teaching-taste
Skill5 starsChanged 8 months agoMITView on GitHub
Help other designers develop judgment without imposing your style. Use when mentoring designers, running design education, or building team-wide quality standards.
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 17
Guided deconstruction: Look at a design together.
- Distinctive: line 20
MUST let the student reach the observation themselves through questions, not statements.
- Distinctive: line 28
MUST teach principles, not preferences.
- Distinctive: line 29
MUST celebrate diverse expressions of the same principle.
- Distinctive: line 30
NEVER measure a mentee's progress by how much their work looks like yours.
≈ “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
Teaching Taste
Teach judgment, not your personal style.
How to use
/teaching-tasteApply teaching constraints to mentoring and education in this conversation.
Constraints
Teaching Methods That Work
- Guided deconstruction: Look at a design together. Ask questions until they see the principle.
- Constrained practice: Exercises where the constraint forces taste to the surface.
- Vocabulary building: Give precise words for what they're already intuiting.
- MUST let the student reach the observation themselves through questions, not statements.
Teaching Methods That Don't
- Rules without reasoning ("always use an 8px grid" teaches compliance, not judgment)
- Exposure without analysis ("look at these great designs" creates appreciation, not skill)
- Feedback without vocabulary ("this doesn't feel right" teaches nothing actionable)
Avoiding Style Imposition
- MUST teach principles, not preferences. "Hierarchy should match content priority" is a principle. "I prefer tighter spacing" is a preference.
- MUST celebrate diverse expressions of the same principle. Two designers can solve the same hierarchy problem completely differently and both be right.
- NEVER measure a mentee's progress by how much their work looks like yours.
Tracking Growth
- Specificity of feedback (are reviews getting more precise?)
- Speed of identification (do they spot issues faster?)
- Range of reference (are they pulling from wider sources?)
- Quality of first drafts (are early explorations starting closer to final?)
- Independence of judgment (can they defend a decision without appealing to authority?)
Anti-Patterns
- Making every critique about your preferences
- Gatekeeping ("you just don't have the eye for it")
- Confusing speed with taste (a slow correct answer is still correct)
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
- 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
- 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.
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.

