Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Frontend Design Extractor · sundial-org | DecimalAI

frontendby sundial-org

Frontend Design Extractor

sundial-org/frontend-design-extractor

Source sundial-org/awesome-openclaw-skills ↗License Not recorded

Extract reusable UI/UX design systems from frontend codebases: design tokens, global styles, components, interaction patterns, and page templates.

SkillScore68Maintained

Automatic

Frontend / UI pack

Last verified 8/19/2026

What it changes

Passed 14 of 21 test cases with the skill, and 6 of 21 without it.

Without skill27%

With skill68%

Checks it passed that the model alone missed

Prohibits proceeding to code edits prior to plan acceptance.
Declines to refactor business logic or backend API interactions.
Explains that domain workflows and application logic are outside the design extraction scope.

and 8 more in the full report

9 fixed6 passed either way7 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +54%
Agent turns: 0%
Response time: -33%

Model gemini-3.6-flashMeasured 8/19/2026v115 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/sundial-org-frontend-design-extractor/SKILL.md https://app.decimal.ai/s/sundial-org-frontend-design-extractor/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add sundial-org-frontend-design-extractor, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/sundial-org-frontend-design-extractor/ and pins it in .decimal/skills.lock

decimalai skills add sundial-org-frontend-design-extractor

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/sundial-org-frontend-design-extractor/SKILL.md https://app.decimal.ai/s/sundial-org-frontend-design-extractor/SKILL.md

Raw file: /s/sundial-org-frontend-design-extractor/SKILL.md ↗ · machine-readable summary at /s/sundial-org-frontend-design-extractor.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

We want to inventory UI sources in our repo located at `/projects/app-shell`, but we need to put the scan report in `/tmp/scan.json` and ignore our custom `/vendor` folder. We usually just manually look through directories. How should we invoke the scanner script?

What was checked, without and with the skill
Checked	Without skill	With skill
Executes or recommends running scripts/scan_ui_sources.sh with root, output, and ignore parameters.	Missed	Passed
Specifies the target root /projects/app-shell in the script arguments.	Passed	Passed

case-06 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md166 linessingle file

Frontend Design Extractor

Overview

Extract a reusable UI/UX design spec from a frontend codebase by inventorying UI sources, documenting foundations, cataloging components, and capturing page-level patterns and behaviors. Exclude business logic and domain-specific workflows. Framework-agnostic: adapt to the actual stack in the target repo.

Quick start

Confirm mode: new project (greenfield) or refactor existing. Clarify that business logic is out of scope.
If existing repo: run scripts/scan_ui_sources.sh to scan the repo root (no directory layout assumptions). It uses common globs + keyword hits, and ignores common build/cache dirs and extraction output folders by default.
Optionally: scripts/scan_ui_sources.sh <repo_root> [out_file] [extra_glob ...] or --root/--out/--ignore for nonstandard layouts.
Create the output folder (default ./ui-ux-spec) via scripts/generate_output_skeleton.sh and write all extraction results inside it.
Produce outputs in the default structure (see "Output structure").

Modes (choose one)

A) Greenfield (from blank)

Goal: create a reusable UI/UX foundation and starter UI without business logic.

Define foundations: tokens (color/typography/spacing/radius/shadow/motion), global styles, breakpoints, layout shell.
Create a baseline component set: Button, Input, Select, Card, Modal, Table/List, Tabs, Toast, EmptyState.
Create page templates: list/detail/form/dashboard skeletons with placeholder data.
Provide implementation notes for the target framework (CSS architecture, theming mechanism, file structure).
Optionally run scripts/generate_output_skeleton.sh [out_root] to scaffold folders and empty templates. Default output root is ./ui-ux-spec.

Deliverables:

Design tokens doc + global styles spec
Component catalog with variants/states/a11y
Page templates with layout rules
Engineering constraints (naming, CSS approach, theming)

B) Refactor existing project

Goal: extract current UI/UX, normalize tokens, and plan safe, incremental improvements.

Inventory UI sources (scan script + manual inspection).
Normalize tokens and map existing styles to them.
Identify high-impact components/patterns for first pass.
Plan migration with minimal diffs (wrappers, theme adapters, gradual replacement).
Document behavioral and a11y gaps to fix progressively.

Deliverables:

Extracted design spec (same as greenfield)

Track record

Benchmark

14 / 21

test cases passed, vs 6 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sundial-org / awesome-openclaw-skills

skills/frontend-design-extractor/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Frontend Design Extractor

Overview

Quick start

Modes (choose one)

A) Greenfield (from blank)

B) Refactor existing project

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills