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/expert.md

Lens: Expert Interview

When: interview with an expert/council member to gather judgments, disagreements, and recommendations in a subject area. Not about the expert's personal role, but about their knowledge of the field. Coding unit: an expert's claim with a quote + a note on the degree of confidence and status (fact / assessment / forecast).

Layer 1 — operational (claims + quote + line)

  • E1 Expertise profile — what exactly they are competent in, relevant experience, limits of competence (what they consider outside it).
  • E2 Key claims — the main statements on the topic, each with a quote; note the type (fact / assessment / forecast).
  • E3 Recommendations — specific proposals for action, priority.
  • E4 Data and precedents — what they rely on: numbers, cases, sources, analogues.
  • E5 Constraints and risks — what they warn about, where they see dangers/pitfalls.
  • E6 Open questions — what they don't know themselves / where additional verification is needed.

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

  • A1 Claim confidence — HIGH / MEDIUM / LOW for each key claim (based on grounding in data vs opinion). (unstable)
  • A2 Points of consensus — where it aligns with the mainstream/other experts (if known).
  • A3 Points of disagreement — where it diverges, what exactly the dispute is about, whose position is better argued. (unstable)
  • A4 Contested/unverifiable statements — what cannot be taken on faith and needs verification.
  • A5 Value for the decision — how the claims affect the original decision/strategy.
  • A6 Key insight — 1 sentence: the expert claims [X] with confidence [Y], which for the decision means [Z].

Forcing questions

What is this conclusion based on — data or experience? Where could you be wrong? Which of your colleagues would disagree with you and why? What would change your mind? What is contested here?