agentleFS
schen22schen22/claude-config/skills/design-review/SKILL.md

design-review

Skill0 starsChanged 2 days agoMITView on GitHub

Read-only design and brand review of one of Sarah's websites — typography, hierarchy, layout at phone/tablet/desktop widths, spacing, navigation, states, motion, contrast, design-token discipline, and brand (mark, voice, share metadata). Produces a findings table with file:line evidence and a top 3. Use on "design review", "brand review", "review the look", "does this feel right", or at the end of a visual milestone.

167 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use project-stage-detect, team-audio and 10 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.
  • CoralGameSkill

    project-stage-detect

    Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.

    Also in 16 projects that use this

  • CoralGameSkill

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 13 projects that use this

  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • +4 more from CoralGame
  • +3 more from lilangMax

The file

Files
SKILL.md

Design review

Findings only. Which ones to act on is Sarah's call, recorded in the project's PLAN.md. Run it as one Sonnet helper (see delegate); it reports ≤ 30 lines.

Read first (and only)

  1. The project's design-system doc (e.g. docs/design-system.md). Where it disagrees with the tokens file, the tokens file wins — report the mismatch as a finding.
  2. The tokens file, the layout/base/components CSS, and the page templates.
  3. Earlier reviews (e.g. docs/archive/*-review.md) — don't re-raise what was decided.

Measure, don't eyeball

Build to a scratch dir and use the project's browser test helpers (Puppeteer) to read computed values at 375, 768 and 1280px: header height, overflow, font sizes, spacing between blocks, target sizes, contrast of each text/background pair. No screenshots or image reads (helper-guard blocks them): report computed values, and name the pages and widths for Sarah to look at.

Lenses

LensCheck
TypeEvery weight/style used ships a real font file (no faux bold/italic); one clear hierarchy per page (h1 > h2 > body); sizes match the doc's tokens
LayoutNo horizontal overflow; mobile header doesn't push content below the fold; one left edge unless an exception is declared
SpaceSpace between groups > space within a group; tokens, not raw values
NavigationOne visual treatment for nav links; current page marked; targets ≥ 24px (project may set 48)
StatesVisible :focus-visible; hover/pressed/current states present (e.g. [aria-pressed="true"])
Motionprefers-reduced-motion respected; nothing loops forever (WCAG 2.2.2)
ContrastText ≥ 4.5:1, large text/UI ≥ 3:1, links vs body text distinguishable, in light and dark
SystemRules in the right file/layer; component-local values declared as such; doc matches code
BrandMark legible at header and favicon size in both themes; one voice and metaphor; title, description, og:* correct and absolute; emoji/glyphs widely supported

Report

**Verdict.** <two sentences: what's strong, what undercuts it>

| # | Finding | Evidence | Sev | Suggested action |
|---|---|---|---|---|
| 1 | ... | `file.css:12-20` or measured value | high/med/low | ... |

Checked and fine: <one line of what passed>.
Top 3: <numbers and why>.

Evidence is a file:line or a measured number, never "looks off". Sarah makes the visual call; the review makes it easy to make.

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.