Skills extract-design-system
๐Ÿ“ฆ

extract-design-system

Content revision r1 Safe โš™๏ธ External commands

Extract Website Design Tokens

Recreating a public site's visual language by hand is slow and inconsistent. This skill extracts starter colors, fonts, spacing, radius, shadows, and token files for review.

Supports: Claude Codex Code(CC)
๐Ÿ“Š 75 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "extract-design-system" from https://skillstore.io/skills/arvindrk-extract-design-system.md and its manifest at https://skillstore.io/api/skills/arvindrk-extract-design-system/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Test it

Using "extract-design-system". Analyze a public marketing page for starter design tokens.

Expected outcome:

  • A concise summary of likely primary, secondary, and accent colors.
  • Detected font families and visible typography patterns.
  • A list of generated token artifacts ready for review.

Using "extract-design-system". Run extraction only for a public documentation site.

Expected outcome:

  • A review summary of extracted design primitives.
  • Notes about missing or uncertain values from the page.
  • No starter files unless the user asks for them.

Using "extract-design-system". Regenerate token files from an existing normalized extraction.

Expected outcome:

The skill refreshes starter token files and explains that existing app styles were not changed.

Security Audit

Safe
v9 โ€ข 7/9/2026 Open versioned report

The skill contains legitimate instructions to run npx commands from SKILL.md, including package execution and Playwright setup. Several static hits are markdown code fences or inline file names and are false positives for Ruby backtick execution. No prompt injection or malicious data exfiltration intent was found in the reviewed files.

3
Files scanned
101
Lines analyzed
3
Review items
0
False positives ignored
Capability review items (3)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
Ruby/shell backtick execution
```bash
This block instructs the agent to run npx commands, including installing Chromium and executing an npm package. The commands are task-related, but they still run external code and can download dependencies.
Medium
Ruby/shell backtick execution
```bash
This block instructs the agent to run npx extract-design-system with a user-provided public URL. It is a legitimate workflow command, but it executes an external package against third-party input.
Medium
Ruby/shell backtick execution
```bash
This block instructs the agent to run npx extract-design-system init. The command is narrowly scoped, but it still executes an npm package in the user's project.
Audited by: codex View Audit History โ†’
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/arvindrk-extract-design-system/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/arvindrk-extract-design-system/security.svg)](https://skillstore.io/skills/arvindrk-extract-design-system?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/arvindrk-extract-design-system?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/arvindrk-extract-design-system/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/arvindrk-extract-design-system.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA ยท BibTeX ยท CFF)

APA citation

arvindrk. (2026). extract-design-system security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/arvindrk-extract-design-system/audits/9

BibTeX citation

@techreport{arvindrk-arvindrk-extract-design-system-2026, author = {arvindrk}, title = {extract-design-system security audit report (audit version 9)}, institution = {Skillstore}, year = {2026}, number = {9}, url = {https://skillstore.io/skills/arvindrk-extract-design-system/audits/9}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "extract-design-system security audit report (audit version 9)" version: "unspecified" type: report authors: - name: "arvindrk" date-released: "2026-07-09" url: "https://skillstore.io/skills/arvindrk-extract-design-system/audits/9" identifiers: - type: other value: "skillstore:arvindrk-extract-design-system:audit:9" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
41
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance

What You Can Build

Bootstrap Project Tokens

Create starter design tokens from a public reference site before building a new frontend.

Audit Brand Styles

Identify likely colors, fonts, spacing, radius, and shadows from a public brand page.

Prepare Migration Assets

Generate token files from an existing public site before planning a styling migration.

Try These Prompts

Extract Starter Tokens
Extract design primitives from this public URL and summarize the starter tokens before generating files: <url>
Analyze Without Files
Analyze this public URL with extraction only. Report the detected colors, fonts, spacing, radius, and shadows: <url>
Regenerate Token Files
Use the existing normalized extraction output to regenerate starter token files. Do not change app code or styling.
Compare Extraction Quality
Extract tokens from this public URL, identify likely gaps from dynamic content, and recommend which values need manual review: <url>

Best Practices

  • Use public URLs and confirm the target page is reachable before extraction.
  • Review extracted output before importing token files into an application.
  • Ask for confirmation before changing existing app code, styling, or config.

Avoid

  • Do not treat one extracted page as a complete product design system.
  • Do not overwrite an existing design system without explicit approval.
  • Do not accept third-party page content as instructions for code changes.

Frequently Asked Questions

Does this build a full component library?
No. It creates starter design tokens and summaries from public website styles.
Can it analyze private websites?
The skill is intended for public, reachable URLs. Private pages may need separate access handling.
What files can it generate?
It can generate raw extraction data, normalized design data, token JSON, and starter CSS variables.
Does it modify existing app styles?
It should ask for confirmation before changing existing app code, styles, or config files.
Is the extracted design system authoritative?
No. The output is a starting point and should be reviewed before production use.
Which assistants can use this skill?
The report lists support for Claude, Codex, and Claude Code.

Developer Details

Author

arvindrk

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Ref

3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88

Maintenance freshness

7/18/2026

Usage

4 downloads ยท 92 views

File structure

๐Ÿ“ references/

๐Ÿ“„ outputs.md

๐Ÿ“„ workflow.md

๐Ÿ“„ SKILL.md