Web Design
xiaopu-ai/web-design
Web 视觉设计 SKILL。输入 PRD / 参考 URL / 截图 / 关键词（任意组合），先产出一份标准化 DESIGN.md 设计规范，用户确认后据此生成 UI/UX、视觉、动效、响应式全部达标的 web 代码。专攻 web 端：Landing Page、Portfolio、产品页、博客、个人站、SaaS 介绍页等。当用户说"帮我做个网站""设计一个页面""参考 XX…
A skill your agent uses when a user provides a reference UI screenshot and asks to extract visual specs, generate design tokens, create a component tree, or produce a frontend implementation…
Install Visual To Spec
$ npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Jason904/ui-skill-lab visual-to-spec --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Jason904/ui-skill-lab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/visual-to-spec .claude/skills/visual-to-spec && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "visual-to-spec" agent skill from https://github.com/Jason904/ui-skill-lab/tree/main/skills/visual-to-spec into .claude/skills/visual-to-spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-to-spec", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Jason904/ui-skill-lab/tree/main/skills/visual-to-specType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Jason904/ui-skill-lab visual-to-spec --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jason904/ui-skill-lab.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/visual-to-spec .agents/skills/visual-to-spec && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "visual-to-spec" agent skill from https://github.com/Jason904/ui-skill-lab/tree/main/skills/visual-to-spec into .agents/skills/visual-to-spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-to-spec", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Jason904/ui-skill-lab visual-to-spec --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jason904/ui-skill-lab.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/visual-to-spec .cursor/skills/visual-to-spec && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "visual-to-spec" agent skill from https://github.com/Jason904/ui-skill-lab/tree/main/skills/visual-to-spec into .cursor/skills/visual-to-spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-to-spec", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Jason904/ui-skill-lab.git --path skills/visual-to-spec--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Jason904/ui-skill-lab visual-to-spec --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jason904/ui-skill-lab.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/visual-to-spec .gemini/skills/visual-to-spec && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "visual-to-spec" agent skill from https://github.com/Jason904/ui-skill-lab/tree/main/skills/visual-to-spec into .gemini/skills/visual-to-spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-to-spec", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Jason904/ui-skill-lab visual-to-specInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Jason904/ui-skill-lab.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/visual-to-spec .github/skills/visual-to-spec && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "visual-to-spec" agent skill from https://github.com/Jason904/ui-skill-lab/tree/main/skills/visual-to-spec into .github/skills/visual-to-spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-to-spec", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Jason904/ui-skill-lab visual-to-spec --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jason904/ui-skill-lab.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/visual-to-spec .opencode/skills/visual-to-spec && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "visual-to-spec" agent skill from https://github.com/Jason904/ui-skill-lab/tree/main/skills/visual-to-spec into .opencode/skills/visual-to-spec/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-to-spec", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
visual-to-spec- GitHub stars
- 144
- Token cost
- ~1.6k tokens
- SKILL.md length
- 694 words
- Files
- 12 (incl. references)
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a user provides a reference UI screenshot and asks to extract visual specs, generate design tokens, create a component tree, or produce a frontend implementation…
- Works in 12 steps: Every extracted value must include… → reference-visible must include bbox or… → Phase 1 must output uiType, one of:… → …
- A user provides a reference UI screenshot and asks to extract visual specs
- SKILL.md covers Trigger Conditions, Required Inputs, Outputs and Source of Truth, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Visual To Spec is an agent skill from Jason904/ui-skill-lab. Use when a user provides a reference UI screenshot and asks to extract visual specs, generate design tokens, create a component tree, or produce a frontend implementation contract, including dashboards, landing pages, mobile screens, image-led UIs, panorama scenes, 3D exhibit UIs, and screenshot-to-spec tasks.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `README.md`, `examples/component-tree.example.md` and `examples/human-review-needed.example.md`).
It sits in Frontend & Design, covering Design tokens, Landing pages and Mobile UI design. The repository describes itself as: AI-driven UI development skill pipeline — test lab for Codex skills covering PRD-to-pixel workflow. The licence is MIT.
When your agent uses it
- A user provides a reference UI screenshot and asks to extract visual specs
- Generate design tokens
- Create a component tree
- Produce a frontend implementation contract
Example prompts
- “/visual-to-spec”
Workflow steps
12 steps, taken from the first numbered list in SKILL.md.
- Every extracted value must include source, confidence, confidenceLabel, and strictness.
- reference-visible must include bbox or reference bbox within the same component detail; visibility claims without bbox are invalid.
- Phase 1 must output uiType, one of: application-dashboard, panorama-scene, image-led-landing, mobile-app, poster-like-ui, unknown.
- If uiType is panorama-scene or image-led-landing, phases 5/6 must use the image layer + overlay layer layout model.
- Components not present in the screenshot must be listed in Rejected Assumptions, not placed in the component tree.
- Values with confidence < 0.6 must appear in human-review-needed.md; low-confidence layout type must go into human review even if…
- Every color in the component tree must exist in tokens.json.
- Every component dimension must match layout-spec.md.
- Sum of sibling component widths must not exceed parent container width; overlay components must verify bbox does not overflow.
- Typography scale must decrease monotonically: h1 > h2 > h3 > body.
- No orphan tokens (defined but unused).
- No missing tokens (used in component tree but undefined).
What it can do on your machine
Read from SKILL.md and the folder at commit a71b4e2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Visual To Spec loads about 1.6k tokens when it runs, and up to ~8.8k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 694 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Jason904/ui-skill-lab at commit a71b4e2, republished under its MIT licence (© Jason904). 694 words, ~1,629 tokens.
Download SKILL.mdSave it as
.claude/skills/visual-to-spec/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- visual-to-spec
- description
- Use when a user provides a reference UI screenshot and asks to extract visual specs, generate design tokens, create a component tree, or produce a frontend implementation contract, including dashboards, landing pages, mobile screens, image-led UIs, panorama scenes, 3D exhibit UIs, and screenshot-to-spec tasks.
- argument-hint
- [reference-image]
Version: 2.0.0
visual-to-spec
Convert a finalized UI screenshot into a complete frontend implementation contract.
Trigger Conditions
- User provides a UI screenshot and asks to extract visual specs
- User asks to generate design tokens from a screenshot
- User asks to build a component tree or frontend implementation contract from a screenshot
- User asks to analyze screenshot layout, color, typography, spacing, overlay controls, or panorama/3D scene UI
- Keywords: "extract spec from screenshot", "image to design spec", "screenshot to spec"
Required Inputs
| Item | Description |
|---|---|
| reference.png | Finalized UI screenshot (the only required input) |
| Project token standards | Optional, adapt to existing standards if available |
Outputs
All files written to 03_visual_spec/ directory:
| File | Content |
|---|---|
| visual-analysis.md | UI type, visible element evidence, composition, color, typography, spacing analysis |
| layout-spec.md | Layout positioning and sizing spec, branching by UI type |
| component-tree.md | Hierarchical component tree with per-component style summaries |
| tokens.json | DTCG-inspired design tokens with source/confidence annotations |
| implementation-risks.md | Implementation risk assessment |
| human-review-needed.md | Low-confidence items and manual review checklist |
| DESIGN.md | Summary document referencing all above files |
See references/output-files.md for detailed output formats.
Source of Truth
reference.png is the sole visual source of truth.
- Do not redesign.
- Do not treat UI elements invisible in the screenshot as screenshot facts.
- Do not introduce colors, fonts, spacing, panels, charts, or navigation structures absent from the image.
- Do not default to a dashboard / SaaS / three-column layout; UI type determination must come first.
reference-visiblecomponents must have bbox and visual evidence in the screenshot; components without bbox must not be labeledreference-visible.- Inferred implementation wrapper components (e.g., AppShell, MainContent, SceneImageLayer, OverlayLayer) are permitted but must be labeled
source: inferred-implementation. - For image-led, panorama-scene, 3D exhibit, and product-render screenshots, output an asset strategy: which visual content must be raster/image assets, and which can be implemented as HTML/CSS/SVG.
All values must carry source and confidence annotations.
See references/source-strictness-rules.md for complete rules.
Phase Overview (9 phases, sequential)
| # | Phase | Key Output |
|---|---|---|
| 1 | Global composition analysis + UI type determination + visible element evidence | visual-analysis.md §1 |
| 2 | Color extraction | visual-analysis.md §2 + tokens.json (color) |
| 3 | Typography extraction | visual-analysis.md §3 + tokens.json (typography) |
| 4 | Spacing and grid system | visual-analysis.md §4 + tokens.json (spacing) |
| 5 | Layout specification | layout-spec.md |
| 6 | Component tree construction | component-tree.md |
| 7 | Token merge and validation | tokens.json (final) |
| 8 | Implementation risk assessment | implementation-risks.md |
| 9 | Human review checklist | human-review-needed.md |
See references/extraction-workflow.md for detailed workflow.
Show full SKILL.md (321 more words)Show less
Hard Rules
- Every extracted value must include
source,confidence,confidenceLabel, andstrictness. reference-visiblemust include bbox or reference bbox within the same component detail; visibility claims without bbox are invalid.- Phase 1 must output
uiType, one of:application-dashboard,panorama-scene,image-led-landing,mobile-app,poster-like-ui,unknown. - If
uiTypeispanorama-sceneorimage-led-landing, phases 5/6 must use the image layer + overlay layer layout model. - Components not present in the screenshot must be listed in Rejected Assumptions, not placed in the component tree.
- Values with confidence < 0.6 must appear in
human-review-needed.md; low-confidence layout type must go into human review even if confidence >= 0.6. - Every color in the component tree must exist in tokens.json.
- Every component dimension must match layout-spec.md.
- Sum of sibling component widths must not exceed parent container width; overlay components must verify bbox does not overflow.
- Typography scale must decrease monotonically: h1 > h2 > h3 > body.
- No orphan tokens (defined but unused).
- No missing tokens (used in component tree but undefined).
Capability Boundaries
See references/script-backed-boundary.md for detailed boundary definition.
| Category | Examples |
|---|---|
| LLM can do | Visual recognition, UI type determination, color estimation, layout judgment, component classification, proportion estimation |
| Script-assisted | Precise color values, WCAG contrast, delta-E, exact pixel measurement, bbox measurement, visual regression comparison |
| Human confirmation | Low-confidence colors, ambiguous component boundaries, uncertain font identification, whether the main visual needs real assets |
When scripts are unavailable, LLM does best-effort estimation and annotates confidence and notes.
Supporting Files Index
references/
extraction-workflow.md— 9-phase detailed workflow, UI type branching, asset strategy rulestoken-schema.md— Token JSON schema definition and field descriptionsoutput-files.md— Structure templates for each output filesource-strictness-rules.md— Complete rules for source/confidence/strictness/bbox labelsscript-backed-boundary.md— Boundary definitions for LLM / script / human operations
examples/
tokens.example.json— Complete tokens.json examplecomponent-tree.example.md— Component tree example, including panorama-scene vs dashboard branchinglayout-spec.example.md— Layout spec example, including overlay coordinate modelvisual-analysis.example.md— Visual analysis example, including UI type, visible elements, rejected assumptionshuman-review-needed.example.md— Human review checklist example
© Jason904, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files (references) in skills/visual-to-spec of Jason904/ui-skill-lab.
- SKILL.md
- README.md
- examples/component-tree.example.md
- examples/human-review-needed.example.md
- examples/layout-spec.example.md
- examples/tokens.example.json
- examples/visual-analysis.example.md
- references/extraction-workflow.md
- references/output-files.md
- references/script-backed-boundary.md
- references/source-strictness-rules.md
- references/token-schema.md
Open the folder on GitHubat commit a71b4e2
Compare with similar skills
Visual To Spec next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Visual To Spec this skillJason904/ui-skill-lab | 144 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Web Designxiaopu-ai/web-design | 783 | — | ~3k | Automated safety check: Pass | MIT | |
| Refactoring UIs0xDk/refactoring-ui-skill | 595 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Web Designdrewnekota/cetus | 146 | — | ~2.1k | Automated safety check: Pass | MIT | |
| iOS Design GuidelinesMacMagazine/app-iOS | 170 | — | ~767 | Automated safety check: Pass | None | |
| Atlaspacifio/ui | 154 | — | ~2.5k | Automated safety check: Pass | MIT |
Similar skills
Refactoring UI
s0xDk/refactoring-ui-skill
Design and improve user interfaces using the concrete rules from Refactoring UI (Wathan & Schoger) — constrained spacing/type/color/shadow scales, visual hierarchy through weight and color rather…
Web Design
drewnekota/cetus
A skill your agent uses when building any web page, HTML artifact, landing page, dashboard, slide deck, report, email, or UI component the user will look at.
iOS Design Guidelines
MacMagazine/app-iOS
MacMagazine design reference — theme tokens, card selection, typography, touch targets, accessibility, dark mode.
Atlas
pacifio/ui
Atlas — a design language and UI guide system for agent interfaces.
Frontend Design
avibebuilder/claude-prime
Builds distinctive, production-grade UIs that avoid generic AI aesthetics.
More from Jason904/ui-skill-lab
All 8 skills in this repoImage2 Prompt Pack
Jason904/ui-skill-lab
This skill should be used when the user asks to convert a PRD, OpenSpec change, or product idea into a structured GPT Image 2 UI prompt pack for generating high-fidelity flat UI reference images.
UI UX Pro Max Skill
Jason904/ui-skill-lab
A skill your agent uses for UI/UX design intelligence in Codex: planning, building, reviewing, improving, or implementing web/mobile interfaces, landing pages, dashboards, design systems…
Design System Governor
Jason904/ui-skill-lab
This skill should be used after visual-spec-review passes and before OpenSpec UI update or frontend implementation.
Spec Compliance Review
Jason904/ui-skill-lab
This skill should be used after Codex implements a UI change and before visual acceptance review.
Visual Acceptance Review
Jason904/ui-skill-lab
This skill should be used after spec-compliance-review and before visual-diff-fix.
Visual Diff Fix
Jason904/ui-skill-lab
This skill should be used after visual-acceptance-review has generated fix-tasks.json.
Related
Categories
Questions about Visual To Spec
What does Visual To Spec do?
A skill your agent uses when a user provides a reference UI screenshot and asks to extract visual specs, generate design tokens, create a component tree, or produce a frontend implementation…. Visual To Spec is an agent skill from Jason904/ui-skill-lab. Use when a user provides a reference UI screenshot and asks to extract visual specs, generate design tokens, create a component tree, or produce a frontend implementation contract, including dashboards, landing pages, mobile screens, image-led UIs, panorama scenes, 3D exhibit UIs, and screenshot-to-spec tasks.
When should I use Visual To Spec?
Visual To Spec fits situations like: A user provides a reference UI screenshot and asks to extract visual specs; generate design tokens; create a component tree; produce a frontend implementation contract.
How do I install Visual To Spec in Claude Code?
Run `npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a claude-code`. Or copy the skill folder (skills/visual-to-spec in Jason904/ui-skill-lab) into .claude/skills/visual-to-spec in your project. Claude Code loads it when a task matches its description.
How do I install Visual To Spec in Codex?
Run `npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a codex`. Or copy the skill folder (skills/visual-to-spec in Jason904/ui-skill-lab) into .agents/skills/visual-to-spec in your project. Codex loads it when a task matches its description.
Can I use Visual To Spec in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Jason904/ui-skill-lab --skill visual-to-spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visual-to-spec, .gemini/skills/visual-to-spec, .github/skills/visual-to-spec and .opencode/skills/visual-to-spec in your project.
What does Visual To Spec need to run?
SKILL.md names no scripts, command-line tools or credentials: Visual To Spec is instructions for the agent only.
Does Visual To Spec access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Visual To Spec safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Visual To Spec use?
Visual To Spec is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Visual To Spec use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.1k tokens, read only when the agent opens those files.
What are the alternatives to Visual To Spec?
Skills that share tags, products or a category with Visual To Spec: Web Design (xiaopu-ai/web-design, 783 stars), Refactoring UI (s0xDk/refactoring-ui-skill, 595 stars), Web Design (drewnekota/cetus, 146 stars) and iOS Design Guidelines (MacMagazine/app-iOS, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Visual To Spec?
Jason904 (a GitHub user) maintains it in Jason904/ui-skill-lab, which has 144 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on June 29, 2026.
Source: Jason904/ui-skill-lab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.