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/evals/fixtures/conflict-mediation/gold.md

Gold mapping — lens "Pre-mediation diagnostic interview with a conflict party"

Interview: Artem (co-founder and developer of a web development studio), mediator — before the joint session with partner Maxim. Party in the conversation — Artem only; the other party (Maxim) does NOT participate in the interview, all information about him is in Artem's words (accounted for in M3/M4/A4).

Layer 1 — operational

M1 Stated position

Artem demands changing the company split from 50/50 to 70/30 in his favor. Quote: "I want to revisit the split. Fifty-fifty isn't fair, I want seventy-thirty in my favor, period, that's not up for discussion." (line 8)

M2 Interest behind the position

Behind the demand for the share is a need for recognition of contribution and real influence over technical decisions, not the percentage figure itself. Quote: "honestly — it's not about the number itself. I need someone to acknowledge that without me there's no product." (line 12) Additionally: "Although if the split stayed fifty-fifty, but something like veto power over technical decisions showed up — maybe I wouldn't even be raising the share question at all." (line 14)

M3 Version of events (in Artem's words — not fact)

Timeline per his version: partnership started 2.5 years ago on a verbal 50/50 agreement (line 4, 6) → first year without complaints → last spring Maxim hires his wife Olya without agreement (line 16) → Olya starts interfering in task prioritization (line 20) → in February a priority conflict between FinTrade vs QuickPay (line 22) → the fix deadline is missed by 11 days, risk of losing the client (line 24) → Artem resolves the situation himself, gives a discount without approval (line 26). Quote (start): "Maxim and I met two and a half years ago, back at our previous job... it was all on trust, no real paperwork, brotherly-style." (line 4) Quote (turning point): "The turning point happened last spring, when Maxim hired his wife Olya for the project manager position, without my agreement, just presented it as a done deal." (line 16)

M4 Attribution of blame

Artem holds Maxim responsible — for hiring Olya into a role she's not qualified for, and for not putting any safety net in place. He considers Olya not malicious, but unsuited for the role. Quote: "Maxim. A hundred percent Maxim. He put Olya in charge of sorting out priorities, knowing she doesn't understand technical urgency, and didn't put any safety net in place." (line 30) Quote (about Olya): "I don't think she did it maliciously, she just didn't understand the consequences, but the choice to put her in that role — that's Maxim's choice." (line 32)

M5 What has already been tried to resolve it

Two direct attempts between the partners (formalizing the prioritization process in March — held for 3 weeks, line 34; a major conversation in May after the QuickPay case, ending in a fight, line 36) and one attempt with a third party (accountant Sveta calculated contribution by the hour, fizzled out after two weeks, line 70). None of them held. Quote: "The first time in March, I proposed formalizing the prioritization process so that only I would make urgency decisions, he agreed verbally, it held for three weeks, then everything went back to how it was." (line 34) Quote (third party): "We tried once, went to our accountant Sveta, she tried to calculate who's actually contributing how much by the hour, but that turned into yet another argument... and it fizzled out from there, dropped it after about two weeks." (line 70)

M6 BATNA (best alternative)

If mediation doesn't produce a result — leave the studio and take the key client (QuickPay) with him; he has already been feeling it out and has prepared a draft proposal. Quote: "If we don't reach an agreement — I'm leaving and taking the key client with me, QuickPay, I already have a direct contact with their CTO, they said they'd be willing to work with me directly as an independent contractor." (line 40) Quote (degree of readiness): "Not yet, nothing official, but yes, I've been feeling it out, that's not empty talk, I even have a draft proposal ready, if it really comes down to it." (line 42)

M7 Red lines

Two stated directly: (1) Olya must not make technical decisions/priority calls; (2) the share cannot be reduced below 50% under any circumstances. Quote (1): "Olya has no right to make technical decisions — that's a red line, no discussion whatsoever." (line 46) Quote (2): "I won't agree to any reduction of the share below fifty, under no circumstances at all, not even temporarily. That's the baseline, below it I just exit the partnership." (line 50)

M8 Attitude toward the other party

Mixed: residual personal warmth and some remaining trust ("we call each other just to chat about football") coexist with distrust of Maxim's business decisions. Quote: "I don't feel hatred toward him, we still sometimes call each other in the evening just to chat about football, like nothing's happening, it's a stupid feeling of being split in two." (line 52) Quote (degree of trust): "It's still there, maybe thirty percent of what it used to be. I believe he doesn't want to deliberately set me up, I don't believe he's capable of telling his wife "no" in time, when the business needs it." (line 54)


Layer 2 — analytical (advice to the mediator)

A1 POSITION↔INTEREST GAP — EXISTS, AND IT'S WIDE

The stated position (M1: 70/30 split) is noticeably harsher than the real interest (M2: recognition of contribution + veto power over technical decisions). Artem himself points to an alternative that would satisfy the interest without changing the split — that is the room for compromise. Anchor quote: "if the split stayed fifty-fifty, but something like veto power over technical decisions showed up — maybe I wouldn't even be raising the share question at all." (line 14)

A2 COMPATIBILITY OF THE PARTIES' INTERESTS — PARTIALLY VISIBLE, NOT CONFIRMED

(unstable — requires mapping both sides; here there is only Artem's version of Maxim's position) There is reason to believe that retaining the key client (QuickPay) is a shared interest of both parties, though they diverge on the method of achieving it (Artem — by eliminating technical risk, Maxim, by Artem's guess — through relationship-building/discounts). Artem himself only formulates this after a leading question and directly acknowledges uncertainty in the interpretation. Anchor quote: "it's bad for both of us to lose them, so I can't say we're exactly in different camps on this... Maybe this isn't even about different interests at all, but about different ways of achieving the same thing, I'm not sure, I need to think about it." (lines 64, 66) [⚑ HIGH-STAKES — must be verified by a human mediator after interviewing Maxim's side, before this conclusion is used in negotiations.]

A3 READINESS TO SETTLE — MEDIUM (UNSTABLE)

(unstable — latent, the respondent himself notes the fluctuation) Taken together, the BATNA (a real but unexecuted plan to leave with the client, M6) and the red lines (M7, two firmly stated) put readiness at medium, leaning toward high, but the respondent himself reports day-to-day swings down to low. Anchor quote: "medium, leaning toward high... Although honestly, on bad days I'd say readiness is low overall, it really fluctuates day to day." (line 72)

A4 FACT VS INTERPRETATION IN THE VERSION OF EVENTS

Independently verifiable facts: Olya's hiring without the partner's agreement (dates, salary, the fact of hiring — lines 16, 18), the 11-day overdue fix for QuickPay and the related correspondence with the client (line 24) — potentially verifiable via correspondence/tickets. Artem's interpretation (not fact): Maxim's motives ("the choice to put her in that role," line 32), a read on Maxim's inner state ("some kind of complex," line 56) — this is the party's reading, not a verifiable fact. Anchor quote (fact): "Hiring his wife at a salary of a hundred and twenty thousand is a major decision, and I found out after the fact from a chat with the accountant." (line 18) Anchor quote (interpretation): "I think it matters to him to feel like an equal partner, not like "the guy who hired the tech person," he's got some kind of complex about it... honestly I don't know, I haven't asked him directly." (line 56)

A5 KEY INSIGHT

Artem states the position "70/30 split," the real interest is recognition of technical contribution and a decisive voice in task prioritization; there IS room for settlement (keeping the 50/50 split in exchange for a formalized veto right over technical decisions, plus a separate conversation about equal profit reinvestment); the main barrier is an unformalized decision-making process and the presence of the partner's family member in an operational role without agreed-upon authority.


Reliability notes

  • The transcript contains ONLY Artem's side; all statements about Maxim's motives and position are one party's version, not fact (see A4).
  • Ambiguous points requiring advice/re-runs: A2 (interest compatibility) and A3 (readiness to settle) — both are explicitly flagged as unstable in the interview text by the respondent.
  • The hidden fact about unequal profit reinvestment (line 58) the respondent himself names as not yet disclosed to the partner and being held "in reserve" — important for assessing the good faith of the negotiating position, but not for drawing final conclusions without checking with both parties.