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 stefanoskarakasis/Product-Marketing-Skills --skill brand-voicegit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-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/stefanoskarakasis/product-marketing-skills/brand-voice)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/brand-voice"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/brand-voice/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/stefanoskarakasis/product-marketing-skills/brand-voice"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/brand-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.02571 |
| Opus 5.5 | $0.00033 | $0.01028 |
| Sonnet 5.5 | $0.00016 | $0.00514 |
| Haiku 4.5 | $0.00008 | $0.00257 |
Grade A, and why
brand-voice 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 11d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brand Voice
How This Works
Voice is who you are — it doesn't change. Tone is how you show up in a specific moment — it shifts by buyer and channel, intentionally, not randomly. This skill builds a voice guide that survives contact with a blank page: every trait gets an example, every persona gets a tone profile, every channel gets a table row. It deepens your brain's existing Section 4 in place rather than creating a second voice file — one source of truth stays intact for every downstream writing skill.
Step 0 — Load brain Section 4 (current voice guide, however thin),
Section 2 (ICP/personas, for tone-by-persona grounding), and any
guardrails from /context/meta-patterns.md.
Step 1 — Establish brand personality and its edges: 3-4 words that couldn't apply to a competitor, plus what the brand explicitly rejects.
Step 2 — Map tone by persona: for each buyer in the committee, what they care about, how they prefer information, what makes them distrust a vendor immediately, what makes them lean in. Never pre-filled — every committee is different.
Step 3 — Build the channel tone table and forbidden-language list, then run the one-sentence voice test against both.
Step 4 — Deepen brain Section 4 with the guide (on user confirmation).
Step 5 — Learning Close: log the session to /context/skill-sessions.md.
Trigger
-
When: Defining or sharpening how the brand sounds — voice attributes, tone shifts by persona or channel, forbidden language, or auditing copy that's drifted off-brand.
-
Not for: Positioning statement or messaging hierarchy itself → use
positioning-messaging. Writing the actual copy → no dedicated drafting skill exists yet in this repo; produce copy withinpositioning-messaging's own output modes, using this skill's voice guide as input. Buying-committee mapping →buyer-personas, run first if tone-by-persona needs real committee data instead of guessed roles. -
Example prompts:
- "How should we sound on LinkedIn vs. a sales deck?"
- "Our copy feels off — voice audit"
- "We sound like everyone else"
- "Write this in our voice for the Champion persona"
- "Build our voice guide"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed · -2 lines · -2 tokens per session e457325fc234
- 16d ago Changed · +2 lines 21c63a90ec12
- 19d ago Changed 62f7ecd42a13
- 20d ago Changed 5ae908b40a20
- 25d ago Changed · +13 lines 305e41c65b2b
- 1mo ago Changed · +3 lines a1327a09863c
- 1mo ago First seen · 267 lines · 84 tokens per session scan A 6a0d99814a3e
brand-voice is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 2,571 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
report
A way to export a chat card or reply as a standalone HTML report, meaning a file that can open in a browser without the chat application. It preserves the card template, including right-to-left Persian or left-to-right English layouts.
k8s-rightsize
Right-size Kubernetes CPU and memory requests from Prometheus usage (p95 CPU, p98 memory over 7 days), size the node count, tune KEDA autoscaling. Use when asked to rightsize workloads, cut node cost, or "how many nodes do we need".
owasp-security
Deep OWASP reference: Top 10 2025, ASVS 5.0, secure patterns, per-language quirks, LLM Top 10 and agentic AI security. Use for an in-depth security review, auth work, or hardening an LLM or agent app. For the everyday baseline use secure-coding.
fig
One self-contained HTML file holding a looping animated SVG, for ideas that move: flows, loops, retries, queues, fan-outs. Use when the user says "fig" or a diagram would be better animated.
brand
A project-specific visual identity for chat cards and saved reports, using the project's colors, logo, and fonts. It finds these details in the repository or asks the user for them, then stores the result in a committable `.readable/` folder.
workspace-rules
A set of guidelines for deciding which rules belong in a repository's workspace instructions and which should be enforced by its build or checks.