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/candidate.md

Lens: Candidate Interview (hiring)

When: an evaluative interview with a candidate for a position. Difference from VMDI org-mapping and exit interviews: the goal isn't to understand the system from the inside, but to assess the candidate's FIT for the role and collect verifiable facts about their past experience. Coding unit: a candidate's statement about their experience with a direct quote + a verifiability tag (specific fact / general claim). Collection discipline: look for STAR episodes (Situation-Task-Action-Result) with numbers and names, not generic self-assessments ("I'm a team player," "good communicator").

Layer 1 — operational (facts + quote + line)

  • K1 Stated relevant experience — what the candidate names as their key experience for this role.
  • K2 STAR episode(s) — a specific situation → task → action → result, with details (timelines, numbers, the candidate's own role vs. the team's).
  • K3 Motivation for leaving — why they're leaving their current job / looking for work; what they're seeking here that was missing there.
  • K4 Expectations of the role — how they picture their tasks, scope of responsibility, first 90 days.
  • K5 Response to a hard/failed case — asked to describe a failure — what they chose to share, how they explain the cause (external circumstances vs. their own role).
  • K6 Candidate's questions to us — what they ask — what they're worried about, what matters to them (a signal of priorities).
  • K7 Terms and constraints — salary expectations, availability date, work format, other constraints — specific numbers/dates.

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

  • A1 Episode verifiability — SPECIFIC FACT (dates/numbers/names, verifiable via reference check) / GENERAL CLAIM (not verifiable). For each K2. (unstable)
  • A2 Result attribution — attributes the result to THEMSELVES / THE TEAM / CIRCUMSTANCES — does the scale match the seniority of the role.
  • A3 Locus of responsibility for failure (K5) — owns it / deflects outward. (unstable — latent trait)
  • A4 Role fit — which specific job-profile criteria match/don't match (not a general impression, but point by point).
  • A5 Risks and red flags — inconsistencies in the story, avoidance of specifics, mismatch between expectations and the role's actual conditions.
  • A6 Key insight — 1 sentence: candidate confirms experience [X] with a STAR episode [verifiable/not], risk is [Y], recommendation — [next step].

Forcing questions

Tell me about a specific case where [skill] came into play — what exactly did you do, and what did the team do? What was the result, in numbers? Tell me about a situation that didn't work out — what went wrong and what would you do differently? Why are you looking for a job right now?

Limitation

Latent traits (motivation, honesty of self-attribution, cultural fit) are a classic weak spot for LLM analysis. All A2/A3/A5 cells are candidates for mandatory human review, not a final mapping decision.