anydesign
"Extract the design of a screenshot, website URL or Figma file into a design.md with tokens, components, layout and brand rules, or copy one element (navbar, card, illustration) into an element.md with a rebuild or image-generation prompt. Use when the user wants to document, replicate, audit or reverse-engineer a visual design: its design system, palette, typography or style."
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/uxkero--anydesign)HTML
<a href="/listings/uxkero--anydesign"><img src="/api/listings/uxkero--anydesign/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
git clone https://github.com/uxKero/anydesign.git # Personal skills (all projects) cp -r anydesign ~/.claude/skills/ # OR for a single project cp -r anydesign /path/to/project/.claude/skills/
Optional extras:
# Python deps for the companion scripts pip install -r requirements.txt playwright install chromium # only for capture_site.py (~300MB first time)
To analyze **Figma files**, connect the Figma MCP in the Claude app (`Settings → Connectors`).
That's it — the skill activates automatically when Claude detects design-analysis intent ("extract the design system from X", "copy this navbar", "what palette does this site use"). No command to remember.
---
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 112 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- ---
- name: anydesign
- description: "Extract the design of a screenshot, website URL or Figma file into a design.md with tokens, components, layout and brand rules, or copy one element (navbar, card, illustration) into an element.md with a rebuild or image-generation prompt. Use when the user wants to document, replicate, audit or reverse-engineer a visual design: its design system, palette, typography or style."
- ---
- # AnyDesign: design analysis and documentation
- ## Role
- You are a **Design Systems Analyst**: part visual detective, part systems designer, part
- frontend engineer. Don't describe what you see; **diagnose the design**: which decisions
- were deliberate, which patterns repeat, which tokens operate under the surface, and what it
- would take to rebuild it. The reader is a designer or another AI that will reconstruct the
- design from your file. Work in the user's language.
- ## Two modes
- - **Full mode** (default): the design of a page, file or system → the workflow below,
- output `design.md`.
- - **Element mode**: ONE element ("copy this navbar", "just the pricing card", "recreate
- this 3D illustration", "give me a prompt to generate this graphic") → read
- `references/element-copy.md` and follow its E-steps, output `element.md`.
- Signals for element mode: a definite article plus a single component ("the navbar"), an
- element-scoped verb ("copy", "extract just", "recreate"), or any request for an
- image-generation prompt. Ambiguous ("analyze this card-heavy dashboard") → full mode, and
- offer element mode as the follow-up.
- ## Token budget (applies to every step)
- Every tool call re-sends the whole conversation, so whatever enters the context early is
- paid again on each later turn. A careless URL run measured 51 model calls and a 209k-token
- context. Keep it lean:
- - **Run scripts, never open their source.** `--help` is enough if a flag is unclear.
- - **Never read a dump whole.** `css-vars.json`, rendered HTML and Figma
- `get_design_context` on a whole file can each be 15k to 500k tokens. Work from the script
- digests. For a missing CSS variable, `extract_css_vars.py --grep 'pattern'`; never parse
- the JSON with your own code.
- - **Images: at most 4 desktop frames plus 2 mobile frames**, and only the ones you need.
- Don't write your own capture or scroll scripts; `capture_site.py --frames N` covers it.
- - **Batch.** Run the capture scripts in one turn, read the references you need in one turn,
- and group small checks into one command.
- - **Generate derived files, don't type them.** `design-tokens.json` comes from
- `build_tokens_json.py`, `design-a11y.md` from `check_contrast.py --output`.
- - **Write `design.md` once**, then fix lint findings with small edits, never a full rewrite.
- ## Workflow
- ### Step 1: source and emphasis
- Ask only if unclear: which source (image, URL, Figma, a combination) and which emphasis
- (reconstruction, mood/reference, design system). Default: reconstruction plus design
- system, at standard depth. Go deep only when the user asks for it.
- ### Step 2: capture
- Details and flags in `references/capture-flows.md`; read it only if something below doesn't
- cover your case.
- - **Image**: view it directly. `scripts/extract_colors.py <image>` when you need exact hex
- codes instead of vision estimates.
- - **URL**: in one turn, run `python scripts/extract_css_vars.py <URL>` (digest of the
- explicit tokens) and `python scripts/capture_site.py <URL> --viewports desktop,mobile`
- (computed styles of body, headings, buttons, inputs and cards, plus up to 4 readable
- frames per viewport). Together they usually carry the whole token layer. No Playwright →
- `WebFetch` for content and structure, and mark measured typography ⚠️.
- - **Figma**: `get_metadata` for structure, `get_variable_defs` for defined tokens,
- `get_design_context` on a node (never a whole file), `get_screenshot` for visual
- reference. Ask for a `node-id` link when given a whole file.
- - **Combination**: scripts or Figma for tokens, the user's screenshot for the state they
- care about; say in Source what each contributed.
- If something fails (URL down, Cloudflare wall, no Figma access, broken image), say so and
- propose an alternative, such as a manual screenshot. Don't bypass protections and don't
- invent content.
- ### Step 3 and 4: analyze and write
- Read `references/design-md.md`. It holds the six layers (identity, system, components,
- layout, reconstruction, brand rules), token rigor, the frontmatter and section contract,
- length caps per depth, and the art direction QA pass to run before writing. Connect the
- analysis to any context the user gave ("this is for an AI brand").
- Then, in order:
- 1. With 2+ text/surface color pairs:
- `python scripts/check_contrast.py --pair "FG,BG:label" ... --output design-a11y.md`
- 2. Write `design.md` in one go.
- 3. `python scripts/lint_design_md.py design.md`, and fix failures with targeted edits.
- 4. If Layer 2 produced concrete tokens: `python scripts/build_tokens_json.py design.md`.
- Never write the JSON by hand; anything to export belongs in the frontmatter.
- ### Step 5: deliver
- List the files and offer the next logical step for the chosen emphasis: refine a weak
- section, turn the design.md into a build prompt for Claude Code or v0, or analyze another
- source to compare. Don't close with "anything else?".
- ## Scripts
- | Script | Use | Deps |
- |---|---|---|
- | `extract_css_vars.py` | URL: token digest; `--grep` searches the saved JSON | stdlib |
- | `capture_site.py` | URL: computed styles + frames; `--selector` for element mode | `playwright` |
- | `extract_colors.py` | Image: dominant hex codes with area % | `Pillow` |
- | `check_contrast.py` | WCAG table; `--output` writes it | stdlib |
- | `lint_design_md.py` | Validates design.md (frontmatter, refs, components 1:1, sections 6-7) | stdlib |
- | `build_tokens_json.py` | design.md → DTCG `design-tokens.json` | stdlib |
- For the user, not part of a run: `verify_design.py` (drift of a tokens file against the live
- URL) and `export_for_claude_design.py` (bundle for claude.ai/design).
README.md · README · 322 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- <div align="center">
- # anydesign
- ### Point it at anything visual. Get a design system back.
- A Claude skill that turns **images, websites, and Figma files** into structured,
- machine-readable design specs — and copies **single elements** (navbars to 3D art)
- as rebuild prompts any AI can execute.
- [](https://opensource.org/licenses/MIT)
- [](./CHANGELOG.md)
- [](https://docs.claude.com/en/docs/agents-and-tools/agent-skills/overview)
- [](https://www.designtokens.org/)
- [](https://github.com/uxKero/anydesign/stargazers)
- **[Install](#-install)** · **[See it work](#-see-it-work)** · **[Element mode](#-element-mode--copy-just-that)** · **[CLI scripts](#-standalone-cli-scripts)** · **[Examples](./examples)**
- </div>
- ---
- ## 🧠 What it does
- **`anydesign` runs in Claude — its output is universal.** Plain Markdown + W3C DTCG
- JSON that v0, Lovable, Cursor, Bolt, Claude Code, or a human designer can consume.
- No lock-in. It's not a description generator — it's a **design diagnostics** tool:
- every inference carries a confidence marker (✅ ⚠️ ❓), every color is a real hex,
- and inventing tokens is treated as worse than saying "not enough info".
- Two modes, picked automatically from what you ask:
- | You say | Mode | You get |
- |---|---|---|
- | *"Extract the design system from this site"* | **Full analysis** | `design.md` (7-section spec) + `design-tokens.json` (DTCG) + optional WCAG report |
- | *"Copy this navbar"* / *"Recreate this 3D graphic"* | **Element mode** | A focused `element.md`: code spec + rebuild prompt, or a **token-grounded image prompt** |
- ---
- ## 🎬 See it work
- Every image below is a real, reproducible run — sources and commands live in
- [`examples/`](./examples).
- ### Act 1 — A full design system becomes a running app
- The skill analyzed [vercel.com](https://vercel.com) (808 CSS custom properties
- extracted, nothing invented), produced a `design.md`, and v0 built this from it:
- [](https://v0-anydesignexample.vercel.app/)
- <div align="center"><sup>Live at <a href="https://v0-anydesignexample.vercel.app/">v0-anydesignexample.vercel.app</a> · full run in <a href="./examples/vercel-landing"><code>examples/vercel-landing/</code></a></sup></div>
- ### Act 2 — One element, rebuilt
- Element mode pointed at the retro Mac OS player of
- [poolsuite.net](https://poolsuite.net): DOM-precise capture, pixel-sampled palette,
- the verbatim bevel-shadow system — and a rebuild prompt that v0 turned into a
- working app.
- | Captured element | Rebuilt by v0 from the `element.md` |
- |---|---|
- |  |  |
- <div align="center"><sup>Live at <a href="https://retro-radio-player-zz.vercel.app/">retro-radio-player-zz.vercel.app</a> · run details in <a href="./examples/poolsuite-player-element"><code>examples/poolsuite-player-element/</code></a></sup></div>
- ### Act 3 — Art becomes a prompt that holds
- When the element is *art*, you get a generative image prompt **grounded in the
- extracted palette** — hex by hex. Discord's 3D hero scene, regenerated on the
- first pass: indigo world locked, every accent on its exact extracted hex, original
- characters (no brand mascots — there's an IP guardrail).
- | Captured element | Generated from the token-grounded prompt |
- |---|---|
- |  |  |
- And the same extraction as an **isolated, web-ready cutout** — single subject,
- real alpha, no scenery. Drop it straight into your site:
- <p align="center">
- <img src="./examples/discord-hero-asset/element-3D-isolated.png" width="260" alt="The robot companion as an isolated transparent PNG generated from the element.md prompt">
- </p>
- <div align="center"><sup>Both prompts + alpha verification in <a href="./examples/discord-hero-asset"><code>examples/discord-hero-asset/</code></a></sup></div>
- ### Act 4 — Game asset packs that stay consistent
- The #1 pain of AI game art is consistency between assets. Element mode extracts a
- game's art direction **once** — palette, lighting recipe, color-allocation rules —
- and emits a prompt pack where every asset shares that base. One key art in, a
- coherent sprite set out:
- | Captured key art | Original character generated from the pack |
- |---|---|
- |  | <p align="center"><img src="./examples/game-asset-pack/asset-character.png" width="240" alt="An original game character generated from the token-grounded asset-pack prompt, transparent PNG"></p> |
- <div align="center"><sup>Prompt pack (character + pickup + prop) in <a href="./examples/game-asset-pack"><code>examples/game-asset-pack/</code></a> · original subjects only, per the IP guardrail</sup></div>
- ---
- ## 🚀 Install
- ```bash
- git clone https://github.com/uxKero/anydesign.git
- # Personal skills (all projects)
- cp -r anydesign ~/.claude/skills/
- # OR for a single project
- cp -r anydesign /path/to/project/.claude/skills/
- ```
- Optional extras:
- ```bash
- # Python deps for the companion scripts
- pip install -r requirements.txt
- playwright install chromium # only for capture_site.py (~300MB first time)
- ```
- To analyze **Figma files**, connect the Figma MCP in the Claude app
- (`Settings → Connectors`).
- That's it — the skill activates automatically when Claude detects design-analysis
- intent ("extract the design system from X", "copy this navbar", "what palette does
- this site use"). No command to remember.
- ---
- ## 📦 What you get
- | File | What it is |
- |---|---|
- | **`design.md`** | 7-section spec: TL;DR → visual identity (incl. brand voice + the "ONE brand thing") → tokens → components → layout → reconstruction notes → Do's/Don'ts → open questions. YAML frontmatter + `{token.refs}` make it machine-parseable and refactor-safe. |
- | **`design-tokens.json`** | [W3C DTCG](https://www.designtokens.org/) format (`$value`/`$type`) — drops into Style Dictionary, Figma Variables, Tokens Studio. |
- | **`design-a11y.md`** *(optional)* | WCAG 2.1 contrast report with AA/AAA pass-fail. |
- | **`element.md`** *(element mode)* | Scoped spec + rebuild prompt (`code`), token-grounded image prompt (`asset`), or both (`hybrid`). |
- ---
- ## 🪄 Element mode — "copy just that"
- Sometimes you don't want the whole system — you want *that* navbar, *that* pricing
- card, *that* 3D illustration. Say so and the skill captures just the element
- (`capture_site.py --selector` grabs its exact bounding box + `outerHTML` on URLs)
- and classifies it:
- | Kind | Example | Output |
- |---|---|---|
- | `code` | Navbar, card, button, hero | Scoped token spec + paste-ready rebuild prompt (v0 / Claude Code / Lovable) |
- | `asset` | 3D illustration, mascot, photo art | **Token-grounded prompt for image models** (gpt-image, Midjourney, SD/Flux) |
- | `hybrid` | A card containing an illustration | Code spec + nested asset prompt |
- The image prompts are the differentiator: instead of an impressionistic description,
- the prompt embeds the **exact extracted palette**, observed lighting, and the parent
- brand's mood — so the regenerated asset *belongs* to the source design. Two delivery
- formats: `scene` (composition with background) or `isolated` (single subject,
- transparent PNG with alpha, ready for the web).
- ---
- ## 🔌 Works with any AI builder
- The deliverable is plain text. Anything that reads Markdown can use it.
- | Tool | How |
- |---|---|
- | **[v0](https://v0.dev)** / **[Bolt](https://bolt.new)** / **[Lovable](https://lovable.dev)** | Paste `design.md` as the brief — see both [live](https://v0-anydesignexample.vercel.app/) [demos](https://retro-radio-player-zz.vercel.app/) |
- | **[Claude Code](https://claude.com/claude-code)** / **[Cursor](https://cursor.sh)** / **[Windsurf](https://codeium.com/windsurf)** | Drop `design.md` + `design-tokens.json` into context, ask for the build |
- | **Style Dictionary / Tokens Studio / Figma Variables** | Import `design-tokens.json` directly (DTCG) |
- | **gpt-image / Midjourney / SD** | Paste the `element.md` image prompt |
- | **Notion / Linear / a human** | `design.md` reads as a designer brief |
- ---
- ## 🧰 Standalone CLI scripts
- Eight pure-Python tools in [`scripts/`](./scripts) that **work without Claude**:
- | Script | What it does | Deps |
- |---|---|---|
- | `extract_css_vars.py` | Pull every `--*` custom property from a URL's stylesheets: compact digest on screen, full JSON on disk | stdlib |
- | `capture_site.py` | Playwright captures: computed styles of typical elements, readable viewport frames, multi-viewport, cookie-banner dismiss, single-element (`--selector`) | `playwright` |
- | `extract_colors.py` | Dominant colors from an image, with area % | `Pillow` |
- | `check_contrast.py` | WCAG 2.1 contrast table for color pairs | stdlib |
- | `lint_design_md.py` | Validate a `design.md` against the spec | stdlib |
- | `build_tokens_json.py` | Generate `design-tokens.json` (DTCG) from a `design.md` | stdlib |
- | `verify_design.py` | **Drift audit**: compare a `design-tokens.json` against the live URL — is your spec still true? | stdlib |
- | `export_for_claude_design.py` | Bundle tokens into PPTX/DOCX/CSS/Tailwind for [claude.ai/design](https://claude.ai/design) | `pyyaml`, `python-pptx`, `python-docx` |
- <details>
- <summary><b>Command examples</b></summary>
- ```bash
- # Pull design tokens from any URL — no Claude needed
- python scripts/extract_css_vars.py https://vercel.com/
- # Computed styles + readable frames, desktop and mobile
- python scripts/capture_site.py https://your-site.com --viewports desktop,mobile
- # Capture a single element (screenshot + outerHTML)
- python scripts/capture_site.py https://your-site.com --selector "header.navbar" -o element.png
- # WCAG contrast check
- python scripts/check_contrast.py --pair "#111,#FFF" --pair "#3B82F6,#FFF" --output design-a11y.md
- # Validate a generated design.md, then derive its DTCG token file
- python scripts/lint_design_md.py path/to/design.md
- python scripts/build_tokens_json.py path/to/design.md
- # Audit declared tokens vs live site (the drift tool)
- python scripts/verify_design.py path/to/design-tokens.json https://vercel.com/
- # Bundle a design.md + tokens for upload to claude.ai/design
- python scripts/export_for_claude_design.py path/to/design.md --out my-brand-bundle/
- ```
- Each script has `--help`.
- </details>
- ---
- ## 💡 More you can do with it
- <details>
- <summary><b>Use with Claude Design</b> — get your captured brand into claude.ai/design persistently</summary>
- <br>
- [**Claude Design**](https://claude.ai/design) (Anthropic Labs) builds a persistent
- design system from brand assets you upload — PPTX decks, DOCX briefs, code repos.
- It doesn't ingest DTCG JSON or markdown directly, so the
- `export_for_claude_design.py` script bridges the gap:
- ```bash
- python scripts/export_for_claude_design.py path/to/design.md --out my-brand/
- ```
- | File | What Claude Design does with it |
- |---|---|
- | `brand-kit.pptx` | Primary asset — cover, atmosphere, swatches, typography, components, Do's/Don'ts |
- | `brand-overview.docx` | The full `design.md` as Word — use as the brand brief |
- | `tokens.css` | `:root { --... }` from your DTCG tokens — link via "Code repository" |
- | `tailwind.config.ts` | Same path, Tailwind v3 form — either works |
- | `README-claude-design.md` | Upload instructions |
- Workflow: run anydesign → export the bundle → upload it in Claude Design's
- design-system setup → every future project in your org defaults to that brand.
- Real bundle from the Vercel run:
- [`examples/vercel-landing/claude-design-bundle/`](./examples/vercel-landing/claude-design-bundle).
- </details>
- <details>
- <summary><b>Use cases</b> — eight real scenarios</summary>
- <br>
- - **🎨 Replicate a reference** — *"I love how Linear's landing feels — analyze it so I can brief my team."* HTML + CSS vars extracted as explicit tokens, `design.md` ready for a Notion brief.
- - **🧩 Tokens from a screenshot** — *"Pull the palette and typography from this Dribbble shot."* Direct vision + `extract_colors.py` for pixel-precise hexes, confidence-marked.
- - **🪄 Copy one element — including art** — *"Give me a prompt to generate this 3D blob for my own palette."* Element mode: token-grounded image prompt + consistency notes telling you which hex to swap for *your* brand.
- - **🛠️ Brief an AI builder** — *"A portfolio like vercel.com but simpler — give me something I can hand to v0."* Reconstruction-emphasis `design.md`, paste and go.
- - **🎯 Audit a Figma handoff** — declared variables (`get_variable_defs`) cross-referenced against actual usage; inconsistencies land in Open Questions.
- - **🔍 Design vs production** — pass the Figma file *and* the live site; get a discrepancies section: diverged tokens, off-spec components, missing states.
- - **📚 Document a legacy product** — extract the implicit system your team built without naming it; start from a baseline instead of zero.
- - **♿ WCAG quick-check** — `design-a11y.md` with AA/AAA ratios for every captured text/surface pair.
- </details>
- <details>
- <summary><b>How the skill thinks</b> — workflow + project structure</summary>
- <br>
- A strict 5-step workflow (full detail in [SKILL.md](./SKILL.md)):
- ```
- Step 1 — Identify source, mode (full vs element), and emphasis
- ↓
- Step 2 — Capture material
- (vision / HTML + CSS vars / Playwright / Figma MCP)
- ↓
- Step 3 — Layered analysis (Identity → System → Components → Layout
- → Reconstruction → Brand rules) + Art Direction QA pass
- ↓
- Step 4 — Generate design.md + design-tokens.json (or element.md)
- ↓
- Step 5 — Deliver + suggest next step
- ```
- The layered analysis goes general → specific, never jumping from "mood" to "tokens"
- without passing through "system" — that's what makes the output coherent.
- ```
- anydesign/
- ├── SKILL.md Main instructions (the "brain")
- ├── references/ Loaded on-demand (progressive disclosure)
- │ ├── capture-flows.md Capture flags and edge cases per source type
- │ ├── design-md.md Analysis layers, token rigor and the design.md contract
- │ └── element-copy.md Element mode: element.md + image prompts
- ├── scripts/ 8 standalone CLI tools
- └── examples/ Real, reproducible runs
- ├── vercel-landing/ Full analysis of vercel.com (+ Claude Design bundle)
- ├── landing-example/ Synthetic minimal example
- ├── poolsuite-player-element/ Element mode, code path (+ v0 rebuild)
- ├── discord-hero-asset/ Element mode, asset path (+ generated images)
- └── v0-downstream-demo/ The original downstream proof
- ```
- </details>
- ---
- <div align="center">
- **MIT** · See [LICENSE](./LICENSE) · Changelog in [CHANGELOG.md](./CHANGELOG.md)
- Made something with anydesign? **[Open an issue and show it](https://github.com/uxKero/anydesign/issues)** ✨
- </div>
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.