AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

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.

Original source
alirezarezvani
License
MIT
Pinned revision
e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

This skill also requires local files or dependencies. Remote reading alone may not be enough.

Ask your assistant

Use Agentic Memory skills to read alirezarezvani--interview-mapper at revision e4a1dc3695908dd5a6c811cc76ab7aa4cf95f2f0, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 63

templates/intercept.md

Lens: Intercept Interview (in-the-moment, at point of contact)

When: a short interview right at the point of contact (a trade show, store, conference, booth) immediately after a specific micro-episode, usually with no prior preparation of the respondent. Difference from visitor-experience: there the respondent retrospectively recounts the whole visit after it ends, here it's an in-the-moment reaction to one fresh episode, memory hasn't yet been processed into a narrative. Coding unit: a reaction to a specific micro-episode that just happened, with a direct quote + how ready the respondent was to talk (rushed / answered willingly). Collection discipline: the interview is short (usually 2–5 minutes) — don't try to squeeze out a full narrative, capture what the respondent actually managed to articulate. Being rushed and low engagement aren't noise — they're part of the data about the contact format.

Layer 1 — operational (facts + quote + line)

  • I1 Intercept context — where exactly, at what point in the respondent's chain of actions (before/during/right after the episode).
  • I2 Micro-episode — what exactly just happened (saw the booth, tried the product, left the hall) — from the respondent's point of view.
  • I3 Immediate reaction — the first emotion/assessment before any reflection, verbatim.
  • I4 Readiness to talk — rushed / stayed willingly / answered formally — affects how much depth to expect from the rest of the answers.
  • I5 Prior awareness/knowledge — did they know about the brand/place/event beforehand or encounter it for the first time.
  • I6 Immediate intent — what they plan to do next (come back, buy, forget) — as stated in the moment, not hypothetically.

Layer 2 — analytical (conclusion + quote; CAPS) — to council

  • A1 Reaction valence — POSITIVE / NEUTRAL / NEGATIVE / MIXED, based on the first immediate reaction (I3), not on subsequent rationalizations.
  • A2 Answer reliability — how much the reaction was affected by being rushed/unready (I4) — low readiness = less trust in deep conclusions, only in the fact of contact.
  • A3 Segment by prior knowledge — knew beforehand vs. discovered by chance (I5) — different types of contact require different conclusions.
  • A4 Point of effect — what exactly in the micro-episode triggered the reaction (a specific element, not a general impression).
  • A5 Key insight — 1 sentence: at point [X], respondents (segment [Y]) react [valence] to [specific element], reliability of the conclusion — [high/low based on readiness].

Forcing questions

What just happened? What did you feel in the first second? Did you know about this before or see it for the first time? What will you do next? (Keep it short — don't hold the respondent longer than they're willing.)

Limitation

Shallow depth by design of the method — doesn't substitute for a full visitor-experience interview. Good for volume/coverage (many touchpoints in a short time), poor for narrative and motivation. Triangulate with deeper lenses if the decision is high-stakes.