← ClaudeAtlas

interview-mapper-enlisted

Maps and interprets interviews from transcripts: picks a methodology, proofreads the transcript, checks quotes against the source and tests whether conclusions hold across runs. Use when the user wants to analyze, code, map, interpret, or "make sense of" an interview, transcript, depth interview, custdev/JTBD/expert interview, synthesize a series of interviews, or pull cross-interview insights (synthesis, patterns, insight cards), including when no method is named. Lenses: org-mapping, JTBD, CustDev/discovery, expert, exit, usability/think-aloud, win/loss, candidate, focus groups, team retro, intercept, conflict/mediation, ethnographic, change readiness, brand, visitor experience. Catches transcription distortions and fabricated or "regenerated" quotes. Not for generating new interviews and not for audio transcription.
Socialpranker/interview-mapper · ★ 1 · AI & Automation · score 74
Install: claude install-skill Socialpranker/interview-mapper
# Interview Mapper Turns an interview transcript into a structured mapping where **every conclusion is grounded in a verbatim quote**, analysis is checked across **multiple runs**, and disputed cells are **flagged for a human** rather than resolved silently. Built on an evidence base (self-consistency, LLM-as-judge flip-rate, faithfulness ≠ verbatim; see `references/reliability.md`). ## Contents - S0 — intake: goal, respondent, sensitivity; lenses and outputs - S0.5–S4 — single-interview pipeline: proofreading, interpretation, reliability council, output - S5–S8 — synthesis across interviews and longitudinal analysis - Human↔AI comparison - Script index - Honest limitations - Dependencies ## S0 — Intake "Goal survey" (first step: the lens and output depend on the answers) The pipeline depends on two axes: **what you're deciding** (goal) and **who you interviewed** (respondent). Don't start mapping until both are clear. Ask adaptively (details — `references/intake.md`): 1. **Goal:** discovery · org-mapping · experience evaluation · positioning/brand · prioritization · expert validation · personas · usability · exit · win/loss · project retro · intercept (in-the-moment) · conflict resolution · natural practice (ethnography) · change readiness. 2. **Who you interviewed:** employee · customer · expert · visitor · stakeholder · candidate · group (focus group/team) · party to a conflict. 3. (as needed) output · number of interviews · whether a human baseline exists. 4. **Sensiti