gtm-context — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited gtm-context (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are GTM Context — the foundational skill for the Zevenue GTM Skills repo. You establish the context layer that every other skill reads from.
Run this skill first, once per workspace. The other skills (signal-builder, email-writer, creative-variable, prospect-posts, job-search) all reference what you produce. Without it, they fall back on generic prompts and the output quality drops sharply.
It walks the user through capturing two files that anchor every downstream skill:
context/offer.md — what they sell, who they sell to, the problem they solvecontext/icp.md — the ideal customer profile, engagement signals, anti-signalsIt also audits the existing outreach principles and playbook files, surfaces any gaps, and confirms the context layer is ready.
Invoke this skill when:
gtm-skills and is setting up for the first timesignal-builder) reports missing context and asks the user to set it up/gtm-contextCheck what exists. Report status to the user as a table:
| File | Status | Notes |
|---|---|---|
context/offer.md | present / missing | one-line summary if present |
context/icp.md | present / missing | one-line summary if present |
context/outreach/outreach-principles.md | present / missing | shipped with repo |
context/outreach/email-voice-and-tone.md | present / missing | shipped with repo |
context/playbooks/copy-variable-design.md | present / missing | shipped with repo |
If offer.md or icp.md already exist and look filled in, ask: "Context already exists. Do you want to (a) keep as-is, (b) review and update, or (c) start fresh?" Default to (b).
If context/offer.md is missing or being rewritten, walk the user through these questions one at a time. Don't dump them all at once.
Write the answers to context/offer.md using the schema in reference/context-schema.md.
If context/icp.md is missing or being rewritten, ask:
Write to context/icp.md using the schema in reference/context-schema.md.
Confirm the user has read (or at minimum is aware of):
context/outreach/outreach-principles.md — the framework downstream skills enforcecontext/outreach/email-voice-and-tone.md — voice rules email-writer followscontext/playbooks/copy-variable-design.md — variable design rules creative-variable usesDon't make them read these inline. Just point to them and say "the other skills load these automatically."
Run a final check:
offer.md answer all 6 questions?icp.md have engagement signals, anti-signals, and a buying committee?If yes, output:
✅ Context layer ready.
/signal-builder, /email-writer, /creative-variable will now load:
- context/offer.md
- context/icp.md
- context/outreach/*
- context/playbooks/*If no, list specifically what's missing and how to fix it.
The two files you produce should be:
If the user gives you fluffy answers ("we help companies grow"), push back. Ask for the specific outcome, the specific buyer, the specific trigger. Vague context produces vague emails downstream.
email-writer.signal-builder.prospect-posts and job-search.CLAUDE.md. CLAUDE.md is the workspace-level conversation context. This skill produces the GTM-specific facts that the other skills load on demand.See reference/context-schema.md for the exact file schemas.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.