Install
$ agentstack add skill-andytoizer-gtm-brain-builder-gtm-brain-builder ✓ 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
GTM Brain Builder
Use this as the orchestrator. The goal is a usable operating brain, not a generic notes repo.
Required First Moves
- Read or create
README.md,AGENTS.md,systems/mvp-checklist.md,systems/sources.md,systems/tools.md,systems/grill-me.md, andprojects/{operator}/building-the-brain/README.md. - Set or refresh the MVP checklist before section work so the agent stays in "build the brain" mode until the MVP is complete.
- Invoke or follow
$source-connector-inventorybefore filling strategy sections. - Keep
$grill-mealways on for interpretation decisions. - Use
$session-relayfor long builds and handoffs.
MVP Checklist Discipline
The orchestrator owns systems/mvp-checklist.md.
That file must make the current boundary obvious:
Current phase: usuallyBuild the brain MVP.In scope: source inventory, canonical docs, proof/ICP/messaging/tone/sales memory, relay, refresh design.Out of scope until MVP complete: launching campaigns, building operating dashboards, running GTM tasks, creating downstream website/deck/campaign assets, or adding automations that assume the brain is finished.MVP checklist: the concrete items required before the brain is usable.Next checklist: what the following session should do next.
At the start of each session, read the MVP checklist before doing work. Before handoff, update it with completed items and the next recommended checklist.
Section-Agent Order
Run section work in this order unless the user has a sharper priority:
$source-connector-inventory$company-core-agent$customer-icp-agent$messaging-market-agent$brand-voice-agent$design-system-agentwhen the user needs a brand kit, design-system brief, Claude.ai/design workflow, or Codex import instructions$sales-memory-agent$freshness-automation-agent
If actual subagents are available and the user explicitly asks for parallel agents, use the plugin-level agent definitions in ../../agents/ and split work by section with disjoint write scopes. Otherwise, act as the relevant specialist yourself and load only the relevant skill.
Agent Hierarchy
../../agents/gtm-brain-orchestrator.md: owns sequencing, MVP checklist, and handoff.../../agents/source-connector-agent.md: owns source coverage.../../agents/company-core-agent.md: owns company/product truth.../../agents/customer-icp-agent.md: owns customers, proof, and ICP.../../agents/messaging-market-agent.md: owns messaging and market.../../agents/brand-voice-agent.md: owns brand and speaker tone.../../agents/design-system-agent.md: owns design-system briefs, design tool workflows, and import guidance.../../agents/sales-memory-agent.md: owns sales memory.../../agents/freshness-automation-agent.md: owns refresh design.
Decision Protocol
Before promoting interpretation into durable context, ask:
Question:
My current best hypothesis:
Why this matters:
What changes depending on your answer:
Ask one question at a time. Use source work to make the question sharper.
References
- Read
../../references/build-lessons.mdfor distilled GTM Brain build lessons. - Read
../../references/brain-section-map.mdbefore changing repo structure. - Read
../../references/output-quality-rubric.mdbefore marking a section complete.
Done State
A first usable GTM Brain has:
- MVP checklist with explicit non-goals and next checklist.
- Connected-source inventory and access gaps.
- Source priority and update rules.
- Company/product truth with approved and working claims separated.
- Customer/proof/ICP docs grounded in commercial, CRM, usage, and customer evidence.
- Messaging and market docs grounded in buyer language and proof.
- Brand and speaker-tone profiles separated from sales copy.
- Design-system brief and import notes when visual systems are in scope.
- Sales memory with campaign lessons and caveats.
- Session relay handoff and transcript archive policy.
- Proposed refresh cadence.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Andytoizer
- Source: Andytoizer/gtm-brain-builder
- License: MIT
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.