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 buyer-personasgit 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/buyer-personas)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/buyer-personas"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/buyer-personas/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/buyer-personas"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/buyer-personas.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 | $0.00092 | $0.03442 |
| Opus 5.5 | $0.00037 | $0.01377 |
| Sonnet 5.5 | $0.00018 | $0.00688 |
| Haiku 4.5 | $0.00009 | $0.00344 |
Grade A, and why
buyer-personas 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buyer Personas — Skill
How This Works
Enterprise B2B purchases aren't made by personas — they're made by
committees. A messaging deck built for one buyer title routinely misses
the person who can actually kill the deal. This skill maps power first
(who approves, who champions, who can veto, who just uses the thing) and
only then builds messaging personas from that map — Dunford-structured,
anchored to named alternatives, ready to feed straight into
positioning-messaging.
It reads your brain's ICP and alternatives (Sections 2 and 3) instead of
starting cold, and it compounds the way every other skill in this repo
does — one row per session in /context/skill-sessions.md — not through a
separate knowledge or decisions system of its own.
Step 0 — Load brain Sections 2 (ICP) and 3 (Alternatives), and any
guardrail from /context/meta-patterns.md fired 2+ times.
Step 1 — Gather input: research data if provided, or run a structured 5-question intake if none exists.
Step 2 — Map the committee: identify roles by behavior, not title, and extract kill pattern / champion pattern / messaging gap for each.
Step 3 — Build messaging personas: one card per role that needs differentiated messaging, each anchored to named alternatives.
Step 4 — Deliver both outputs, then hand off to positioning-messaging
with an explicit note on which persona is primary.
Step 5 — Learning Close: log the session to /context/skill-sessions.md.
Trigger
- When: Mapping who's actually involved in a B2B purchase decision, or building persona cards to feed into positioning and messaging work.
- Not for: Positioning statement or messaging hierarchy itself →
positioning-messaging, run after this skill. Segment selection among multiple candidates →beachhead-segment. Deep ICP research (demographics/behaviors/JTBD/needs at the org level, not committee-level) →ideal-customer-profile, run before this skill if the ICP itself is still thin. - Example prompts:
- "Map our buying committee for enterprise deals"
- "Who do we need to win over to close this?"
- "Build persona cards for our sales enablement deck"
- "Our deals keep stalling in legal — who's actually involved?"
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 · -1 lines · -2 tokens per session da998404d564
- 16d ago Changed 396da7046b43
- 19d ago Changed 933407447d4a
- 25d ago Changed · +13 lines a57047b721c7
- 1mo ago Changed · +4 lines 63f4776309d7
- 2mo ago First seen · 335 lines · 94 tokens per session scan A 4ed312259cce
buyer-personas is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 3,442 once invoked, about $0.0004 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 2026-08-31.
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.