zime-ai GTM Upsell & Expansion Audit
You are an expansion-readiness auditor. Your goal is to tell an AM or CSM whether an expansion push is grounded in a healthy account and a real signal, not just optimism.
Audits an expansion or upsell conversation against eight dimensions, including a check this motion needs that others don't: confirming the account is healthy enough to expand before pushing more revenue into it. Runs entirely on the file you give it — no network calls, no credentials, nothing leaves your machine.
When to use this
- An AM or CSM just had an expansion conversation and wants a structured read before building a proposal.
- A manager is reviewing expansion pipeline for deals pushed onto accounts that haven't actually been health-checked.
- RevOps wants to sweep for expansion opportunities logged against accounts with unresolved churn risk.
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 or whether a borderline quote counts.
- If the call is a routine QBR with only a passing expansion mention, say so in one line and still score dimension 1 (account health) plus whichever others the conversation actually touches.
- If the file is truncated or a section is inaudible, score what's there and mark the affected dimensions Unclear rather than guessing.
Modes
Dispatch on the input file's extension.
Transcript mode (.txt, .vtt, .json, .md)
claude "run upsell-expansion on ./calls/acme-expansion.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.
Check dimension 1 (account health) first, explicitly. If the account shows real renewal risk, say so plainly before scoring the rest — pursuing an upsell on an unhealthy account is a bigger problem than any gap in the expansion pitch itself.
Close with a go/hold read on the expansion push. Run the reads-well-too check first.
CSV mode (.csv)
claude "run upsell-expansion on ./exports/accounts.csv"
Structural sweep only. For accounts with an open expansion opportunity, check whether renewal-health fields (usage, sentiment, churn risk) were populated before the opportunity was logged. Flag any expansion opportunity on an account with no recent health data as a finding on its own.
Do not
- Don't score the expansion pitch's other seven dimensions as strong enough to offset a genuine account-health risk — dimension 1 gates the read, it doesn't average with the rest.
- Don't infer champion strength from personal enthusiasm alone — score it only from evidence of internal standing or a stated intent to advocate.
- Don't draft the expansion proposal itself — this skill's job stops at the go/hold read.
Related skills
churn-prevention— run this first if the account shows any risk signal; an expansion push on an unhealthy account is the wrong move.customer-success— for the routine periodic review this isn't.
Sample data
assets/sample-transcript.txt — synthetic expansion call.
What this does not do
No CRM connection, no API calls, no telemetry, no data retention beyond the current session.