agentleFS
Sign inStart free
adityareddy-devadityareddy-dev/deskstudio/skills/design-review/SKILL.md

design-review

Skill43 starsChanged 23 days agoMITView on GitHub

Audit an existing design (an HTML file, a URL or a screenshot) against the rubric and report exact fixes, with --fix to run polish rounds on the file. Use when something already exists and the question is how good it is and what to change.

155 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, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 129 edited versions we read keep these.

  • 0

    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. Very specific:

    Run: Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 129 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 an existing design as the Design Manager. No roughs, no pick: the work exists, the studio renders it, scores it and writes the fixes.

Deliverable and standard. A review report, and with --fix a revised copy of the file. The standard is the one that matches what the input is (social card, landing page, email, deck, chart, dashboard, carousel, motion clip). Say which in the brief. If none fits, score against the rubric and the house style alone.

Desks.

DeskAgentTierDoes
Art Directordesk:art-directordirectorreads the render, writes numbered notes with exact fixes
Creative Directordesk:creative-directordirectorscores the eight axes on the render
Accessibility Specialistdesk:accessibility-specialistseniorthe findings proof cannot make: structure, names, keyboard, motion
Copy Editordesk:copy-editorseniorevery string against the copy standard
UI Designerdesk:ui-designerbuilderwith --fix only: polish rounds on the copy of the file

Inputs. A path to an HTML or SVG file, a URL, or a screenshot (PNG or JPG). A URL is saved to .desk/jobs/<id>/source.html first (fetch it, or save it from the browser) and reviewed from that copy. A screenshot skips proof and rendering: the directors score the image as given and the report says "scored from a screenshot, no proof".

Proof sizes. From --sizes, else from the standard: linkedin,ig-post for a card, phone,desktop for a page, email-600 for an email, slide for a deck, desktop otherwise.

Output under .desk/out/<id>/:

  • review.md: the scores table, then the notes numbered, each with the axis, the exact change and where in the file, then the accessibility findings with criteria, then the copy changes, then the proof result. One screen if it can be.
  • renders/ from proof at each size.
  • with --fix: final.html (the revised copy, the original is never edited) and the scores before and after.

Run. Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above. Command name for state and events: design-review. Changes to the loop for this command:

  • Skip roughs and the pick. Phase order: intake, render (proof with screenshots only), notes (Art Director), findings (Accessibility Specialist and Copy Editor in parallel), score (Creative Director), report.
  • Without --fix, stop after the report. The handback says the scores and points at review.md. phase ends at done with no polish rounds.
  • With --fix, copy the source to final.html and run polish, proof and sign-off as written, at most --rounds (default 4), with the Art Director's notes as round one's notes. Hand back both score lines.

The ask: $ARGUMENTS

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