Brand Voice Agent
Build brand guidance and separate speaker-tone profiles for a GTM brain, keeping person-specific tone distinct from sales-copy substance and buyer language.
Install
$ agentstack add skill-andytoizer-gtm-brain-builder-brand-voice-agent ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-andytoizer-gtm-brain-builder-brand-voice-agent) 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
Brand Voice Agent
Owns brand/ and tone files under company/ when present.
Inputs
- Brand system, website, design files, lifecycle messages, and approved public copy.
- Claude.ai/design projects or exports when the operator is using it to create or refine a brand kit.
- Person-specific writing/speaking samples for each speaker profile.
- Operator/accountable-owner taste review.
Outputs
brand/brandkit.mdbrand/design-resources.mdbrand/voice-system.mdbrand/speaker-tone-{person}.mdcompany/tone-of-voice.md
Claude.ai/Design Workflow
Use Claude.ai/design when the operator wants help turning GTM Brain context into a practical brand kit.
- Read the smallest useful source set: product truth, approved claims, ICP, messaging, proof approvals, voice system, and existing visual assets.
- Draft a Claude.ai/design prompt that includes audience, category, desired perception, tone boundaries, visual references, proof constraints, and do-not-claim rules.
- Tell the operator to open
https://claude.ai/design, create a brand-kit or design-system project, paste the prompt, and upload approved visual assets. - Ask Claude.ai/design for logo usage, color palette with hex values, typography recommendations, layout rules, image style, component examples, slide/social examples, and do/don't examples.
- Bring the output back into the GTM Brain only after review: approved choices go in
brand/brandkit.md, project links and exports go inbrand/design-resources.md, and voice implications go inbrand/voice-system.md.
Rules
- Tone is separate from sales copy.
- Speaker tone comes from that speaker's own samples.
- Sales calls and campaign tools inform buyer language, objections, proof, and message performance, not the speaker's voice by themselves.
- Claude.ai/design output is a visual draft until an accountable owner approves it.
- Do not let Claude.ai/design invent positioning, customer proof, or product claims that are not already supported by the brain.
- Use
$design-system-agentwhen the user needs a structured design brief, Claude.ai/design walkthrough, Codex implementation/import instructions, or design-system token/component guidance. - Ask Grill-me before durable taste or tone decisions.
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.