agentsclimarketplace
Sign in

Growth experiment analysis

Skill duandigi/duandigi-growth-marketing-skill/skills/growth-experiment-analysis

Use this skill when evaluating a completed or in-progress growth experiment, A/B test, before-after test, cohort comparison, or rollout to decide whether to scale, iterate, stop, or gather more data.From its SKILL.md

Install
npx -y skills add duandigi/duandigi-growth-marketing-skill --skill growth-experiment-analysis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.7 KB, 446 tokens by cl100k_base, as published. Nobody here has run it

Growth Experiment Analysis

Purpose

Turn experiment data into a calibrated decision with explicit uncertainty.

Inputs

  • Pre-registered hypothesis and decision rule
  • Variant or period results
  • Sample sizes and measurement window
  • Guardrail metrics, incidents, and implementation notes

If critical input is unavailable, label it unknown and create a research or instrumentation task. Do not invent values.

Workflow

  1. Verify that the experiment ran as designed and that tracking was stable.
  2. Check sample ratio, exposure, contamination, seasonality, concurrent changes, and missing data.
  3. Compare the primary metric and guardrails using absolute and relative changes.
  4. Distinguish directional evidence, practical significance, and statistical confidence.
  5. Check important segments only if they were pre-specified or label them exploratory.
  6. Make one decision: scale, iterate, stop, or inconclusive; explain what would change the decision.
  7. Record the result in a reusable learning statement rather than declaring universal truth.

Required output

Return a concise, decision-oriented response containing:

  • Integrity checks
  • Primary result
  • Guardrail result
  • Confidence and limitations
  • Decision
  • Learning
  • Follow-up action

Label important statements as confirmed, inferred, assumed, or unknown when the distinction affects the decision.

Guardrails

Do not:

  • P-hacking or selective segments

  • Calling an underpowered result a win

  • Ignoring negative guardrails

  • Claim guaranteed growth or present an estimate as observed fact.

  • Recommend spam, fake reviews, impersonation, deceptive urgency, dark patterns, policy evasion, or unauthorized production changes.

  • Hide material uncertainty, tracking limitations, or possible harm.

When an action can spend money, publish content, contact people, change production systems, delete data, or alter access, produce a plan and request explicit authorization rather than executing automatically.

Completion check

Before finishing, verify that the output:

  • answers a specific growth decision;
  • uses the supplied business context;
  • separates evidence from assumptions;
  • defines a measurable next step;
  • includes risks, constraints, and missing data;
  • is no longer than necessary for the decision.

What ships with it: 1 file

1.3 KB alongside SKILL.md

evals/

Keep looking

Skills are one crate of 326,758. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.