posthog/ai-plugin · Official
analyzing-offline-evaluations
Inspect and compare offline AI evaluation experiments, diagnose case-level regressions, and follow scorer history across application, model, or prompt changes. Use when a user asks whether an offline run improved, why a case failed, how scores changed between runs, or how to publish externally computed offline results. Covers immutable scorer versions, comparable dataset cohorts, incomplete coverage, and selective payload reads.
Installation
npx skills add https://github.com/posthog/ai-plugin
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Also in this package
Other skills from posthog/ai-plugin · top by installs.
npx skills add posthog/ai-plugin
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
main