Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

design-review

skill · julianoczkowski/designer-skillsApache-2.0 licenceAudited 23 Oct 2026 · source 80a50dfcaf5a

★ 590pushed 108 days ago
✓SAFEGrade B · 89/100 · 23 Oct 2026 · 80a50df
590repo stars · whole julianoczkowski/designer-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 80a50dfcaf5a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Run a structured design critique against the brief and codebase. Checks visual hierarchy, consistency, responsiveness, accessibility, and aesthetic fidelity. Use when user wants a design review, critique, QA pass,…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “design-review (julianoczkowski/designer-skills)”. Retrieved 23 Oct 2026. https://modelsatlas.com/skills/julianoczkowski/design-review

5 skills are called “design-review”. You are viewing julianoczkowski/designer-skills.

Trust audit

Audit 0.4.1 · source read 23 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 80a50dfcaf5a · 23 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherjulianoczkowski GitHub userOwner of the repository this skill is read from
  • Source folderjulianoczkowski/designer-skills/design-reviewThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict80a50dfcaf5aA new audit runs when the source changes
  • Repository statusNot archivedLast push 108 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Run a structured design critique against the brief and codebase. Checks visual hierarchy, consistency, responsiveness, accessibility, and aesthetic fidelity. Use when user wants a design review, critique, QA pass,…

---
name: design-review
description: Run a structured design critique against the brief and codebase. Checks visual hierarchy, consistency, responsiveness, accessibility, and aesthetic fidelity. Use when user wants a design review, critique, QA pass, polish pass, or mentions "review" after building.
---

This skill runs a structured design review of what has been built, measured against the design brief and the chosen aesthetic philosophy.

> **CRITICAL — Visual Screenshot Capture**
>
> You MUST capture screenshots of the running application as part of every design review. Code review alone is insufficient — you need to see what the user sees. Follow the screenshot capture protocol in Step 3 below. This is not optional.

## Example prompts

- "Review what I just built"
- "Run a design critique on the landing page"
- "Check this against the brief"
- "Here's a screenshot. How does it look?" [paste screenshot]
- "QA pass before I ship this"

## Process

1. **Read the brief.** Look for the active feature's brief at `.design/<feature-slug>/DESIGN_BRIEF.md`. If multiple feature folders exist under `.design/`, ask the user which feature to review. If no `.design/` folder exists, fall back to `DESIGN_BRIEF.md` in the project root. If neither exists, ask the user what the intended design direction was.

2. **Explore the built code.** Examine every component, page, and style file that was created or modified. Scan specifically for:
   - All new or modified components and their relationship to pre-existing components
   - Token/variable usage: are components using shared tokens or hardcoding values?
   - Duplicate components that should be consolidated
   - File naming and organization: do new files follow the project's conventions?
   - Understand what was actually built, not what was planned.

3. **Capture screenshots of the running application.**

   This step is **mandatory**. Do not skip it. Do not rely only on user-provided screenshots.

   ### Screenshot Tool Priority

   Try each option in order. Use the first one that is available:
   1. **Playwright MCP (preferred).** Check if the `plugin-playwright-playwright` MCP server is available. If it is, use it — it gives you precise control over viewport sizing, full-page captures, and file naming.
   2. **Cursor IDE Browser (second choice).** If Playwright MCP is not available, use the `cursor-ide-browser` MCP server's `browser_take_screenshot` tool instead. It has the same core capabilities.
   3. **Ask the user (last resort).** If neither MCP server nor in-app browser is available, you MUST ask the user to provide screenshots manually. Be specific about what you need:
      - "I don't have access to a browser tool. To complete the visual review I need screenshots of the running application. Please provide:"
      - A full-page screenshot at **desktop** width (1280px)
      - A full-page screenshot at **tablet** width (768px)
      - A full-page screenshot at **mobile** width (375px)
      - Dark mode variants (if applicable)
      - Any specific component or interactive state you want reviewed
      - Ask the user to paste/attach the images directly in chat, or to save them into the `screenshots/` folder themselves.
      - **Do not skip the visual review.** Wait for the user to provide screenshots before proceeding with the checklist.

   ### Screenshot Save Location

   All screenshots MUST be saved to a `screenshots/` subfolder inside the feature's `.design/` directory — the same folder where `DESIGN_BRIEF.md` and other design flow files live.

   Path pattern: `.design/<feature-slug>/screenshots/`

   If the brief lives at `.design/onboarding-flow/DESIGN_BRIEF.md`, screenshots go to `.design/onboarding-flow/screenshots/`. Create the folder if it does not exist.

   If no `.design/` folder exists (legacy project or standalone review), fall back to a `screenshots/` folder in the project root.

   Use descriptive filenames that encode what was captured:

   ```
   .design/
   └── onboarding-flow/
       ├── DESIGN_BRIEF.md
       ├── DESIGN_REVIEW.md
       └── screenshots/
           ├── review-homepage-desktop-1280.png
           ├── review-homepage-tablet-768.png
           ├── review-homepage-mobile-375.png
           ├── review-homepage-dark-mode-desktop-1280.png
           └── review-card-component-hover.png
   ```

   ### Screenshot Capture Protocol

   **a. Navigate to the application.** Ask the user for the URL if not obvious from the project (e.g., `http://localhost:3000`). Use `browser_navigate` to open it.

   **b. Capture responsive breakpoints.** At minimum, capture these three viewports for every key page/view:

   | Breakpoint | Width × Height | Filename suffix |
   | ---------- | -------------- | --------------- |
   | Mobile     | 375 × 812      | `-mobile-375`   |
   | Tablet     | 768 × 1024     | `-tablet-768`   |
   | Desktop    | 1280 × 800     | `-desktop-1280` |

   Use `browser_resize` to set the viewport before each screenshot. Use `browser_take_screenshot` with `fullPage: true` to capture the entire scrollable page, and save with the `filename` parameter pointing to the `screenshots/` folder.

   **Playwright MCP example sequence** (assuming feature slug is `onboarding-flow`):

   ```
   1. browser_navigate → { url: "http://localhost:3000" }
   2. browser_resize   → { width: 1280, height: 800 }
   3. browser_take_screenshot → { type: "png", filename: ".design/onboarding-flow/screenshots/review-homepage-desktop-1280.png", fullPage: true }
   4. browser_resize   → { width: 768, height: 1024 }
   5. browser_take_screenshot → { type: "png", filename: ".design/onboarding-flow/screenshots/review-homepage-tablet-768.png", fullPage: true }
   6. browser_resize   → { width: 375, height: 812 }
   7. browser_take_screenshot → { type: "png", filename: ".design/onboarding-flow/screenshots/review-homepage-mobile-375.png", fullPage: true }
   ```

   **c. Capture interactive states (when relevant).**
   - Hover states on buttons,

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 80a50df

Download folder ↗
git clone https://github.com/julianoczkowski/designer-skills
git -C designer-skills checkout 80a50dfcaf5a

The author documents no install command, so this uses the repository directly. Our verdict covers commit 80a50dfcaf5a only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 80a50dfcaf5a

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/julianoczkowski/design-review/badge.svg)](https://modelsatlas.com/skills/julianoczkowski/design-review/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/julianoczkowski/design-review/badge.svg)](https://modelsatlas.com/skills/julianoczkowski/design-review/)

Questions about design-review

What does the design-review skill do?
A collection of agent skills for designers who prototype and build with AI coding tools. These skills encode design process so AI follows a structured path instead of producing random output.
Is design-review safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can design-review access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does design-review work with?
Its documentation mentions cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (80a50dfcaf5a), read on 2026-10-23. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.