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 j4flmao/agent-skills --skill experimentationgit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/experimentation)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/experimentation"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/experimentation/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/j4flmao/agent-skills/experimentation"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/experimentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00112 | $0.06061 |
| Opus 5.5 | $0.00045 | $0.02424 |
| Sonnet 5.5 | $0.00022 | $0.01212 |
| Haiku 4.5 | $0.00011 | $0.00606 |
Grade A, and why
data-science-experimentation 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 1mo 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 — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experimentation
Purpose
Design and analyze rigorous A/B tests and experiments. Enforce proper sample size planning, pre-registration, statistical methods, guardrail monitoring, and decision frameworks.
Agent Protocol
Trigger
Exact user phrases: "A/B test", "experiment", "randomized trial", "sample size", "power analysis", "hypothesis test", "p-value", "multiple testing", "guardrail metric", "experiment design", "treatment effect", "H0", "alternative hypothesis", "statistical significance", "practical significance", "MDE", "minimum detectable effect".
Input Context
- Experiment type (A/B, multivariate, MAB, switchback)
- Primary metric(s) and their baseline values
- Minimum detectable effect (MDE) in absolute or relative terms
- Traffic volume and expected experiment duration
- Unit of randomization (user, session, cluster)
- Guardrail metrics and acceptable thresholds
- Regulatory and ethical considerations
- Existing experiment platform and tooling
Output Artifact
Experiment design with sample size calculation, analysis plan, and decision criteria.
Response Format
## Experiment Design
Hypothesis: {H0 and H1}
Primary Metric: {name, baseline, MDE}
Sample Size: {N per variant, total N}
Duration: {days} at {traffic allocation}
Analysis: {test type, corrections, covariates}
## Analysis Results
Treatment Effect: {estimate, CI, p-value}
Practical Significance: {effect size, decision}
Guardrails: {√ or ✗ per metric}
Completion Criteria
- Pre-registered hypothesis with H0 and H1
- Sample size calculated for desired power (80%+)
- Randomization method selected (simple, stratified, cluster)
- Primary metric defined with baseline and MDE
- Guardrail metrics defined with thresholds
- Statistical test selected (t-test, chi-square, etc.)
- Multiple testing correction applied
- Decision criteria: ship, iterate, or kill
Workflow
Step 1: Hypothesis Development
Formulate clear, falsifiable hypotheses. H0 (null): no effect. H1 (alternative): effect exists in specified direction. A good hypothesis: "Changing the checkout button color from blue to green will increase purchase conversion rate by at least 0.5 percentage points." Pre-register on experiment platform or in documentation before launch. Include rationale, prior evidence, and expected mechanism of action.
What ships with it
6 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.
- 1mo ago First seen · 545 lines · 112 tokens per session scan A b9dbe8f90bbd
data-science-experimentation is a skill published in the GitHub repository j4flmao/agent-skills (34 stars, last pushed 13d ago), licensed MIT. It adds 112 tokens to every session and 6,061 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 2026-09-03.
Other skills, from other repositories
statspai-analysis
Run a full empirical / causal analysis in Python with StatsPAI (import statspai as sp) — applied-economics style (DID / RD / IV / synthetic control / DML / matching with estimating equation, identifying assumption, Table 1, main table, event-study figure, robustness gauntlet, Word / Excel / LaTeX export), epidemiology…
cnsplots
Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise physical figure dimensions…
audit-ml-pipeline
Read-only audit of one persisted skore report: audit/NN .py (jupytext percent), 1:1 with experiments/ and journal/. Do not execute it. Run materialize.py once. Never call skore.evaluate or project.put. TRIGGER when a completed run needs an audit, the user asks to audit, show, or re-audit an experiment, a re-run…
evaluate-ml-pipeline
Evaluate one learner with skore.evaluate. The splitter and any non-default score are already on the DataOp from build-ml-pipeline. This skill writes the call without splitter=, persists the report, and records the locator. When the locked split is the training table and test table that shipped with the data, fit on…
model-ml-pipeline
Deterministic entry point for modeling. On a first landing, write the locked baseline design note and ask for approval. Later landings offer only the choices the workspace justifies (an EDA proposal, Backlog, discussion). A missing modeling lock loads frame-ml-problem and stops. After a design is approved, coordinate…
alterlab-qiime2-amplicon
Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 distribution (2026.7; the "amplicon" distribution was renamed "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier…