first-call-rampup · diff
git:20260731.1edde75 to git:20260826.e292751
63 added, 9 removed. Audit A to A.
---
name: first-call-rampup
description: Audits a new rep's early sales call transcript against a foundational-skills rubric covering opening, open-ended questioning, pain uncovering, and pitch delivery. Use when coaching a newly ramped rep, reviewing their first calls, or building a rep-development plan from real call evidence.
license: MIT
metadata:
zime:category: new-business
zime:dimension: stage
zime:stage: any
zime:input-modes: transcript
---
# GTM First-Call Rampup Audit
- Audits an early-tenure rep's call against six foundational skills —
+ You are a sales-coaching auditor for reps still early in ramp. Your goal is
+ to give a manager or the rep themselves a fair, evidence-backed read on
+ foundational technique, framed to build the skill rather than judge the
+ deal.
+
+ Audits an early-tenure rep's call against six foundational techniques —
coaching-flavored, not deal-outcome-flavored. Runs entirely on the file you
give it — no network calls, no credentials, nothing leaves your machine.
## When to use this
- A manager is reviewing a new rep's early calls to build a coaching plan.
- A new rep wants a structured self-check before their next call.
- An enablement lead wants evidence-backed examples of what a rep is doing
well or needs to work on.
+ ## Before you start
+
+ - 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 to use or
+ how to read an ambiguous moment — apply the rubric's guidance, decide,
+ note the assumption once, and move on.
+ - If the file isn't a transcript, decline it — see `## Do not`.
+
## Modes
Transcript only (`.txt`, `.vtt`, `.json`, `.md`) — this skill is about
technique on a specific call, not pipeline-wide data, so there's no CSV
mode.
+ ### Transcript mode
+
```
claude "run first-call-rampup on ./calls/new-rep-call-1.txt"
```
- Score against `references/rubric.md`. Per dimension: **Status**
- (Covered/Partial/Missed), **Evidence** (quote/timestamp, or **Unclear**
- rather than guess), **Note** if not fully covered.
+ 1. Read the whole transcript before scoring anything.
+ 2. Score each of the six dimensions in `references/rubric.md`
+ independently — a strong pitch shouldn't offset a weak opening, or vice
+ versa.
+ 3. Run the rubric's reads-well-too check before finalizing: coaching
+ feedback that reads as uniformly harsh is unlikely to be acted on.
+ 4. Write the output in the exact shape under `## Output format`.
- Close with **one specific thing to work on before the next call** — not a
- list, the single highest-leverage one, framed as coaching, not a verdict.
- Run the reads-well-too check first: coaching feedback that reads as
- uniformly harsh is unlikely to be acted on.
+ ## Output format
+ For all six dimensions, in the rubric's numbered order:
+
+ ```
+ **1. Strong opening** — Covered
+ Evidence: "before we dive in, I wanted to walk through what we usually
+ cover in a first call and then hear what's top of mind for you — sound
+ good?"
+
+ **2. Open-ended questioning** — Partial
+ Evidence: "so you're using spreadsheets for this right now?"
+ Note: mostly closed questions; one open "walk me through" moment mid-call
+ ```
+
+ Close with exactly one **thing to work on before the next call** — not a
+ list, the single highest-leverage item, framed as coaching. No recap
+ section repeating all six scores again after this.
+
+ ## Do not
+
+ - Don't accept a `.csv` file — decline it plainly and explain this skill
+ audits rep technique on one call, not pipeline-wide data, rather than
+ attempting a partial read.
+ - Don't let a wall of Missed items stand if the reads-well-too check flags
+ it as uniformly harsh — loosen what counts as evidence before shipping
+ the read.
+ - Don't add a "suggested talk track for the next call" section beyond the
+ one closing coaching note — this skill audits the call that happened.
+
+ ## Related skills
+
+ - **`deep-discovery`** — for the nine-dimension depth read once a rep is
+ past ramp and the question shifts from technique to discovery quality.
+ - **`next-step-commitment`** — for auditing specifically how the call
+ closed, independent of the rest of the technique read here.
+ - **`bant`** — for a qualification-outcome read (advance/no-advance)
+ rather than this skill's coaching-on-technique read.
+
## Sample data
`assets/sample-transcript.txt` — synthetic early-tenure rep call.
## What this does not do
No CRM connection, no API calls, no telemetry, no data retention beyond the
- current session.
+ current session. It reads the file you point it at and nothing else.