experiments
experiments is an Experimentation & statistics skill for AI agents, published by growthbook in the growthbook repository on GitHub. Skillspace rates experiments C (74/100) and it passed the safety scan; a judge model has also reviewed it.
Read and modify experiments (A/B tests), snapshots, and results. Use when the user asks about experiments, hypotheses, variations, goal/guardrail metrics, launching or stopping tests, or page context under /experiment/*.
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 7,992
Placed #5 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
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Vendor-specific: built around one product. Uses GrowthBook's public experiments REST API; useful to any GrowthBook user
Judge review
Placed #5 of 6 in the judged category final for Experimentation & statistics.
- Trigger
82 82 - Instructions
78 78 - Specificity
80 80 - Safety
88 88 - Disclosure
90 90 - Maintenance
65 65
A genuinely lean router that gates mutating API calls and defaults to Bayesian chance-to-win reporting over p-values, but it shows little beyond dispatch logic since the real work lives in un-shown leaf skills.
Not checked yet
- No blind task eval yet
- 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.