design-critique-polish
Skill16 starsChanged 5 months agoMITView on GitHub
Critique and polish frontend interfaces before shipping, with focused review of hierarchy, typography, spacing, states, color, and UX clarity. Use when a page, component, or app surface feels unclear, inconsistent, flat, awkward, under-tested, or not yet production-grade and needs design verification instead of a broad rewrite.
In this repository94 other files it gives its agents.
- agent-friction-ledgerSkill
- agent-learning-layer-triageSkill
- agent-operations-contractSkill
- agents-best-practicesSkill
- agent-tool-contract-reviewSkill
- anti-slop-reviewSkill
- architecture-deepening-reviewSkill
- assumption-excavationSkill
- authorized-security-routerSkill
- book-to-skillSkill
- bounded-evaluationSkill
- bounded-growth-loopSkill
- bounded-orchestration-contractSkill
- brief-first-executionSkill
- browser-verificationSkill
- bug-evidence-protocolSkill
- codex-review-loopSkill
- compaction-survivalSkill
- complexity-optimizerSkill
- confidence-fragility-reviewSkill
- context-degradation-reviewSkill
- corporate-surfaceSkill
- delivery-baseline-auditSkill
- delivery-preflight-gateSkill
- designmd-brand-kitSkill
- design-register-bootstrapSkill
- diagnoseSkill
- doc-grounded-grillingSkill
- doc-to-lora-evaluatorSkill
- durable-context-maintenanceSkill
- dynamic-workflow-packetsSkill
- editorial-surfaceSkill
- evidence-ledger-researchSkill
- filesystem-context-disciplineSkill
- fluid-interaction-reviewSkill
- frontend-product-builderSkill
- frontend-taste-layerSkill
- git-native-context-contractSkill
- goal-loop-designerSkill
- graph-guided-code-readingSkill
- handoffSkill
- happy-handoffSkill
- html-brief-artifactSkill
- html-diagram-artifactSkill
- hypothesis-diversificationSkill
- idea-to-ship-gatesSkill
- knowledge-base-enrichmentSkill
- lean-context-layoutSkill
- local-inference-tuningSkill
- loop-hardening-contractSkill
- loopops-protocolSkill
- loop-readiness-reviewSkill
- lottie-motion-builderSkill
- minimal-diff-builderSkill
- motion-review-gateSkill
- overengineering-reviewSkill
- personal-workspace-routerSkill
- phase-spec-executionSkill
- pipeline-readiness-gateSkill
- plan-to-issuesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
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 12
Run a deliberate critique pass before shipping.
- Distinctive: line 60
Keep findings concrete. Name the surface, the defect, and the consequence.
- Distinctive: line 64
Prefer small, high-leverage corrections over full rewrites.
- Distinctive: line 65
If the core design language is wrong, say so explicitly instead of endlessly polishing local details.
- Distinctive: line 66
If the page is good enough to ship, say that too and focus on blockers only.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design Critique Polish
Run a deliberate critique pass before shipping. This is not a vague “make it nicer” prompt.
Use For
- pre-ship review of a frontend surface;
- critique after implementation but before release;
- “this feels off, but I do not know why” situations;
- tightening hierarchy, spacing, typography, copy, motion, and edge states.
Inputs
Take:
- the page, component, or route to review;
- screenshots, live URL, or repo files;
- current
PRODUCT.md/DESIGN.mdif available; - known constraints: ship date, design system, browser targets, accessibility requirements.
Critique Order
Evaluate in this order:
- Surface fit
- does this look like the right class of product or brand?
- Hierarchy
- can a first-time user tell what matters first?
- Layout and rhythm
- spacing, grouping, alignment, section cadence, empty space.
- Typography
- font choice, scale, line length, display/body contrast, overflow.
- Color and contrast
- palette discipline, readable text, accent overuse, weak affordances.
- States and resilience
- hover, focus, loading, empty, error, disabled, overflow, long labels.
- Motion and interaction
- helpful versus noisy; reduced-motion handling. If the diff materially changes transitions, keyframes, gestures, Lottie, popovers, toasts, or hover/press motion, run
motion-review-gateas the dedicated review pass.
- helpful versus noisy; reduced-motion handling. If the diff materially changes transitions, keyframes, gestures, Lottie, popovers, toasts, or hover/press motion, run
- Technical quality
- responsive behavior, accessibility signals, obvious performance issues.
Output Mode
Produce:
what workswhat failshighest-leverage fixes firstship blockers
Keep findings concrete. Name the surface, the defect, and the consequence.
Fix Strategy
- Prefer small, high-leverage corrections over full rewrites.
- If the core design language is wrong, say so explicitly instead of endlessly polishing local details.
- If the page is good enough to ship, say that too and focus on blockers only.
Common Frontend Tells To Catch
- same card pattern repeated everywhere;
- weak first viewport with no real anchor;
- gray text that reads low-contrast on tinted backgrounds;
- spacing that is mechanically even instead of rhythmic;
- headings that overflow or collapse on tablet/mobile;
- decorative motion without task value;
- UI copy that sounds like implementation notes rather than product language.
Final Report
Include:
- top issues ordered by severity;
- what should change now versus later;
- whether the surface is ship-ready;
- what to verify in-browser after changes.
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.

