ab-testing
ab-testing is an Experimentation & statistics skill for AI agents, published by sickn33 in the agentic-awesome-skills repository on GitHub. Skillspace rates ab-testing C (77/100) and it passed the safety scan; a judge model has also reviewed it.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
- Grade
- C
- Quality
- 77 / 100
- Safety
- Passed
- GitHub stars
- 46,357
Placed #6 of 6 in the judged category final for 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
- 94 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #6 of 6 in the judged category final for Experimentation & statistics.
- Trigger
55 55 - Instructions
78 78 - Specificity
75 75 - Safety
80 80 - Disclosure
70 70 - Maintenance
45 45
Generic A/B-testing textbook content with none of the contract structure, owner-approval gating, or data-provenance discipline the domain-specific designer skills in this group show.
Same generic body as the other two ab-testing variants but with the shortest, least specific trigger description of the four.
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.