ab-test-setup
ab-test-setup is an Experimentation & statistics skill for AI agents, published by sickn33 in the agentic-awesome-skills repository on GitHub. Skillspace rates ab-test-setup D (64/100) and it passed the safety scan; a judge model has also reviewed it.
Use when designing an A/B or split test: define the hypothesis, control and variants, estimate sample size, verify tracking, and predeclare metrics and stopping rules.
- Grade
- D
- Quality
- 64 / 100
- Safety
- Passed
- GitHub stars
- 46,357
Placed #1 of 4 when judged against its near-duplicates in Experimentation & statistics.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 93 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #1 of 4 when judged against its near-duplicates in Experimentation & statistics.
- Trigger
80 80 - Instructions
92 92 - Specificity
88 88 - Safety
88 88 - Disclosure
72 72 - Maintenance
55 55
The only variant with real statistical guardrails — a hard hypothesis-lock gate, a five-point tracking-verification checklist (event firing, de-dup, sample-ratio mismatch), and an explicit rule against overriding guardrail failures.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.