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 ideal-customer-profilegit 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/ideal-customer-profile)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/ideal-customer-profile"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/ideal-customer-profile/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/ideal-customer-profile"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/ideal-customer-profile.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 | $0.00089 | $0.03091 |
| Opus 5.5 | $0.00036 | $0.01236 |
| Sonnet 5.5 | $0.00018 | $0.00618 |
| Haiku 4.5 | $0.00009 | $0.00309 |
Grade A, and why
ideal-customer-profile 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideal Customer Profile
How This Works
An ICP built from opinion is a guess with a template around it. This skill builds one from evidence — survey responses, interview transcripts, usage data, win/loss notes — synthesized across four layers: who they are (demographics), how they decide (behaviors), what they're hiring your product to do (Jobs to Be Done), and what's actually broken for them (needs). It deepens your brain's existing Section 2 in place rather than creating a second ICP file — one source of truth stays intact for every downstream skill.
Step 0 — Load brain Section 2 (current ICP, however thin) and any
guardrails from /context/meta-patterns.md.
Step 1 — Gather and segment: collect available research, then identify which customer cohort actually has the value — highest retention, fastest time-to-value, best expansion — since that's who the profile should describe, not just "whoever we have."
Step 2 — Profile across the four layers: Demographics, Behaviors, JTBD, Needs.
Step 3 — Deepen brain Section 2 with the profile (on user confirmation).
Step 4 — Learning Close: log the session to /context/skill-sessions.md.
Trigger
- When: Defining or sharpening who you sell to from research data — PMF surveys, interview transcripts, usage analytics, win/loss notes — or when brain Section 2 is firmographic-only with no behavioral or JTBD layer.
- Not for: Choosing among several candidate segments once the ICP is
profiled →
beachhead-segment, run after. Turning a confirmed ICP into positioning or messaging →positioning-messaging, run after. Full brain build from zero →product-marketing-context, run first if no brain exists at all. - Example prompts:
- "Build my ICP from our PMF survey data"
- "Here are 8 customer interviews — define our ideal customer"
- "Who are our best-fit customers? I have usage and churn data."
- "Our ICP is just company size and industry. Go deeper."
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 · -5 tokens per session 2b41d6da0c61
- 16d ago Changed · +3 lines bf009936ead3
- 19d ago Changed ddf323edd6a9
- 20d ago Changed · +12 lines 6519a04f7183
- 25d ago Changed · +13 lines ae5d6864f689
- 1mo ago Changed · +2 lines 4345966e4cf7
- 2mo ago First seen · 290 lines · 94 tokens per session scan A 3fc79cacb457
ideal-customer-profile is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 3,091 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.