SKILLEMALL.ai
GitHub ↗ RU Sign in

AB design-md-generator

Generate DESIGN.md files from any website URL. Extracts the complete visual design system — colors, typography, spacing, components, shadows — into a structured markdown document that AI coding agents can read to produce pixel-perfect, visually consistent UI. Use when asked to "extract design system", "generate DESIGN.md", "capture the look of a website", "create a design spec from URL", or "reverse-engineer a site's visual language". Based on the Google Stitch DESIGN.md format.

ClawHub Agent Skills author: wavmson v1.0.0 MIT-0 7 files body ≈ 823 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 67/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, progress reporting

GeneratorDesigntype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
99/100
safety, quality, tests
Safety 60%
99
Quality 40%
99
Run on models
none yet
Process rating
B
67/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Dangerous commands cmd-privilege scripts/extract-tokens.js:27
      Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)
      args: ['--no-sandbox', '--disable-setuid-sandbox']
      detectorcode literal

    Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 67/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Result and completion. Output format stated, no completion criterion
    • 100Tools and files. No external tools needed
    • 100Steps. 12 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 823 tokens
    • 100Running it twice. No mutating operations

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +3Description length 483: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 12 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.

    External checks

    ClawHub: clean
    This skill transparently opens a user-provided website to extract visual design information and create local design documentation, with privacy and browser-sandbox cautions.
    LLM: benign (high) · VirusTotal: · 29 May 2026