Edge Copy setup link
Skill evidence / stitch::extract-design-md
Skill profile

stitch::extract-design-md

Extract a comprehensive design system (DESIGN.md) directly from frontend source code : React.

What this skill does for you

Extract a comprehensive design system (DESIGN.md) directly from frontend source code : React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce a rich, Stitch-compatible design system document. Use this skill whenever the user wants to reverse-engineer a design system from an existing codebase, audit the visual language of a project, extract design tokens from source files, or understand the styling patterns in a frontend repo : even if they just say "what does this app look like?" or "pull out the design from this code."

Quoted from the skill description in the pinned source

Who made it

Publishergoogle-labs-code
Repositorystitch-skills
Installs9,000as of Sep 27, 2026

Use it with Edge

Bring this skill into your Edge workflow. Read the pinned instructions to check its setup.

Security evidence

3 static scans, 0 counted findings. What this means: the listed scanners recorded the results shown for this package revision.

ScannerDateResultFindings
Edge static checks2026-09-27Pass0
Cisco skill-scanner2026-09-27Pass0
Semgrep Edge rules2026-09-27Pass0

Static scans check the code, not how well the skill works.

Scanner scope, raw findings and mirrored provider records

Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Revision: 0337446dadde6f8c94210444e2aa9d546126480f. Raw findings: . Counted findings: .

Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Revision: 0337446dadde6f8c94210444e2aa9d546126480f. Raw findings: 2. Counted findings: .

Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Revision: 0337446dadde6f8c94210444e2aa9d546126480f. Raw findings: . Counted findings: .

Source and licence

Repository
https://github.com/google-labs-code/stitch-skills
Pinned skill file
View source at revision
Revision
0337446dadde6f8c94210444e2aa9d546126480f
Package hash
sha256:bd8c401c5510b271b3c0957d34d74e6ea4019714e91aa6c4b3f541d25cbe5aaf
Licence
Apache-2.0