Skills ad-test-designer
πŸ“¦

ad-test-designer

v19.0.0 Content revision r2 Safe πŸ“ Filesystem accessβš™οΈ External commands🌐 Network access

Design reliable paid-ad experiments

Paid-ad tests can produce misleading results when variables, thresholds, and decision ownership are unclear. This skill creates structured test plans and interprets exported results with separate statistical and practical-effect checks.

Supports: Claude Codex Code(CC)
πŸ₯‰ 77 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "ad-test-designer" from https://skillstore.io/skills/aaron-he-zhu-ad-test-designer.md and its manifest at https://skillstore.io/api/skills/aaron-he-zhu-ad-test-designer/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Test it

Using "ad-test-designer". A landing-page test with a 3% baseline conversion rate and a 15% target lift.

Expected outcome:

  • Hypothesis: A clearer hero will increase conversion rate by at least 15%.
  • Design: Control and one hero-only variant with the same audience and budget logic.
  • Plan: State alpha, power, minimum detectable effect, required exposure, duration, and guardrails.

Using "ad-test-designer". Finished results for a control and one variant with sessions and conversions.

Expected outcome:

  • Effect: Report each conversion rate, relative lift, confidence interval, and p-value.
  • Decision status: Separate statistical and practical flags from the owner-approved action rule.
  • If the rule or owner is absent, return decision: UNDECIDED.

Security Audit

Safe
v9 β€’ 7/26/2026 Open versioned report

All 35 static alerts are false positives caused by Markdown backticks, relative documentation links, metadata, or the decimal alpha notation. The sole documented command runs a fixed local statistical helper and contains no evidence of network access, arbitrary code execution, data exfiltration, or prompt injection. The skill also explicitly treats exported CSV content as untrusted data and requires consent before saving results.

2
Files scanned
167
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: claude View Audit History β†’
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/aaron-he-zhu-ad-test-designer/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/aaron-he-zhu-ad-test-designer/security.svg)](https://skillstore.io/skills/aaron-he-zhu-ad-test-designer?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/aaron-he-zhu-ad-test-designer?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/aaron-he-zhu-ad-test-designer/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/aaron-he-zhu-ad-test-designer.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA Β· BibTeX Β· CFF)

APA citation

aaron-he-zhu. (2026). ad-test-designer security audit report (audit version 9) [Author version 19.0.0]. Skillstore. https://skillstore.io/skills/aaron-he-zhu-ad-test-designer/audits/9

BibTeX citation

@techreport{aaron-he-zhu-aaron-he-zhu-ad-test-designer-2026, author = {aaron-he-zhu}, title = {ad-test-designer security audit report (audit version 9)}, institution = {Skillstore}, year = {2026}, number = {9}, url = {https://skillstore.io/skills/aaron-he-zhu-ad-test-designer/audits/9}, note = {Author version 19.0.0} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "ad-test-designer security audit report (audit version 9)" version: "19.0.0" type: report authors: - name: "aaron-he-zhu" date-released: "2026-07-26" url: "https://skillstore.io/skills/aaron-he-zhu-ad-test-designer/audits/9" identifiers: - type: other value: "skillstore:aaron-he-zhu-ad-test-designer:audit:9" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
41
Architecture
100
Maintainability
87
Content
65
Community
91
Spec Compliance

What You Can Build

Plan a landing-page test

Define a controlled hero or call-to-action test with metrics, sample targets, duration, and guardrails.

Assess creative test results

Read a finished creative experiment export and report effect size, uncertainty, and practical-effect status.

Design an incrementality study

Structure a geo or audience holdout test with a comparable control and a longer measurement window.

Try These Prompts

Start a simple A/B test
Design an A/B test for two landing-page hero variants. Baseline conversion rate is 3%, and I need to detect a 15% lift.
Plan a creative experiment
Create a test matrix for four responsive search ad variants. Include one changed variable per variant, a primary metric, guardrails, sample size, and duration.
Read an exported result
Review my finished experiment results with sessions and conversions by variant. Report effect size, confidence interval, statistical status, and practical-effect status.
Design an incrementality test
Design a geo-holdout incrementality test for a paid campaign. Define the treatment, matched holdout, decision owner, precommitted rule, metrics, and read schedule.

Best Practices

  • Change one variable per variant and retain a control or holdout.
  • Precommit metrics, sample size, alpha, power, and stopping rules before reviewing results.
  • Name the decision owner and action rule before a test starts.

Avoid

  • Do not declare a winner from a p-value alone.
  • Do not stop early after repeated unplanned result checks.
  • Do not combine several creative or landing-page changes in one variant.

Frequently Asked Questions

What data do I need for a test plan?
Provide a baseline conversion or click rate, daily traffic, and the minimum lift worth detecting.
What data do I need for a read-out?
Provide exported exposures and conversions, or equivalent metric data, for each variant.
Can the skill choose a winner?
No. It reports evidence and applies an action only when a decision owner and precommitted rule are provided.
Does it generate ad creative?
No. It designs and interprets experiments. Use a creative-focused skill to produce variants.
Can it run incrementality tests?
It can design geo or audience holdout studies and explain the required comparison structure.
Does it require ad-platform access?
No. It is designed to work with manually exported data from the user.

Developer Details

License

Apache-2.0

Author version

v19.0.0

Skillstore revision

r2

Ref

adcb3549b15782055d0beb6d29f113d20de08f92

Maintenance freshness

7/28/2026

Usage

0 downloads Β· 0 views

File structure

πŸ“ references/

πŸ“„ test-design-guide.md

πŸ“„ SKILL.md