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

assets/example-outputs/insight-cards.md

Output: Insight cards

When: the goal is to extract cross-interview insights. The default synthesis output (S5–S7). Input: nuggets with clusters → score_insights.py. Write cards only for insight/watchlist.

Card format

### [ID] Title — one sentence
Statement: [observation + interpretation + implication — not a retelling]
Holds for: [roles/segments] · NOT for: [where it doesn't work]
Prevalence: X of N interviews (roles: …) · Criticality: high/medium/low
Type: CONSENSUS | TENSION ([role A] vs [role B] — on what)
Evidence (verified + support=yes only):
  - [Interview, role] «verbatim quote» (Lxx)
  - [Interview, role] «…» (Lxx)
Counter-evidence: [who didn't confirm / what contradicts / where there's silence]
Confidence: high/medium/low (based on triangulation + grounding)
Implication / recommendation: [what to do; for whom]

Rules

  • A pattern = ≥k different interviews with a verified quote (not k quotes from one person).
  • Every card goes through counter-evidence.
  • Scope by role: "for collections staff", not "for employees".
  • Sorting: insight by frequency×criticality → watchlist (tensions, rare-but-critical). weak — into the appendix.
  • Optionally → HTML board: render_board.py provenance.json.