Skip to content

Anydesign skill

Extract a screenshot, website or Figma design into design.md, design tokens or a single-element rebuild brief.

Community · Alan Ponce (uxKero)
AuthorAlan Ponce (uxKero)
LicenceMIT
SourceuxKero/anydesign · SKILL.md on GitHub
Works inClaude Code · Codex, Gemini CLI, Cursor, Copilot
Read from the source on

The anydesign skill documents the design of an image, website or Figma node as a structured design.md.

Element mode narrows the job to one navbar, card or illustration and produces an element.md rebuild or image prompt.

From the skill's SKILL.md: Work in the user's language.

This is a community skill by Alan Ponce (uxKero), not checked by us or by Anthropic. Skills can tell the agent to run code, read files or call the network. Before installing, read its SKILL.md and every script in the folder, and look for anything that does not match what it says it does.

What it does

  1. Captures source evidence, separates measured and estimated tokens, writes the brief, lints it and exports token JSON.

What you get

  • design.md, design-tokens.json, optional design-a11y.md, or element.md.

When to use it

  • You need an evidence-based brief for a redesign or handoff.

When not to use it

  • You expect a screenshot to reveal unseen states or exact font values.

What it needs

  • Python for helper scripts; Pillow for image sampling; Playwright plus Chromium for websites; Figma MCP for Figma input. Website capture makes network requests.

Files in the skill

File or folderWhat it is for
SKILL.mdFull analysis and single-element workflows.
references/Capture, document contract and element-copy guidance.
scripts/Capture, contrast, lint and token-export helpers.

Licence as found in the repository on 2026-11-15: MIT.

Example prompts

Type one of these after installing; naming the skill makes sure it is used.

  • Extract design.md from this screenshot; mark estimates.
  • Document this website at desktop and mobile widths.
  • Analyze only this navigation bar and write element.md.

How to install anydesign

Choose the capture tools

Copy the complete repository as the anydesign skill folder. Install only the optional packages your capture or export route needs.

python3 -m venv .venv
source .venv/bin/activate
python -m pip install -r ~/.claude/skills/anydesign/requirements.txt
python -m playwright install chromium

A skill is a folder with a SKILL.md file. You install it once; the agent reads its short description at the start of each session and loads the full instructions only when a request matches. Pick the place you use:

Claude Code: copy the folder into your skills folder

Put the skill's folder in ~/.claude/skills/ to use it in every project on this computer, or in .claude/skills/ inside a repository to share it with everyone who works there (commit it).

git clone --depth 1 https://github.com/uxKero/anydesign.git
mkdir -p ~/.claude/skills/anydesign
git -C anydesign archive HEAD | tar -x -C ~/.claude/skills/anydesign

Claude Code notices new or changed skills in these folders during the session. If the skills folder did not exist when the session started, run /reload-skills once. Then type /anydesign or just describe the task.

On Windows, run the commands in Git Bash or WSL, or copy the folder into the same place with File Explorer.

Codex, Gemini CLI, Cursor and GitHub Copilot

These agents read the same SKILL.md folders. The one folder all four accept inside a project is .agents/skills/, so this copies the skill there:

git clone --depth 1 https://github.com/uxKero/anydesign.git
mkdir -p .agents/skills/anydesign
git -C anydesign archive HEAD | tar -x -C .agents/skills/anydesign
AgentProject folderYour user folderNotes
OpenAI Codex
.agents/skills/
~/.agents/skills/
Type $ or run /skills to pick a skill; Codex also chooses one when your task matches.
Gemini CLI
.agents/skills/
.gemini/skills/
~/.agents/skills/
~/.gemini/skills/
Or install from Git with gemini skills install <git URL> --path <folder> --consent. Google replaced Gemini CLI with Antigravity CLI for free-tier and Google One users on 18 June 2026; Antigravity uses .agents/skills/ in a project and ~/.gemini/config/skills/ for you.
Cursor
.agents/skills/
.cursor/skills/
~/.agents/skills/
~/.cursor/skills/
Type / in Agent chat to pick a skill. Cursor also reads Claude Code's .claude/skills/ folders.
GitHub Copilot
.github/skills/
.agents/skills/
.claude/skills/
~/.copilot/skills/
~/.agents/skills/
Works in Copilot CLI, the cloud agent, and agent mode in VS Code, Visual Studio and JetBrains (IDE support depends on the version). Or run gh skill install OWNER/REPOSITORY SKILL (public preview, GitHub CLI 2.90.0 or later).
Only install skills you trust. Anthropic's advice is to use skills only from trusted sources, and to read every file of any other skill before using it: a skill can direct the agent to run commands, read files or send data in ways its description does not mention.

Sources for these steps

Checked against each vendor's documentation on 2026-11-14:

Measured tokens

CSS variables and Figma definitions provide stronger evidence than visual guesses. The source and confidence belong in the brief.

Contrast checks apply to captured foreground/background pairs, not every possible state of the original product.

Keep the handoff small

The workflow limits captures and reads compact digests. Generate token JSON from the linted document so both outputs stay consistent.

Questions about anydesign

Does it build the website?

It produces the design brief and tokens; a separate implementation step builds the interface.

Is Figma required?

Only for Figma input. Screenshots and websites have independent capture paths.

Can it copy one element?

Yes. Element mode produces a scoped brief and a code, image or hybrid rebuild prompt.

Can the API capture a website?

The shared API sandbox has no network access; the full capture workflow is not offered there.

More AI skills

Related skills

Skill categories