-skill/skills/ocr Skill

    1★ repo

    Image and PDF to Markdown OCR for AI agents: portable skill + ocr CLI (DeepSeek-OCR-2), stdio only, no MCP

  • Skill

    spfr/figma-design-pipeline/skill Skill

    1★ repo

    Open-source MCP pipeline for Figma: inspect designs, apply safe mutations, sync tokens, and generate code with Claude, Codex, Gemini, and Figma desktop.

  • Terminal logo ui

    Haaaiawd/Cli-ui-forge-skills/skills/terminal-logo-ui Skill

    no license1★ repo

    AI agent skills for designing terminal logos, banners, and CLI selection UIs with stronger structure, clearer interaction models, and less generic noise.

  • Brand assets

    wwwyo/syokan/.agents/skills/brand-assets Skill

    1★ repo

    syokan — LLMs summon rich UI. Chant a JSON incantation, and a living interface appears. Ephemeral by design.

  • Dataviz svg

    oubakiou/skills/skills/dataviz-svg Skill

    1★ repo

    AI agent skills

  • Svg create

    alavten/svg-create Skill

    no license1★

  • Imagegen

    yzp100911/skillgate-agent/cclaw/data/codex-home/skills/.system/imagegen Skill

    1★ repo

    skillgate-agent - AI多模型网关与智能代理框架, 支持MiniMax/DeepSeek等主流模型, 集成MCP工具调用与技能系统。skillgate-agent - AI multi-model gateway & intelligent agent framework, supporting MiniMax/DeepSeek, MCP tools & skill system。

  • Figma to email html

    AzalDaniel/FigForge/skills/figma-to-email-html Skill

    1★ repo

  • Top cs figure

    zhiming33416/top-cs-paper-skills/skills/top-cs-figure Skill

    1★ repo

    Evidence-grounded Codex skills for writing, polishing, reviewing, reviewer responses, and figures for top CS conferences.

  • Annotate screenshots

    madeyexz/annotate-screenshots/skills/annotate-screenshots Skill

    1★ repo

    screenshots annotation skill for coding agents

  • Retro Diffusion Pixel Art

    Retro-Diffusion/retro-diffusion-mcp/ai.retrodiffusion/pixel-art MCP server

    1★ repo

    Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client

  • Figma Context MCP AIR

    compassalessandrolorenz/Figma-Context-MCP-AIR/io.github.compassalessandrolorenz/Figma-Context-MCP-AIR MCP server

    1★ repo

    Figma MCP server for AI agents. 9 tools: design context, variables, screenshots, and FigJam.

  • Figma MCP Server

    oabolade/figma_mcp_server_actor/io.github.oabolade/figma_mcp_server_actor MCP server

    1★ repo

    MCP server enabling AI assistants to interact with Figma designs via natural language commands

  • Image Generation MCP Server

    pvliesdonk/image-generation-mcp/io.github.pvliesdonk/image-generation-mcp MCP server

    1★ repo

    MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.

  • Ascii art

    theduodecim/ascii-art-mcp/io.github.theduodecim/ascii-art MCP server

    no license1★ repo

    MCP server that exposes ASCII and Unicode art tools

  • Figma code connect

    Moliboy5000/.claude/plugins/cache/claude-plugins-official/figma/2.2.78/skills/figma-code-connect Skill

    no license0★ repo

    Claude dotfile containing skills, agents etc I use.

  • Logo design generator

    blammectrappora/logo-design-generator Skill

    no license0★

    Logo Design Generator — AI-powered ai logo generator

  • Yoto pixel art

    mbrg/yoto/.claude/skills/yoto-pixel-art Skill

    no license0★ repo

    Generate 16x16 pixel art icons for Yoto MYO cards using Claude Code

  • Polaroid photo generator

    blammectrappora/polaroid-photo-generator Skill

    no license0★

    Polaroid Photo Generator — AI-powered polaroid photo generator ai

All 1,136 in the catalog