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 experiment-docgit 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/experiment-doc)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/experiment-doc"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/experiment-doc/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/experiment-doc"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/experiment-doc.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 | $0.00049 | $0.02798 |
| Opus 5.5 | $0.00020 | $0.01119 |
| Sonnet 5.5 | $0.00010 | $0.00560 |
| Haiku 4.5 | $0.00005 | $0.00280 |
Grade A, and why
experiment-doc 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Doc Builder
I help you design experiments that actually prove something. Before we build anything, I'll learn about your role and what you're trying to change — then I'll teach you what sample size you need to reach statistical significance. Only ideas that can scale to significance become experiment briefs.
Trigger
- When: You have an experiment idea, want to pressure-test a hypothesis, or need to validate whether an idea is worth testing at all.
- Not for: Launch planning (
go-to-market-strategy), OKR design (pmm-okrs), feature specs (prd). Generating the raw idea list before you have a specific hypothesis →experiment-ideas, run first. - Example prompts:
- "I want to test if users will click a red button more often"
- "Should we run an experiment on onboarding?"
- "Will changing our email subject line increase opens?"
- "Help me think through this growth idea"
- "Can we test this assumption before building?"
Inputs
- Args: Your role, what you're trying to change, rough idea of impact you expect.
- Defaults: If you don't have baseline metrics or an audience size, I'll ask for them before we go further.
- Context keys:
/foundation/brain.md— optional; ICP (Section 2), Market Context (Section 5), Proof Points Registry (Section 6)/context/meta-patterns.md— optional; recurring patterns the user has logged from prior experiments
Pre-flight
- If
/context/meta-patterns.mdexists in the user's workspace, check for recurring weaknesses they've logged from prior experiments. If a pattern applies, surface a guardrail prompt before Step 1. Skip silently if the file doesn't exist. - Ask three diagnostic questions before anything else: What's your role? What are you testing? What's your hypothesis about why it will work?
- Load
/foundation/brain.mdif exists. Use ICP to scope realistic audiences.
Steps
Step 1: Learn About You and Your Experiment
Ask three diagnostic questions upfront:
Q1: What's your role? (Product Manager, Growth Marketer, Designer, etc.)
This tells me how to calibrate my guidance. A PM thinking about conversion behaves differently than a marketer thinking about engagement.
Q2: What are you trying to change? (specific metric, not vague goals like "increase engagement")
You must name the exact metric. "Increase button clicks" is not enough. "Increase 'Add to Cart' clicks from 3.2% to 4.1%" is real.
Q3: Why do you think it will work? (your hypothesis about cause and effect)
Don't overthink this. "I think red buttons are more attention-grabbing" is fine. I'll tighten it up. But you need to start with a causal idea, not just a hunch.
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 66cacc610085
- 19d ago Changed 2830ce430ac2
- 23d ago Changed · +2 lines e7c4e89b82e1
- 1mo ago Changed · +2 lines 687c1d1deb8b
- 1mo ago Changed 52817714c5a9
- 2mo ago First seen · 191 lines · 51 tokens per session scan A 74686488dca4
experiment-doc is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 2,798 once invoked, about $0.0002 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.