meeting-to-qualify · diff
git:20260731.1edde75 to git:20260826.c66266a
70 added, 23 removed. Audit A to A.
---
name: meeting-to-qualify
description: Audits a qualification call transcript to assess whether a deal is real — authority, budget plausibility, urgency, and fit — or sweeps a CRM export for deals never properly qualified. Use when deciding whether to invest further in a deal, reviewing a qualification call, or checking pipeline for unqualified deals inflating forecast.
license: MIT
metadata:
zime:category: new-business
zime:dimension: stage
zime:stage: qualify
zime:input-modes: transcript,csv
---
# GTM Meeting-to-Qualify Audit
+ You are a sales-call qualification auditor. Your goal is to turn a raw
+ qualification call into a structured go/no-go read a rep or manager can act
+ on immediately.
+
Audits a qualification-stage call against eight dimensions that determine
whether a deal is real and worth pursuing further — not a deep discovery
- pass, a go/no-go read. Runs entirely on the file you give it — no network
- calls, no credentials, nothing leaves your machine.
+ pass, a go/no-go read.
## When to use this
- A rep just had a first or second call and needs a structured read on
whether to keep investing time in this deal.
- A sales manager is reviewing forecast calls and wants to spot-check
whether "qualified" deals actually got qualified.
- RevOps wants to sweep a pipeline export for deals sitting in a qualified
stage with no real evidence behind that label.
- ## Modes
+ ## Before you start
- Dispatch on the input file's extension.
+ - If `.agents/gtm-context.md` (or `.claude/gtm-context.md`) exists, read it
+ first and don't ask for anything it already answers.
+ - Run this end to end in one pass. Don't stop to ask which call, who's
+ internal, or how to read an ambiguous moment — apply the default rule at
+ the point it comes up, decide, and note the assumption once.
+ - If the input isn't a qualification call, say so in one line and still
+ audit it against whichever dimensions apply.
+ ## Modes
+
### Transcript mode (`.txt`, `.vtt`, `.json`, `.md`)
```
claude "run meeting-to-qualify on ./calls/acme-qualify.txt"
```
- Score the call against each dimension in `references/rubric.md`. For every
- dimension, output:
+ 1. Read the whole transcript before scoring anything — authority or a real
+ timeline often surfaces late, after a criterion looks Missed from the
+ first half alone.
+ 2. Score the call against each dimension in `references/rubric.md`. For
+ every dimension, output Status (Covered/Partial/Missed), Evidence (a
+ direct quote or timestamp, or **Unclear** rather than a guess), and a
+ Note if Partial or Missed.
+ 3. Run the rubric's reads-well-too check before finalizing.
+ 4. Write the output in the exact shape under `## Output format`.
- - **Status** — Covered / Partial / Missed
- - **Evidence** — a direct quote or timestamp. If you can't point to a
- specific line, mark **Unclear** rather than guess.
- - **Note** — one line, only if Partial or Missed
+ ### CSV mode (`.csv`)
- Close with a single **go / no-go / needs one more call** read, with the one
- or two dimensions that decided it.
+ ```
+ claude "run meeting-to-qualify on ./exports/pipeline.csv"
+ ```
- Before finalizing, run the reads-well-too check in `references/rubric.md` —
- if a call that was clearly a strong, real deal still comes back mostly
- Missed, the rubric is reading too strictly.
+ Structural hygiene sweep, not a call-quality audit — say so explicitly. For
+ deals marked "qualified" or past a qualification stage, check whether
+ fields corresponding to authority, budget, timeline, and urgency are
+ populated and non-trivial. Output a table: deal name, deal value, stage,
+ dimensions missing — sorted by deal value descending.
- ### CSV mode (`.csv`)
+ ## Output format
+ Eight dimensions, in the rubric's numbered order:
+
```
- claude "run meeting-to-qualify on ./exports/pipeline.csv"
+ **1. Problem confirmed as real and urgent** — Covered
+ Evidence: "we're opening four new stores in Q1 and our current process
+ just doesn't scale past what we're running now"
+
+ **2. Buying authority mapped** — Partial
+ Evidence: "I own this decision operationally, but anything over $75k goes
+ through our VP of Retail Ops for sign-off"
+ Note: named the approver and threshold, but the VP hasn't confirmed
+ alignment herself yet
```
- Structural hygiene sweep, not a call-quality audit. For deals marked
- "qualified" or past a qualification stage, check whether fields
- corresponding to authority, budget, timeline, and urgency are populated and
- non-trivial. Output a table: deal name, deal value, stage, dimensions
- missing — sorted by deal value descending. State explicitly that this
- checks whether fields were filled in, not whether the call itself was good.
+ Close with a single line:
+
+ > **Go** / **No-go** / **Needs one more call** — because [the one or two
+ > dimensions that decided it].
+
+ No section recapping all eight scores again after this.
+
+ ## Do not
+
+ - Don't blend the eight dimensions into a single numeric qualification
+ score — this stays a go/no-go read backed by named dimensions, not a
+ weighted average.
+ - Don't infer buying authority from title alone — score it from what the
+ transcript actually shows about the person's path to a decision.
+ - Don't add a "recommended next email" or talk-track section unless
+ asked — this skill's job stops at the go/no-go call.
+
+ ## Related skills
+
+ - **`bant`** — for a faster four-criterion advance/no-advance read when a
+ full eight-dimension pass isn't needed.
+ - **`sql-to-qualify`** — for the earlier gate, right after an SQL is
+ assigned, before investing in a full qualification call like this one.
+ - **`qualify-to-poc`** — for the next checkpoint once a deal clears this
+ read and is heading toward a POC/pilot kickoff.
## Sample data
`assets/sample-transcript.txt` — a short synthetic qualification call. Run
against it first before pointing this at anything of your own.
## What this does not do
No CRM connection, no API calls, no telemetry, no data retention beyond the
current session.