ui-review
Skill0 starsChanged 58 days agoMITView on GitHub
Visual UI review of course screens from screenshots (hierarchy, typography, spacing, density, alignment, controls, clipping, figure legibility, responsive layouts, consistency). Use when reviewing the look of a CourseForge course or design plan.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- colasama/MahoShojo-Generatortheir own version, first seen Nov 9, 2026
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- krzysztofsurdy/code-virtuosotheir own version, first seen Nov 1, 2026
- TucsenRoman/claude-skillstheir own version, first seen Oct 20, 2026
- arla6ka/design.howtheir own version, first seen Oct 17, 2026
- arla6ka/skillstheir own version, first seen Oct 17, 2026
Used with
Projects with it also use accessibility and grill-me.
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.
ElasticSkillaccessibility
Accessibility guidance for Kibana. Use this skill when working with or reviewing EUI components, resolving a11y-related (@elastic/eui) ESLint issues, and ensuring proper use of ARIA attributes, focus management, keyboard interactions, and accessible naming conventions.
Also in 3 projects that use this
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 3 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- RandallLiuXin/GodotMaker★ 555same name
- arla6ka/design.how★ 281same name
- arla6ka/skills★ 281same name
- colasama/MahoShojo-Generator★ 167same name
- jvm-skills/jvm-skills★ 140same name
- buildomator/buildomator★ 102same name
- krzysztofsurdy/code-virtuoso★ 36same name
- nimadorostkar/Claude-Skills-collection★ 33same name
- applypack/applypack★ 30same name
- ceptln/quota-burner★ 18same name
10 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 repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibility-reviewSkill
- alignment-reviewSkill
- assessment-designSkill
- assessment-reviewSkill
- course-gap-analysisSkill
- editorial-humanizationSkill
- fact-checkSkill
- html-intake-reviewSkill
- instructional-designSkill
- instructional-graphicsSkill
- research-authoringSkill
- research-planningSkill
- research-reviewSkill
- scenario-designSkill
- storyboard-authoringSkill
- ux-reviewSkill
- visual-directionSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
2
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
- Distinctive: line 22
No awkward breaks: single-word last lines in headings, hyphenated labels in buttons, text squeezed against borders.
- Distinctive: line 27
No cramped clusters or elements floating without alignment.
“Common” is measured: kept by at least 6 in 10 of the 16 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
UI review
How to look at screenshots
Review the same screen type side by side at 1440, 768 and 390 pixel widths, then compare the same component across modules. Squint test: blur your attention and ask what stands out first. It should be the screen title and then the primary content or question, not decoration or navigation chrome.
Criteria
Hierarchy
- One clear focal point; heading levels visibly distinct; the primary action is the most prominent control.
- Callouts (law, guidance, warning, misconception) are distinguishable and subordinate to the main text.
Typography
- Body line length roughly 60–80 characters on desktop, 35–50 on phones.
- Line height comfortable for body text (around 1.5); headings tighter.
- Consistent sizes and weights for the same role; no more than a few sizes in use.
- No awkward breaks: single-word last lines in headings, hyphenated labels in buttons, text squeezed against borders.
Spacing and rhythm
- A consistent spacing scale; more space between sections than within them.
- Related elements grouped (question, options, feedback); unrelated ones separated.
- No cramped clusters or elements floating without alignment.
Density
- Screens neither walls of text nor mostly empty. Dense content is broken into scannable parts: lists, sub-headings, figures, disclosure for optional depth.
Alignment and layout
- Shared edges and a consistent content column; figures and callouts align with it.
- Nothing overlaps; nothing clipped; no horizontal page scrolling.
Controls and states
- Interactive elements look interactive; consistent button styles; adequate target size.
- Selected, correct, incorrect, disabled and focus states are distinct and not colour-only.
Figures
- Labels readable at each width; no text overlapping shapes or other text; consistent style with the course; figures scale down or switch to a vertical layout on phones.
Responsive design
- Tablet and phone layouts designed, not just shrunk: navigation collapses to an accessible menu, progress remains visible, tables and matrices adapt, controls remain reachable.
Reporting
- Location: screen ID, or a CSS selector for shell-wide issues.
- Evidence: screenshot file names and a precise description of what is visible ("GA-04 at 390 px: option D label clipped after 'where reasonably'").
- Group by root cause (one component defect across many screens is one finding).
- Severity: unusable content or controls at a viewport → critical; broken hierarchy on a common screen type, illegible figures → major; spacing inconsistencies, single awkward wraps → minor; taste → style.
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.

