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/decision-memo.md

Output: Decision memo (memo for a decision)

When: the goal is to distill interviews into a short document supporting a specific stakeholder decision. Input: insights + (if available) human↔AI comparison. Shorter than insight cards, tailored to 1 decision.

Format (1–2 pages)

# Decision: [the question we're answering]
## Recommendation
[one clear action/choice + for whom]
## What it's based on (3–5 insights)
- [insight] — X of N interviews, criticality — «quote» (Interview, Lxx)
## Risks and counterarguments
- [what argues against it; who would disagree; where data is thin]
## What we DON'T know
- [open questions, gaps, silence in the data]
## Confidence: high/medium/low
[based on triangulation + grounding + n interviews]

Rules

  • One specific recommendation. If there's no data to support it, say so — don't stretch.
  • The counterarguments and "what we don't know" sections are mandatory — otherwise it's a presentation, not a decision.
  • Every support point is a verified quote + interview count. Latent conclusions (eNPS, etc.) are marked as requiring a human.
  • n<k → "pilot, not a basis for an irreversible decision".