Ads Test skill: what it does and how to install it
Designs and evaluates paid-media experiments with hypotheses, sample-size assumptions, guardrails and clear decision rules.
Summary generated from the skill's documentation.
Install
$ npx skills add AgriciDaniel/claude-ads --skill ads-testRun it in a terminal. If your agent is already running, start a new session so it picks the skill up.
About this skill
What it does. Defines the decision, hypothesis, treatment, control, randomisation unit, metrics and stopping rule for a paid-ad experiment. It checks platform constraints and measurement quality, calculates sample and duration assumptions, and returns setup or readout results as versioned JSON with a plain-language decision.
When to use it. For A/B tests, split tests, experiment design, statistical significance, sample sizing, test duration and paid-media readouts. It avoids repeated peeking, treating underpowered noise as a win, and generalising beyond the tested population.
History
Repo stars
9.9k+192 since 5 Oct 2026
Stars are counted for the whole repository, which holds 23 skills.
Show as a table
| Date | Repo stars |
|---|---|
| 12 Oct 2026 | 9,914 |
| 11 Oct 2026 | 9,873 |
| 10 Oct 2026 | 9,857 |
| 9 Oct 2026 | 9,834 |
| 8 Oct 2026 | 9,804 |
| 7 Oct 2026 | 9,770 |
| 6 Oct 2026 | 9,744 |
| 5 Oct 2026 | 9,722 |
Installs
3.5k
Tracking since . A chart appears once there are 7 days of data.
Installs via skills.sh
Similar skills
- Ad Creative Test PlanDesigns pre-launch paid-media creative test plans with hypotheses, budgeted test cells, sample sizing and pre-registered kill or scale rules.
- Content Experimentation Best PracticesGuides content experiments and A/B tests: design, hypotheses, metrics, sample size and analysis pitfalls.
- Ad Spend GuardrailsSets paid-media CAC, ROAS, cash and kill-switch guardrails from contribution margin, payback and runway, with owners, overrides and restart rules.