Install
$ agentstack add skill-zime-ai-zime-gtm-skills-sandler ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Sandler Submarine Audit
Audits a sales conversation against the seven compartments of the Sandler Selling System's submarine. Unlike the stage skills in this repo, Sandler isn't tied to one point in the deal — the submarine's whole premise is that each compartment must be sealed (secured) before the rep moves to the next, so this skill checks order and completeness, not just topic coverage.
When to use this
- A rep pitched a solution and you want to know whether they'd actually
earned the right to — did they secure an up-front contract and surface real pain first, or did they jump straight to features.
- Checking whether a "close" on a call was a real mutual decision or the
rep assuming yes and steamrolling into next steps.
- RevOps wants to sweep a pipeline export for deals where Sandler-relevant
fields (budget confirmed, decision process, next-step contract) are missing before a forecast call.
Modes
Transcript mode (.txt, .vtt, .json, .md)
claude "run sandler on ./calls/acme-call.txt"
Read the transcript, then score it against each compartment in references/rubric.md, in submarine order. For every compartment, output:
- Status — Covered / Partial / Missed / Not applicable to this call
- Evidence — a direct quote from the transcript. If a compartment
genuinely wasn't reachable on this specific call (e.g. Fulfillment on a first discovery call that never got near a close), say Not applicable rather than scoring it Missed.
- Note — one line, only if Partial or Missed
Pay particular attention to order: a compartment scored Covered late in the call after an earlier compartment was skipped (e.g. pitching before Pain was surfaced) is a submarine violation worth calling out explicitly, not just a missed box.
Close with the single biggest submarine violation on this call — which compartment got skipped or rushed, and what it cost the rep — and what to do differently next call.
CSV mode (.csv)
claude "run sandler on ./exports/pipeline.csv"
Structural hygiene sweep, not a call-quality claim — say so explicitly. For each deal row, check whether fields corresponding to the seven compartments (especially budget confirmed, decision process, next-step commitment) are present and non-trivial. Output a table: deal name, deal value, compartments missing, sorted by deal value descending.
Sample data
assets/sample-transcript.txt is a synthetic call that bonds well and gets an up-front contract, but pitches before pain is fully surfaced, assumes budget instead of discussing it, and closes hard instead of tentatively — run the skill against it first.
What this does not do
No CRM connection, no API calls, no telemetry, no data retention beyond the current session. It reads the file you point it at and nothing else.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: zime-ai
- Source: zime-ai/zime-gtm-skills
- License: MIT
- Homepage: https://zime.ai
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.