decision-tracing
Skill5 starsChanged 8 months agoMITView on GitHub
Reverse-engineer why a design decision was made. Move from observation to inference. Use when studying products you admire, learning from competitors, or building analytical design thinking.
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 8
Look at a decision. Figure out why it was made.
- Distinctive: line 17
MUST follow: Observation > Decision > Probable Reason
- Distinctive: line 19
MUST generate at least 5 traces per design screen
- Distinctive: line 20
SHOULD acknowledge uncertainty: "probable reason" not "the reason"
- Distinctive: line 21
NEVER state intent as fact unless you have insider knowledge
≈ “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
Decision Tracing
Look at a decision. Figure out why it was made.
How to use
/decision-tracingApply decision-tracing analysis to any design in this conversation.
Constraints
Trace Structure
- MUST follow: Observation > Decision > Probable Reason
- "The primary font is Inter" > "They chose a geometric sans-serif" > "Data-heavy product needing maximum legibility at small sizes with neutral personality"
- MUST generate at least 5 traces per design screen
- SHOULD acknowledge uncertainty: "probable reason" not "the reason"
- NEVER state intent as fact unless you have insider knowledge
What to Trace
- Typeface selection and type system
- Color palette and color role assignments
- Layout structure and grid decisions
- Spacing and density choices
- Navigation architecture
- What's absent (what they chose NOT to include)
Anti-Patterns
- Assuming the most flattering interpretation of every decision
- Tracing only visual decisions and ignoring structural ones
- Stating reasons as facts without marking them as hypotheses
In this repository38 other files it gives its agents.
- absence-auditSkill
- 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
- 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.