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 krillinai/growth-skills --skill experiment-designgit clone --depth 1 https://github.com/krillinai/growth-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/krillinai/growth-skills/experiment-design)<a href="https://agentmods.dev/skills/krillinai/growth-skills/experiment-design"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/experiment-design/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/krillinai/growth-skills/experiment-design"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/experiment-design.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 | $0.00056 | $0.01487 |
| Opus 5 | $0.00028 | $0.00744 |
| Sonnet 5 | $0.00011 | $0.00297 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
experiment-design 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 12d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Design
Turn an important uncertainty into a trustworthy evidence design and an accountable decision. Use randomized experiments only when assignment, exposure, outcomes, ethics, reversibility, traffic, maturation, and interference make them appropriate; otherwise choose the strongest bounded alternative without relabeling it an experiment.
Read experiment-contract.md for intake, evidence, privacy, and required fields. Read design-methods.md before choosing units, assignment, metrics, power inputs, alternatives, or quality controls. Read readout-methods.md before interpreting results, segments, proxies, guardrails, or uncertainty. Use playbook-sources.md to cite the pinned Growth Playbook basis.
Select One Mode
| Mode | Use |
|---|---|
design |
Decide whether and how to run a controlled experiment or alternative evidence design |
review |
Audit a proposed or running design for decision fit, ethics, assignment, exposure, metrics, power, interference, and quality risks |
readout |
Interpret supplied mature results against the frozen specification and make a bounded decision recommendation |
Name one primary mode. Keep preregistered, amended, and exploratory analysis visibly separate.
Gate The Experiment
Record the decision, owner, important uncertainty, mechanism, reversibility, legal and ethical boundary, eligible population, controllable intervention, measurable outcome, maturation horizon, traffic or sample constraints, and interference risk.
Do not default to an A/B test when a severe defect should be fixed, exposure cannot be controlled, the action is unethical or irreversible, traffic cannot support the required sensitivity, the outcome matures too late for the decision, or spillovers dominate. Recommend qualitative research, offline evaluation, simulation, bounded pilot, switchback, interrupted time series, difference-in-differences, regression discontinuity, or matched comparison only when its assumptions fit.
What ships with it
4 files 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.
- 12d ago First seen · 83 lines · 56 tokens per session scan A f3a4421e9157
experiment-design is a skill published in the GitHub repository krillinai/growth-skills (43 stars, last pushed 16d ago), licensed MIT. It adds 56 tokens to every session and 1,487 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…