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/conflict-mediation.md

Lens: Diagnostic Interview with a Conflict Party (Pre-Mediation)

When: interview with one side of an unresolved conflict, before/as part of mediation prep or dispute resolution. Difference from team-retro: there, the team jointly reviews a closed episode in a relatively peaceful mode; here, the parties are STILL in conflict, are interviewed SEPARATELY, and the task is to map each side's positions, not to reconcile them in a single session. Coding unit: a statement with a mandatory split between position (what the party demands) and interest (what is actually needed behind that demand) — per Fisher/Ury (Getting to Yes). Collection discipline: interviewer neutrality is mandatory — do not confirm or refute either side's version during the interview. Each party — a separate mapping file; do not mix them in one document before the synthesis stage.

Layer 1 — operational (facts + quote + line)

  • M1 Stated position — what the party demands/insists on, literally (their wording).
  • M2 Interest behind the position — what is actually needed (need/fear/value), drawn out with clarifying questions like "why exactly does this matter."
  • M3 Version of events — chronology of the conflict in this party's words, flagged explicitly as THEIR version (not fact).
  • M4 Attribution of blame — who they hold responsible and why, verbatim.
  • M5 What's already been tried to resolve it — attempts made to reach agreement, why they didn't work (in the party's view).
  • M6 BATNA (best alternative) — what the party will do if no agreement is reached — ask directly.
  • M7 Red lines — what the party calls unacceptable under any circumstances.
  • M8 Attitude toward the other side — tone, willingness to engage, any remaining trust.

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

  • A1 Position↔interest gap — where the stated demand (M1) is wider/narrower than the real interest (M2) — this is usually where room for compromise lies.
  • A2 Compatibility of the parties' interests — (filled in AFTER mapping both sides separately) — where interests don't actually conflict despite conflicting positions. (unstable — requires both mappings)
  • A3 Readiness to settle — HIGH / MEDIUM / LOW, based on BATNA (M6) and red lines (M7) combined. (unstable — latent)
  • A4 Fact vs interpretation in the version of events — what in M3 can be independently verified (dates, documents) vs what is only the party's reading.
  • A5 Key insight — 1 sentence: the party states [position], the real interest is [X], room for settlement — [yes/no], main barrier — [Y].

Forcing questions

Why exactly does this matter to you? What happens if you don't get it? What will you do if no agreement is reached? What would be an acceptable compromise, and what is categorically not? What do you think matters to the other side?

Limitation and ethics

Interviewer neutrality is not a technicality but a condition for the method's validity: if the interviewer is perceived as "siding" with one party, the whole picture is distorted. A2 (compatibility of interests) is filled in only after interviewing BOTH parties and requires mandatory review by a human mediator before use in negotiations — this is a classic high-stakes case, not for autonomous AI conclusions.