Agent skill · alirezarezvani
interview-mapper
Use when coding or making sense of one interview transcript (customer, JTBD, expert, usability, exit). Extracts verbatim-grounded nuggets with extract_nuggets.py, verifies quotes with verify_quotes.py and checks conclusions hold across reruns with consensus.py.
What it needs
About 4k tokens when loaded.
What this skill does
Interview Mapper Turns one interview transcript into a structured mapping where every conclusion is grounded in a verbatim quote (checked by a script, not by eye), analysis is checked across multiple runs (disagreement is flagged, never silently resolved), and cross-interview patterns require triangulation across independent sources before being called an insight. Distinct from product-research research-ops/skills/product-research operates one level up: it picks the research method (generative vs evaluative), sizes the sample, and synthesizes already-coded observations into an insight repository — it never touches a transcript. This skill is the transcript-level layer: it reads the raw interview, produces the per-lens coding with quote-level grounding, and hands verified, triangulated evidence to product-research's synthesis step (or works standalone). See ../product-research/SKILL.md. Workflow 1. Route the intake. python3 scripts/route.py --goal <goal> --respondent <who> picks the lens (which of 16 templates) and output, and returns the applicable pipeline steps. 2. Number and verify. python3 scripts/numberlines.py transcript.(txt docx srt vtt) numbers lines for traceability (from subtitles it also writes timecodes and speakers to a sidecar, and flags lines that read as instructions to the model — a transcript is untrusted input); python3 scripts/verifyquotes.py --transcript tnl.txt --claims claims.json checks every quote is actually in the source (verbatim ≠ support — see references/reliability.md). 3. Check reliability, then synthesize. python3 scripts/consensus.py run1.json run2.json run3.json flags cells where independent runs disagree — and flags the opposite failure too: total agreement (councildegenerate) usually means the runs were not independent, and agreement across weakly grounded runs (unanimousbutungrounded) may be identical bias rather than correctness. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/interview-mapper