product-ui-polish-review
Skill0 starsChanged 7 months agoApache-2.0View on GitHub
Guardrail for reviewing and polishing product UI reward moments, typography, spacing, hierarchy, and perceived-quality details without drifting into manipulative retention design.
In this repository57 other files it gives its agents.
- ai-app-integrationSkill
- anti-llm-frontend-designSkill
- aspnet-core-web-developmentSkill
- async-python-patternsSkill
- browser-game-foundationsSkill
- browser-local-qaSkill
- build-mcp-server-sdk-v2Skill
- canva-design-opsSkill
- check-completionSkill
- cli-tool-creatorSkill
- cloudflare-agents-mcpSkill
- cloudflare-durable-objectsSkill
- cloudflare-workers-platformSkill
- deployment-preview-workflowsSkill
- docx-document-artifactsSkill
- durable-workflow-orchestrationSkill
- dynamic-og-imagesSkill
- eval-auditSkill
- evaluate-ragSkill
- figma-design-to-code-rulesSkill
- fine-tuningSkill
- frontend-product-builderSkill
- game-asset-pipeline-expansionSkill
- game-ui-playtestSkill
- generate-synthetic-dataSkill
- github-pr-ci-opsSkill
- gmail-inbox-opsSkill
- golden-datasetSkill
- huggingface-llm-trainerSkill
- javascript-monorepo-buildsSkill
- linear-issue-managementSkill
- media-generation-transcriptionSkill
- millrace-rs-contract-paritySkill
- minecraft-mod-qa-automationSkill
- notion-workspace-flowsSkill
- openai-docsSkill
- optimize-agentic-cliSkill
- pdf-artifact-workflowSkill
- phaser-2d-game-developmentSkill
- postgres-query-performanceSkill
- pydantic-v2-patternsSkill
- python-repo-refactoring-hygieneSkill
- rag-corpus-hygieneSkill
- react-next-performance-reviewSkill
- rust-best-practicesSkill
- shadcn-ui-compositionSkill
- skill-evaluation-harnessSkill
- tauri-desktopSkill
- tauri-mcp-cliSkill
- tauri-ptySkill
- tile-pixel-art-transitionsSkill
- train-sentence-transformersSkill
- typer-cli-patternsSkill
- using-dbt-for-analytics-engineeringSkill
- validate-evaluatorSkill
- visual-asset-pipelineSkill
- watchdog-file-watcher-patternsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. About 0 are common, 18 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈18
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 43
If a gift moment is appropriate, design anticipation, reveal, and afterglow with restraint.
- Distinctive: line 45
Check ethics and product fit before adding celebration or habit-forming ceremony.
- Distinctive: line 48
Do not make manipulation the goal.
- Distinctive: line 49
Do not add reward ceremony to irreversible, risky, financial, medical, safety, children, or addiction-sensitive actions.
- Distinctive: line 50
Do not celebrate trades, losses, purchases, health outcomes, or other moments where excitement can impair judgment.
- Distinctive: line 51
Do not hide latency with fake uncertainty unless the product truthfully has a real pending result.
- Distinctive: line 52
Do not use confetti, glow, sound, haptics, badges, or share prompts as default decoration.
- Distinctive: line 53
Do not interrupt expert or repeated workflows with ceremony after the novelty has worn off.
- Distinctive: line 54
Do not center-align long text, mix center-aligned headings with left-aligned body copy, or let body text run too wide.
- Distinctive: line 55
Do not overuse text sizes for hierarchy when weight, tone, color, and spacing can do the job.
- Distinctive: line 67
If ceremony is used, specify anticipation, reveal, and afterglow as separate pieces.
- Distinctive: line 74
Find receipt moments: Look for places where the user receives something: success, match, score, report, streak, badge, export, generated …
- Distinctive: line 75
Choose receipt or gift: Keep the moment plain when speed, seriousness, reversibility, or risk matters.
- Very specific: line 81
Use heading line-height around 1.1-1.3.
- Very specific: line 82
Use body line-height around 1.3-1.5.
- Distinctive: line 83
Use slight negative letter spacing only for large headings when the font benefits from it.
- Distinctive: line 84
Avoid negative letter spacing in body text.
- Very specific: line 85
Keep body text around 50-75 characters per line.
- Distinctive: line 87
Use left alignment for body text longer than about three lines.
- Distinctive: line 88
Keep heading and body alignment consistent within the same text group.
- Very specific: line 92
Use simple ratios: if heading-to-body spacing is 1x, spacing between unrelated groups should usually be 2x or more.
- Distinctive: line 94
Verify the polish: Check that the screen still communicates the real task, remains accessible, and does not slow down frequent users …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Product UI Polish Review
Purpose
Help agents review and improve product UI surfaces by finding meaningful result moments, then tightening typography, spacing, hierarchy, and perceived-quality details. This is a polish guardrail, not a growth-hacking manual or a substitute for a full design system.
Use When
- a product screen, onboarding flow, generated-result page, dashboard, app, or tool needs final polish
- the work involves success states, milestones, matches, reports, scores, streaks, generated artifacts, unlocks, badges, or other user-receives-something moments
- typography, spacing, line length, alignment, or hierarchy make the UI feel amateur despite mostly-correct structure
- a frontend build or review needs product-specific delight without becoming generic decoration
Do Not Use When
- the work is backend-only, copy-only, or a purely mechanical bugfix
- the user asks for dark-pattern retention, gambling-like engagement, compulsive loops, or deceptive urgency
- the product category is finance, trading, health, education for children, addiction-sensitive, or otherwise high-risk and the requested reward treatment could distort user judgment
- a specific design system already dictates the interaction and typography choices
Quick Start
- Classify the surface and its real job before adding polish.
- Find the user-receives-something moments: result, report, score, match, milestone, unlock, generated artifact, payout, badge, save, or completion.
- Decide whether each moment should stay a plain receipt or become a small gift moment.
- If a gift moment is appropriate, design anticipation, reveal, and afterglow with restraint.
- Tighten typography and spacing: line height, letter spacing, alignment, measure, hierarchy, and relationship spacing.
- Check ethics and product fit before adding celebration or habit-forming ceremony.
Operating Constraints
- Do not make manipulation the goal. Optimize clarity, perceived quality, confidence, and meaningful feedback.
- Do not add reward ceremony to irreversible, risky, financial, medical, safety, children, or addiction-sensitive actions.
- Do not celebrate trades, losses, purchases, health outcomes, or other moments where excitement can impair judgment.
- Do not hide latency with fake uncertainty unless the product truthfully has a real pending result.
- Do not use confetti, glow, sound, haptics, badges, or share prompts as default decoration.
- Do not interrupt expert or repeated workflows with ceremony after the novelty has worn off.
- Do not center-align long text, mix center-aligned headings with left-aligned body copy, or let body text run too wide.
- Do not overuse text sizes for hierarchy when weight, tone, color, and spacing can do the job.
Inputs This Skill Expects
- the product category and target user
- the screen, flow, diff, screenshot, or implementation being reviewed
- the main user goal and the important objects, states, and actions
- any brand, design-system, accessibility, motion, or risk constraints
- the moments where the user receives a result, reward, confirmation, or generated output
Output Contract
- Name the surface type and the primary job before proposing polish.
- Identify at least one receipt-or-gift decision and explain why it should stay plain or gain ceremony.
- If ceremony is used, specify anticipation, reveal, and afterglow as separate pieces.
- Include at least one typography or spacing correction with concrete values or rules.
- Reject at least one tempting but inappropriate polish move and name the safer alternative.
- Preserve existing product structure and workflow; polish should not replace missing functionality.
Procedure
- Classify the surface. Name whether it is onboarding, generated result, dashboard, operational tool, consumer loop, checkout, editor, game UI, or another product surface.
- Find receipt moments. Look for places where the user receives something: success, match, score, report, streak, badge, export, generated file, completed task, unlocked item, saved state, or payout.
- Choose receipt or gift. Keep the moment plain when speed, seriousness, reversibility, or risk matters. Consider gift treatment when the moment is earned, positive, safe, and important enough to remember.
- Design gift moments in three stages.
- Anticipation: brief loading, staged reveal, progress, or suspense that truthfully reflects an upcoming result.
- Reveal: the result arrives with weight through layout, timing, contrast, animation, haptics, or sound when appropriate.
- Afterglow: give the user a moment to save, share, compare, claim, continue, or attach identity to the result.
- Tune typography.
- Use heading line-height around
1.1-1.3. - Use body line-height around
1.3-1.5. - Use slight negative letter spacing only for large headings when the font benefits from it.
- Avoid negative letter spacing in body text.
- Keep body text around
50-75characters per line; around600pxis a useful desktop maximum for typical body copy.
- Use heading line-height around
- Tune alignment and hierarchy.
- Use left alignment for body text longer than about three lines.
- Keep heading and body alignment consistent within the same text group.
- Limit type-size count; prefer weight, color, opacity, spacing, and position for secondary hierarchy.
- Tune relationship spacing.
- Elements with a closer semantic relationship should be physically closer.
- Use simple ratios: if heading-to-body spacing is
1x, spacing between unrelated groups should usually be2xor more. - Make whitespace an active layout element, not leftover empty space.
- Verify the polish. Check that the screen still communicates the real task, remains accessible, and does not slow down frequent users unnecessarily.
Pitfalls And Gotchas
- Rejected trope: turn every success state into confetti. Better alternative: scale the ceremony to the importance and risk of the moment.
- Rejected trope: deliver every generated report as a flat bank-statement receipt. Better alternative: use a truthful anticipation and reveal sequence when the result is meaningful and safe.
- Rejected trope: fix a weak UI with glow, blur, gradients, or motion before typography and spacing. Better alternative: fix line height, measure, hierarchy, and relationship spacing first.
- Rejected trope: use center alignment because it looks premium in a mockup. Better alternative: left-align longer reading surfaces and reserve centered text for short, controlled chunks.
- Rejected trope: use many font sizes for every level of importance. Better alternative: use two or three type sizes, then adjust weight, color, and spacing.
Progressive Disclosure
Start with the smallest useful polish review: receipt-or-gift decision, typography, spacing, and risk check. Widen into motion, sound, haptics, sharing, or identity only when the product moment is safe and important enough to justify ceremony. Keep transcripts, examples, and broad product psychology out of context unless the current task needs them.
Verification Pattern
- Confirm the surface type and user job were named.
- Confirm at least one receipt moment was classified as plain receipt or gift moment.
- Confirm any gift moment has anticipation, reveal, and afterglow, not just a reveal animation.
- Confirm high-risk categories were not given manipulative celebration.
- Confirm heading and body line-height, text measure, alignment, hierarchy, and relationship spacing were checked.
- Confirm the final UI is more specific to the product, not just more decorated.
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.

