critique-vocabulary
Skill5 starsChanged 8 months agoMITView on GitHub
Precise language for design feedback. Ban vague words. Name what you actually see. Use when giving design feedback, running critiques, or training teams to communicate about quality.
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 17
NEVER use these in design feedback: clean, modern, sleek, nice, cool, interesting, beautiful, ugly, minimal, bold, intuitive, seamless, …
- Distinctive: line 18
MUST replace every banned word with a specific observation about hierarchy, weight, rhythm, density, contrast, proportion, consistency, or …
- Distinctive: line 31
MUST use: Observation > Principle > Question
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Critique Vocabulary
Say exactly what you mean. Kill vague words.
How to use
/critique-vocabularyApply precise vocabulary constraints to all design feedback in this conversation.
Constraints
Banned Words
- NEVER use these in design feedback: clean, modern, sleek, nice, cool, interesting, beautiful, ugly, minimal, bold, intuitive, seamless, stunning, pop, vibe
- MUST replace every banned word with a specific observation about hierarchy, weight, rhythm, density, contrast, proportion, consistency, or spacing
Replacement Vocabulary
| Instead of... | Use... |
| "It feels cluttered" | "The information density is high relative to the content hierarchy. Nothing signals where to start." |
| "It looks boring" | "The visual rhythm is flat. Every section has the same scale and spacing." |
| "Make it pop" | "The CTA doesn't have enough visual separation from surrounding elements." |
| "Something feels off" | "The spacing between these groups seems inconsistent. Is this relationship intentional?" |
| "It's not polished" | "The border radius is inconsistent between these elements." |
| "Explore other directions" | "The current approach prioritizes X. What happens if we prioritize Y instead?" |
Feedback Structure
- MUST use: Observation > Principle > Question
- Observation: what you specifically see
- Principle: why it matters
- Question: what to explore (not what to do)
Anti-Patterns
- Giving feedback in the form of commands ("make the button blue")
- Using technical jargon to sound authoritative without actually being specific
- Being vague-positive ("looks great!") which teaches nothing
In this repository38 other files it gives its agents.
- absence-auditSkill
- decision-tracingSkill
- system-deconstructionSkill
- version-archaeologySkill
- audience-translationSkill
- design-rationaleSkill
- written-critiqueSkill
- field-notesSkill
- learning-by-makingSkill
- quality-checklistSkill
- 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.

