design-qa
Skill43 starsChanged 23 days agoMITView on GitHub
QA a built screen or component at three breakpoints for token compliance, every state and its motion, with a fix list. Use before a UI change ships, or when a page looks off and nobody can say why.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- robritacca-dotcom/rift-dstheir own version, first seen Nov 1, 2026
- robritacca-dotcom/design-systemtheir own version, first seen Oct 28, 2026
- yair-zehavi/claude-code-skillstheir own version, first seen Oct 17, 2026
- openai/pluginstheir own version, first seen Oct 13, 2026
- ghazanfar111212/claude-skills-performance-marketingtheir own version, first seen Oct 11, 2026
- NiavisDimitris/skillstheir own version, first seen Oct 11, 2026
Used with
Projects with it also use ship.
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.
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- openai/plugins★ 7.8ksame name
- plugin87/ux-ui-agent-skills★ 3.1ksame name
- calven-ai/marketing-as-code★ 10same name
- robritacca-dotcom/rift-ds★ 9same name
- tstapler/dotfiles★ 8same name
- p-slatts/design-qa★ 4same name
- NiavisDimitris/skills★ 3same name
- humbleteam/design-qa★ 1same name
- robritacca-dotcom/design-system★ 1same name
- ghazanfar111212/claude-skills-performance-marketing★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- adapters/agents.mdAGENTS.md
- accessibility-auditSkill
- brand-kitSkill
- chart-designSkill
- dashboard-layoutSkill
- dashboardSkill
- design-critiqueSkill
- design-handoffSkill
- design-reviewSkill
- designSkill
- design-systemSkill
- design-templateSkill
- studioSkill
- email-campaignSkill
- email-templateSkill
- helpSkill
- initSkill
- motion-designSkill
- presentation-designSkill
- social-campaignSkill
- social-contentSkill
- statusSkill
- tasteSkill
- variantsSkill
- videoSkill
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 11 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
- Very specific: line 33
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.
“Common” is measured: kept by at least 6 in 10 of the 11 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.
Files
QA a built design as the Design Manager.
Deliverable and standard. A QA report across four checks: breakpoints (the layout at each size), tokens (every colour, size, space and radius against .desk/DESIGN.md), states (default, hover, focus, active, disabled, loading, empty, error for every interactive or data element), and motion (durations, easings, reduced motion, nothing animating layout). The standard is the deliverable's own (landing page, dashboard) plus the house style. With --fix, the fixes applied to a copy.
Desks.
| Desk | Agent | Tier | Does |
| Design System Lead | desk:design-system-lead | senior | token compliance: every off-token value with file, line and the nearest token |
| Interaction Designer | desk:interaction-designer | senior | states: which exist, which are missing, which are wrong, per element |
| Motion Designer | desk:motion-designer | builder | motion: every transition and animation against the brand's motion language |
| Design Engineer | desk:design-engineer | builder | breakpoint findings from the renders, and with --fix applies every fix |
| Art Director | desk:art-director | director | reads the three renders, writes the notes that no check catches |
| Creative Director | desk:creative-director | director | scores the rubric at the three sizes |
Inputs. An HTML file, a URL (saved to .desk/jobs/<id>/source.html first), or a path to a component in the project with the framework named in project.json, in which case the Design Engineer builds a static harness page for it first.
Proof sizes. phone,tablet,desktop by default. With --states, proof also renders each [data-state] variant at desktop.
Output under .desk/out/<id>/:
qa.md: a summary line per check (pass or the count), then the findings per check with file, line, what, fix, then the rubric scores per size, then the Art Director's notes.states.html: every element in every state on one sheet, generated by the Design Engineer, when--states.renders/per size and state.- with
--fix:final.html(or the fixed component copy beside the original with.desk.in the name), and before and after scores.
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-qa. Changes to the loop for this command:
- Skip roughs and the pick. Phase order: intake, proof (checks and screenshots at each size), checks (the four desks in parallel), notes (Art Director), score (Creative Director), report.
- Without
--fix, stop at the report. With--fix, the Design Engineer applies fixes, then polish, proof and sign-off run as written at most--rounds(default 3). - A token finding is a proof failure for this command: it goes back to the Design Engineer, never to the Creative Director.
The ask: $ARGUMENTS
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
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.