agentleFS
Sign inStart free
rschuftrschuft/ai-frontend-skill-packs/skills/design-review/SKILL.md

design-review

Skill4 starsChanged 5 days agoMITView on GitHub

Review existing UI aesthetics against brand and composition goals; prioritize evidenced layout, typography, color, hierarchy, and imagery issues. Use for visual design audits.

164 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

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 137 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Avoid subjective numeric scores.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 137 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

Review visual design and art direction

Scope

Review an existing UI, screenshot, prototype or implementation against its design intent and brand constraints. Distinguish observed visual issues from untested interaction behavior.

Procedure

  1. Establish actual target: brand, product segment, user task, page type (marketing/editorial/transactional/data dense), design constraints, available artifacts, and target viewports/themes. Separate opinions about style from violations of documented requirements.
  2. Observe the full page and at least the important component states; inspect two or more screen sizes when possible. If no browser access, label responsive and interactive judgments untested. Inventory typography roles, palette roles, grid, spacing, borders/shadows, imagery and primary focal moment.
  3. First-pass scan: emphasis → contrast → balance → movement → proportion → repetition → unity. Then examine seven elements: line, shape, form, color, value, texture and space. Use the structured catalog ../design-diagnose/references/principles.json and ten routing categories.
  4. Compare with the actual design system/brand guide. Do not recommend wholesale rebranding as a fix for one misaligned card. Audit cross-screen unity and route each finding to one specialist; cite the exact source article when useful.
  5. For each issue: evidence, user or brand consequence, severity, proposed change, tradeoff, and test. Distinguish confirmed visual observations from hypotheses about user behavior. Run wcag-review and ux-review separately where barriers or usability questions arise.
  6. Avoid subjective numeric scores. Report observed outcomes and reproducible checks. Sort by impact and change leverage; prefer design token fixes when they correct multiple screens.

Deliverable

Lead with a 2–4 sentence assessment, then a prioritized finding set. Include surface/viewport, before-state observation, classifier category, principles and source URL, actionable diff/pattern, verification, outstanding UX/WCAG evidence. If asked for a style direction, give bounded alternatives with explicit tradeoffs rather than invented brand rules.

See references/review-checklist.md for a systematic review matrix and an output template.

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.

Check your setup, free