agentleFS
whanoftheworldwhanoftheworld/graphic-skills/skills/design-critique/SKILL.md

design-critique

Skill0 starsChanged 34 days agoMITView on GitHub

Review a graphic or page against the brand, the brief, and design craft, and return a ranked list of evidence-backed fixes.

41 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use presentation-design, ux-writing and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ArnavPuriSkill

    presentation-design

    Design slide decks as HTML/CSS (custom or reveal.js): slide layouts on a fixed 16:9 canvas, presentation typography, slide charts, builds and transitions, speaker notes, and PDF export. Use for decks presented or shared from the browser; for native .pptx files use a PowerPoint-specific tool. Trigger phrases: "presentation", "slide deck", "slides", "pitch deck", "keynote", "reveal.js", "slide design", "presentation template", "speaker notes"

    Also in 3 projects that use this

  • brianciouSkill

    ux-writing

    UX writing guidelines for reviewing and optimizing interface copy. Use when the user asks to review, improve, or rewrite UI text including button labels, error messages, onboarding flows, or any interface copy. Apply when auditing microcopy for web apps, mobile apps, or any digital product requiring clear, user-centered communication.

    Also in 5 projects that use this

  • jpoindexterSkill

    design-system-audit

    Audit code for design system violations - grid spacing, tokens, existing components

    Also in 3 projects that use this

  • agentes100xSkill

    brand-identity

    Proporciona la fuente única de verdad para lineamientos de marca, tokens de diseño y voz/tono. Usa esto para mantener consistencia visual y de comunicación.

    Also in 3 projects that use this

  • GitHubSkill

    accessibility-audit

    Audits actual components and routes against applicable WCAG 2.2 A/AA criteria using consumer-owned design-system evidence and repository tools. Use when asked for an accessibility audit, a11y check, keyboard or focus review, contrast check, or screen-reader verification.

    Also in 4 projects that use this

  • soilmassSkill

    motion-design

    Create animations and motion graphics using industry standards. Use when asked to animate UI elements, create video content, implement transitions, or build motion systems. Implements W3C Design Tokens, Material Design 3 baseline, and Lottie specification compliance.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before judging, record what the viewer sees:

    line 15
  2. Distinctive:

    Brand: every rule in the brand memory (logo clear space and version, palette roles and proportions, type roles, graphic language, voice, …

    line 27
  3. Very specific:

    Accessibility: run design-craft's contrast.mjs on every pair, sampling the busiest region under text that sits over an image.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 35 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design critique

A studio critique asks one question of every choice: does it work, and how do you know? This skill reviews a graphic the same way, with evidence, and changes nothing until the human asks.

Load the brand-context and design-craft skills (the Skill tool, or read their SKILL.md). Reply in the user's language. The target can be an image, a screenshot, an HTML file, a PDF, or a URL; read or render it fully. Look for notes.md in the graphic's folder (under brand/applications/<slug>/), which names the brief, the planned read order, and the gate results, and read the brief it names.

1. See it the way the viewer does

Before judging, record what the viewer sees:

  • Three-second read: what the eye hits first, second, third, in your words.
  • Squint test and grayscale test: blur it and drain its color; what survives.
  • Thumbnail test: view it at 200 px wide.

Compare these reads to the intended read order in notes.md (with no notes, to the brief's single message). A mismatch is the first finding.

2. Check four axes, exhaustively

Walk each axis against its source, and cover every rule in it:

  1. Brand: every rule in the brand memory (logo clear space and version, palette roles and proportions, type roles, graphic language, voice, guardrails). Measure colors and fonts in the file rather than judge them by eye.
  2. Craft: hierarchy, alignment, proximity, spacing against the scale, margins, line length and leading, and the Thai stacking test where Thai appears (layout.md, typography.md, thai-typography.md). For generated imagery add the image gate from image-prompts.md: garbled or invented text, hands and faces, stray logos or watermarks, palette drift from the tokens, and a generated person standing in for a real one named in the copy.
  3. Accessibility: run design-craft's contrast.mjs on every pair, sampling the busiest region under text that sits over an image; check the smallest text size and any meaning carried by color alone.
  4. Brief: the message is clear in one read, the success test passes, and no claim lacks a source.

Then apply the remove test (Rams: as little design as possible): list every element that could go without loss.

3. Report

Rank findings by severity:

  • Blocker: breaks a brand rule, fails contrast, or hides the message.
  • Major: weakens hierarchy or craft in a way a viewer notices.
  • Minor: polish.

Each finding states where (element or region), evidence (the measured value, the rule it breaks, or what the squint test showed), and fix (specific, in tokens or measurements, such as "heading to --size-h2, leading to --leading-heading"). End with what works, named specifically, so the human keeps it.

The critique is done when every rule of every axis was checked, every finding carries location, evidence, and fix, and the report names what to keep. Ask whether to apply the fixes; apply them only after a yes. Findings that point at the system rather than this graphic (a missing token, a rule that never worked) go back to the owning command (/type-system, /color-system, /brand-system).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.