Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add minhnv0807/ai-business-skills --skill 35-brand-voice-globalgit clone --depth 1 https://github.com/minhnv0807/ai-business-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/minhnv0807/ai-business-skills/35-brand-voice-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/35-brand-voice-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/35-brand-voice-global/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/35-brand-voice-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/35-brand-voice-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00163 | $0.02834 |
| Opus 5 | $0.00081 | $0.01417 |
| Sonnet 5 | $0.00033 | $0.00567 |
| Haiku 4.5 | $0.00016 | $0.00283 |
Grade A, and why
35-brand-voice-global scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Voice (Global)
The foundation skill of the content cluster. Every other content skill — 36-content-brief-global, 37-social-caption-global, 04-script-video-global, 05-ad-copy-global, 14-email-marketing-global, 38-community-seeding-global — reads this document before writing. Without it, output is technically correct and tonally inconsistent.
Information gathering
Read .agents/product-marketing-context-global.md and any existing brand guideline first. If information is missing, ask up to 4 questions:
- What does the brand sell, to whom, at what price point — and what should a reader feel after reading its content?
- Which 3 adjectives describe the brand's actual character — and how must the brand never be perceived?
- Is there a brand or writer whose voice is close to the target? (reference only, never to copy)
- What words do customers use when they talk about the brand or category? Paste real reviews, comments, support tickets, or call notes — this is the single most valuable vocabulary source.
Principles
- Voice is a living document. Review quarterly or whenever the brand pivots. Do not write it once and file it.
- It is a compass, not a statute. Use it to check work, and flex by context.
- The core voice is constant across channels. Only format and length change per platform — never the personality.
- Vocabulary comes from real customer language. Run
09-customer-insight-globalfirst so word choices are sourced, not invented. - Final test: cover the logo and it still reads as you. If it could be any competitor in the category, it is not done.
- Every claim in the voice must be substantiable. A confident voice does not license unsupported superiority or results claims — FTC advertising rules apply to organic posts, not just ads.
Workflow
1. Lock brand personality: 3 adjectives
Pick exactly 3 core adjectives, each with one sentence explaining why it reflects the brand truthfully. More than 3 dilutes the voice.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 232 lines · 163 tokens per session scan A d138af91209e
35-brand-voice-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 163 tokens to every session and 2,834 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
mcp-oauth-remote-gateway
Manual OAuth for remote MCP servers on headless gateways.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
honcho
Configure and troubleshoot Honcho memory for Hermes.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
hyperframes
Render MP4/WebM videos from HTML compositions.