empathy-analysis

Installation
SKILL.md

Empathy Analysis

Core principle: True empathy = cognitive model of the user's emotional state + what they believe is happening. The test: "Does this make sense for someone who doesn't know what's coming next?"

Two Layers — Both Required

Layer What it captures Key question
Informational What users believe is happening vs. what's actually happening. What they need to predict next. Whether labels/cues help them estimate a path's value (information scent). Where will the mental model diverge from system reality?
Emotional Baseline emotion before contact, peak intensity during, ending impression (peak-end rule). Which backstage conditions create negative peaks. What will they remember feeling?

Build from Evidence

Accept transcripts, interviews, pasted content, files, and URLs as input — ingest them, don't summarize them. Code reveals what the system actually does; contrast that with what users believe. Populate says/thinks/does/feels quadrants from observed evidence. Never invent quotes or emotions.

Confidence Discipline

Tag every claim: [confirmed] (direct quote or observed behavior), [hypothesis] (inferred from patterns), or [gap] (unknown). Flag inferred emotions explicitly — "User likely feels frustrated [hypothesis]" not "User feels frustrated." For each hypothesis, note what evidence would confirm or refute it.

Installs
1
GitHub Stars
3
First Seen
May 5, 2026
empathy-analysis — zemptime/zemptime-marketplace