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/change-readiness/gold.md

Gold mapping — "Change readiness" lens

Interview: head of the internal medicine department in a clinic network, interviewed ahead of rolling out a single medical information system (MIS) to replace three disconnected scheduling sources (Excel, a paper log, and the senior nurse's memory). Transcript: transcript.txt (78 lines).

Layer 1 — operational

R1 — Stated position on the change

Fact: the respondent states full, public support for the rollout and readiness to volunteer for the pilot group. Quote: "Definitely for it, I even said it out loud at the general meeting back in June, that I'm ready to be in the pilot group if needed." Line: 4

R2 — Official reason for the position

Fact: grounds support in reduced error risk from the three mismatched scheduling sources and in transparency for the patient. Quote: "Yes, reducing the risk, and honestly, transparency for the patient too, right now someone calls and they can't be told right away when their appointment is, because the three sources don't match up." Line: 8

R3 — Who else, in the respondent's view, is for and against

Fact (for): the chief physician (initiator) and Marina from reception. Quote: "Of those clearly for it — the chief physician, of course, it's his initiative, also Marina from reception, she's long been tired of paper." Line: 16

Fact (against): head of surgery Artyom Viktorovich — doesn't object openly, but calls the change "extra control from above" in private. Quote: "Nobody's openly against it yet, but I know the head of surgery, Artyom Viktorovich, grumbles in private that it's just extra control from above." Line: 16

Fact (assumption about those waiting it out): the respondent suspects hidden disagreement among three of the five department heads — flags this himself as a guess based on nonverbal signals, not as fact. Quote: "honestly I suspect maybe three out of five aren't happy deep down, but nobody's said it out loud, I'm judging by faces at meetings, not by words." Line: 18 (unstable cell — the source is the respondent's personal guess, not a confirmed fact; the respondent himself refuses to name specific people at line 70)

R4 — Past experience with similar changes

Fact: an attempt to roll out an electronic queue in 2022 failed — three months of glitches, doctors keeping paper duplicates in parallel, then a quiet shutdown with no explanation. Quote: "We tried, yeah, back in twenty-two we tried to set up an electronic queue, it was a disaster honestly, three months of everything crashing, doctors manually duplicating it on paper in parallel, then the system was quietly shut down, and nobody apologized, it was just like it never happened." Line: 10

Fact (effect on the organization): a general distrust of new rollouts being carried through has taken hold, including in the respondent himself. Quote: "people now default to not believing things will get finished, we even got a saying, "we'll survive this one too," not maliciously, but there's a residue, and for me too, no point hiding it." Line: 12

R5 — Conditions for support

Fact: the respondent names three conditions to move to "one hundred percent" support: (1) lossless migration of data from the old system, (2) full-fledged training rather than a token webinar, (3) a "reasonable hierarchy" of access rights. Quote: "Well, first, that the data from the old system gets transferred without loss, or it'll be like in twenty-two. Second, that there's proper training, not a two-hour webinar just for show. And third... well third, that access rights get set up sensibly, so not everyone sees absolutely everything, some reasonable hierarchy needs to stay in place." Line: 56

R6 — Expected personal losses/gains for the respondent

Fact (loss): the respondent personally runs the department schedule and uses that opacity as a management lever ("shift someone quietly"); after the rollout this becomes visible and will require explanations. Quote: "it'll be a bit less convenient for me to distribute shifts the way I think best without extra questions, right now if I need to shift someone quietly, I just do it, and there it'll all be visible and, I guess, I'll have to explain it every time." Line: 30

Fact (gain): less routine calls/operational load plus a promised bonus for a smooth pilot rollout. Quote: "I definitely gain less running around, fewer calls of "where's my appointment," that's genuinely gotten old, plus, they say, management promised a bonus to whichever department head rolls it out first without hiccups, that's nice too, no point hiding it." Line: 34

R7 — Channel of influence

Fact: regular biweekly planning meetings with the chief physician (carefully "floating" ideas) plus direct personal off-the-record access to the chief physician, built on ten years of working relationship. Quote: "Most often at the chief physician's planning meetings, they happen every two weeks, all the department heads gather there, I usually drop a thought carefully, not head-on, more like a suggestion to think about." Line: 62

Additionally: "and also the chief physician trusts me, we've worked together ten years, so if something's important, I can go straight to him too, off the record." (line 64)

Layer 2 — analytical

A1 — Public position vs. hidden interest [HYPOTHESIS]

Conclusion: THE PUBLIC POSITION OF "FOR THE ROLLOUT, FULLY SUPPORTIVE OF TRANSPARENCY" CONFLICTS WITH A HIDDEN INTEREST IN PRESERVING SOLE INFORMAL CONTROL OVER SHIFT ALLOCATION, WHICH THE RESPONDENT HIMSELF CALLS HIS "LEVER." Supporting quotes: "in a sense that's my lever for keeping the department in order." (line 26); "I'm for transparency in general, but... well yeah, if I'm completely honest, it'll be a bit less convenient for me to distribute shifts the way I think best without extra questions" (line 30). (unstable — latent; an interpretation of the degree of hidden interest, not a fact)

A2 — Coalition map (from one interview — preliminary, needs triangulation with other respondents)

Conclusion: FOR — THE CHIEF PHYSICIAN (INITIATOR), MARINA FROM RECEPTION. AGAINST (LATENTLY) — ARTYOM VIKTOROVICH, HEAD OF SURGERY. WAITING IT OUT — MOST DEPARTMENT HEADS (BY THE RESPONDENT'S GUESS) AND DOCTOR OLGA FROM THE RESPONDENT'S OWN DEPARTMENT. Supporting quote: "She's... I don't know, honestly, probably waiting it out, "we'll see" isn't "against," but it's not "for" either, somewhere in between." (line 72); also ""well, we'll see," you know, the kind of "we'll see" that actually means "I don't like this," but she didn't object outright." (line 24) (unstable — the "waiting department heads" coalition rests on one respondent's nonverbal guesses, with no independent confirmation; needs cross-checking against other parties' interviews)

A3 — Power of influence

Conclusion: THE RESPONDENT'S POWER OF INFLUENCE IS HIGH — A REGULAR INSTITUTIONAL CHANNEL (PLANNING MEETINGS) PLUS PERSONAL TRUSTED ACCESS TO THE CHIEF PHYSICIAN OFF THE RECORD. Supporting quote: "and also the chief physician trusts me, we've worked together ten years, so if something's important, I can go straight to him too, off the record." (line 64)

A4 — Conditional support (R5) — specificity

Conclusion: TWO OF THE THREE CONDITIONS ARE CONCRETE AND MEASURABLE (LOSSLESS DATA MIGRATION, FULL-FLEDGED TRAINING), BUT THE THIRD ("REASONABLE ACCESS HIERARCHY") IS VAGUE — THE RESPONDENT HIMSELF CANNOT OPERATIONALIZE IT. THIS IS A LIKELY SIGNAL OF HIDDEN DISAGREEMENT (SEE A1) THAT WILL NOT BE RESOLVED BY A FORMAL COMPROMISE. Supporting quote: "I don't know how to put it right, but I feel total transparency is overkill." (line 58) (unstable — the boundary of "reasonable hierarchy" is not defined by the respondent himself)

A5 — Risk of repeating the past failure

Conclusion: THE RISK IS PARTIALLY REDUCED — THIS TIME THERE IS A TWO-YEAR BUDGET (THE RESPONDENT CHECKED THIS PERSONALLY), BUT ORGANIZATIONAL DISTRUST FOLLOWING THE 2022 FAILURE PERSISTS AND MAY SURFACE AS PASSIVE RESISTANCE EVEN ALONGSIDE FORMAL SUPPORT. Supporting quote: "Better, because this time the budget is set for two years ahead, not just a quarter, I checked that separately with the CFO, specifically asked, so as not to walk into a second failure." (line 14)

A6 — Main insight

Conclusion: ON THE SINGLE MIS ROLLOUT, THE RESPONDENT HOLDS A PUBLIC POSITION OF FULL SUPPORT; THE LIKELY REAL INTEREST — HYPOTHESIS: PRESERVING INFORMAL CONTROL OVER SHIFT ALLOCATION AND AVOIDING QUESTIONS ABOUT UNEVEN DOCTOR WORKLOAD IN HIS OWN DEPARTMENT; POWER OF INFLUENCE — HIGH (DIRECT ACCESS TO THE CHIEF PHYSICIAN); RISK — HIDDEN RESISTANCE FROM SOME DEPARTMENT HEADS AND HIS OWN DOCTOR (OLGA) MAY NOT SURFACE UNTIL THE PILOT BEGINS AND COULD DERAIL THE ROLLOUT ALONG THE SAME SCENARIO AS IN 2022. Supporting quote: "I'm for rolling out a single medical information system, because three sources for the schedule is a risk and a mess, but I probably do genuinely worry a bit about my own autonomy in scheduling shifts, and I want the new system to keep reasonable access boundaries, not make everything visible to absolutely everyone." (line 76)

Ambiguous spots (for unstable Layer 2 cells)

  1. Lines 68–70 — the respondent, reasoning about Artyom Viktorovich's motives ("he's got his favorites there too"), himself admits "well, that's me speculating now, he never said that directly," and then, when the interviewer asks directly whether he shares a similar motivation, answers evasively: "probably partly yes, though I wouldn't want to put us in the same category, my situation is still softer." Ambiguous whether the respondent is effectively admitting the same thing about himself that he described in his opponent, or genuinely distancing himself — this affects the strength of A1.
  2. Lines 59–60 — on the direct forcing question "would you support it even with full transparency," the respondent answers "probably yes, I'd still support it... I'll have to see how it goes" — blurred between hypothetical agreement and avoiding commitment, which weakens A4 (the vague condition's boundary is not testable).