agentleFS
seancabalseseancabalse/agentic-playbook/skills/design-review/SKILL.md

design-review

Skill0 starsChanged 15 days agoMITView on GitHub

Review a UI change for UX, visual quality and use of the design system, from screenshots. Use for each UI change.

166 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

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 138 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read: the design source the ticket links (if any), the component kit, the tokens module, and the diff.

    line 13
  2. Distinctive:

    Tokens and kit: no hard-coded colours, fonts, spacing, curves or durations.

    line 17
  3. Distinctive:

    Copy: every string is in the catalogue, in the product's voice, written from the reader's side.

    line 19
  4. Very specific:

    Look at real screenshots (ask for them, or capture them via verify-feature): the default state, each other state, the largest text size, …

    line 27

“Common” is measured: kept by at least 6 in 10 of the 138 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 review

Playbook files named here: when the project has its own copy at .playbook/local/<same path>, use that copy instead.

Scope: $ARGUMENTS

Read: the design source the ticket links (if any), the component kit, the tokens module, and the diff. Principles: ${CLAUDE_PLUGIN_ROOT}/principles/04-design-and-ux.md and 05-accessibility-i18n.md.

Check

  1. Tokens and kit: no hard-coded colours, fonts, spacing, curves or durations. Kit components are used where they exist, and any new pattern is added to the kit with a preview.
  2. States: loading (a skeleton in the content's shape), error (friendly, with retry), offline (calm, cached data visible), empty (invites action). Nothing flashes "empty" before data arrives.
  3. Copy: every string is in the catalogue, in the product's voice, written from the reader's side; names and pronouns come from data. Errors and limits are mapped by code. Destructive actions confirm with their consequence.
  4. Interaction: selected states have a non-colour cue; targets are at least 24 × 24 CSS px (44 recommended); feedback on press; no dead ends (every sheet and screen has a way back).
  5. Motion: meaningful, uses the token curves through the motion hook, gentle or reduced mode respected, nothing continuous on the main screen.
  6. Layout: wraps and stacks at 200% zoom; reflows at 320 CSS px; works at tablet and desktop widths; text in fixed art scales with it and its information is in an accessible name.
  7. Fidelity: matches the design source (spacing, hierarchy, illustration style). Deviations are deliberate and noted.

Evidence

Look at real screenshots (ask for them, or capture them via verify-feature): the default state, each other state, the largest text size, and the narrowest width. Review what's on screen, not just the code.

Output

Findings ranked by customer impact, each with a screenshot reference or a file:line and a suggested fix. List what's good too, so it stays that way.

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.