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/personas.md

Output: Personas

When: the goal is segments/personas from a series of interviews. You need ≥5 interviews, otherwise a persona = a stereotype. Input: nuggets (with role/segment) → clustering by segment, not by theme.

Grounding rule

A persona is not fiction, but an aggregate. Every persona attribute rests on ≥k different interviews with a verified quote. One vivid respondent ≠ a persona. Mark [weak: n<k] if data is thin.

Persona format

## Persona: [archetype, not a name] — [segment]
Based on: N interviews (roles/segment)
Goals: [what they want] — «quote» (Interview, Lxx)
Behavior: [what they actually do, past facts] — «quote» (Lxx)
Pains: [pains, ranked] — «quote» (Lxx)
Barriers: structural vs operational
Triggers/motivators: [what drives them]
Difference from other personas: [how they differ]
Confidence: high/medium/low

Rules

  • An attribute without ≥k confirmations → not into the persona, but into "hypotheses".
  • Don't invent demographics that aren't in the data.
  • Personas must DIFFER (if two are nearly identical — it's one).
  • Record tensions between segments separately (more important than averaging).