quality-checklist
Skill5 starsChanged 8 months agoMITView on GitHub
Systematic design quality evaluation. Hierarchy, type, color, space, craft, system. Use when evaluating whether a design is ready to ship, running quality audits, or setting quality standards.
Files
Quality Checklist
A systematic pass through every dimension of design quality.
How to use
/quality-checklistRun a quality evaluation on any design in this conversation.
Constraints
Hierarchy
- Clear primary element on every screen
- Visual weight matches content priority
- No unintentional competing elements at the same hierarchy level
- Eye path follows the intended reading order
Typography
- Type scale uses a consistent ratio
- Weight usage is systematic with named purposes
- Line height varies appropriately (tighter headlines, looser body)
- No more than 4-6 sizes per screen with clear justification
- Typeface matches product voice
Color
- Every color has a clear, non-overlapping role
- Semantic colors are consistent everywhere
- Neutrals do 80-90% of the heavy lifting
- Sufficient contrast for accessibility (WCAG AA minimum)
Space
- Spacing follows a consistent scale
- Proximity signals correct relationships
- Density matches the use case
- Margins create appropriate breathing room
Craft
- Border radii consistent across element types
- Alignment pixel-perfect where intended
- All states covered: loading, empty, error, success, overflow
- Transitions purposeful and consistently timed
System
- Design could scale to 10 more screens without breaking
- Another designer could extend this without asking questions
- Components are reusable, not one-offs
- System breaks are intentional, not accidental
Anti-Patterns
- Checking only visual polish and ignoring information architecture
- Treating the checklist as pass/fail instead of diagnostic
- Running the checklist once and never revisiting
In this repository38 other files it gives its agents.
- absence-auditSkill
- decision-tracingSkill
- system-deconstructionSkill
- version-archaeologySkill
- audience-translationSkill
- critique-vocabularySkill
- design-rationaleSkill
- written-critiqueSkill
- field-notesSkill
- learning-by-makingSkill
- self-assessmentSkill
- flow-patternsSkill
- motion-designSkill
- timing-feedbackSkill
- constraint-evaluationSkill
- design-rankingSkill
- taste-as-strategySkill
- taste-gapSkill
- taste-vs-trendsSkill
- tradeoff-assessmentSkill
- consumption-disciplineSkill
- cross-domain-seeingSkill
- detail-observationSkill
- screenshot-surgerySkill
- visual-auditSkill
- cross-pollinationSkill
- library-architectureSkill
- principle-taggingSkill
- daily-routinesSkill
- design-critiqueSkill
- teaching-tasteSkill
- type-as-signalSkill
- type-selectionSkill
- type-systemsSkill
- color-systemsSkill
- craft-signalsSkill
- hierarchy-principlesSkill
- spatial-rhythmSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

