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/custdev.md

Lens: CustDev / Problem Discovery (The Mom Test)

When: problem/discovery interview to validate a need before building a solution. Goal — separate facts from polite lies. Coding unit: a fact about past behavior with a quote. Opinions and compliments — separately and with skepticism. Rule: talk about their life, not your idea; ask about specific past events, not hypotheticals; listen 80% of the time.

Layer 1 — operational (facts + quote + line)

  • C1 Problem/task — what problem they describe in their own concrete words; how it manifests.
  • C2 Real episodes — specific past cases (when, what they did), NOT "usually I…".
  • C3 Current solution / workaround — how they cover it now, including hacks (Excel, manual work, "I ask a colleague").
  • C4 Cost of the problem — how much it has already cost: time, money, nerves, missed opportunities. Numbers.
  • C5 Who else is involved — who suffers/decides/pays; roles in decision-making.
  • C6 What they've tried and dropped — which solutions they hired and why they gave up.

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

  • A1 Fact vs opinion — what is confirmed by BEHAVIOR, and what is only a declaration/compliment. Flag explicitly. (unstable)
  • A2 Strength of pain — BURNING / NAGGING / IMAGINED. Marker: whether they already paid/spent a resource. (unstable)
  • A3 Readiness signals — did they search for a solution themselves? spend money? call in others? (real commitment signals, not "would be interesting").
  • A4 Hypothesis: confirmed/refuted — which hypothesis the interview confirmed/refuted and with what exactly.
  • A5 False-positive risk — where answers might have been politeness; what should be re-checked.
  • A6 Key insight — 1 sentence: problem [X] is real/doubtful, because [behavioral evidence], therefore [what to do].

Forcing questions

When did this last happen? What did you do? What happened next? How much did it cost? What did you try to solve it? Why didn't it work? (Avoid: "would you buy…", "do you like the idea…".)