Design Review Panel

What it does

When your agent uses it

• Redesigning a screen/modal/dialog and the user wants grounded
• Scored design feedback (summon the design panel
• Rate this with the experts
• Run the persona panel)

Example prompts

• “summon the design panel”
• “rate this with the experts”
• “run the persona panel”
• “/design-review-panel”

Requirements

• Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Baseline screenshot first. Use the app-screenshots skill / the
2. 2Rate the baseline with BOTH panels up front. Get grounded starting
3. 3Iterate with the expert panel until experts clear the bar. Bring the
4. 4Adjudicate genuine tradeoffs with the user (AskUserQuestion) instead
5. 5Harden to PR-ready once converged: tests, l10n, feature README, a

What it can do on your machine

Read from SKILL.md and the folder at commit a80a35f. 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

  Ships script files (JavaScript), which the agent can run.

  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

Design Review Panel loads about 1.6k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 660 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~140

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

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

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 matthiasn/lotti at commit a80a35f, republished under its GPL-3.0 licence (© matthiasn). 660 words, ~1,591 tokens.

name

design-review-panel

description

Run a multi-agent design review on a UI surface — capture reproducible baseline screenshots, then rate them with a panel of design experts (one agent per craft dimension) and, optionally, a panel of user personas with different cognitive styles. Iterate implement → re-screenshot → re-rate until every panel hits a numeric target (e.g. avg ≥8/10). Use when polishing or redesigning a screen/modal/dialog and the user wants grounded, scored design feedback ("summon the design panel", "rate this with the experts", "run the persona panel").

argument-hint

<surface to review, e.g. 'AI popup model picker'>

stateDiagram-v2
    [*] --> Baseline
    Baseline --> RateBaseline: capture reproducible PNGs (app-screenshots)
    RateBaseline --> Implement: both panels score the current state
    Implement --> Rescreenshot: apply highest-leverage fixes (design-system tokens only)
    Rescreenshot --> Rerate: regenerate the SAME shots
    Rerate --> Implement: either panel average < target
    Rerate --> Harden: both panel averages ≥ target
    Harden --> [*]: tests, l10n, README, changelog.d fragment, analyzer clean, PR

Workflow({ scriptPath: ".claude/skills/design-review-panel/panel_workflow.js", args: { ...see file header... } })

© matthiasn, GPL-3.0. 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 1 other file in .claude/skills/design-review-panel of matthiasn/lotti.

• SKILL.md
• panel_workflow.js

Open the folder on GitHubat commit a80a35f