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.
Install
npx skills add PostHog/ai-plugin --skill analyzing-offline-evaluationsnpx skills add PostHog/ai-plugin --skill analyzing-offline-evaluations -a claude-code -gnpx skills add PostHog/ai-plugin --skill analyzing-offline-evaluations -a codex -ggemini skills install https://github.com/PostHog/ai-plugin.git --path skills/analyzing-offline-evaluationsgh skill install PostHog/ai-plugin analyzing-offline-evaluationsgit clone --depth 1 https://github.com/PostHog/ai-plugin /tmp/PostHog__ai-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/PostHog__ai-plugin/skills/analyzing-offline-evaluations ~/.claude/skills/analyzing-offline-evaluations # Claude Code
cp -R /tmp/PostHog__ai-plugin/skills/analyzing-offline-evaluations ~/.agents/skills/analyzing-offline-evaluations # Codex, Cursor, Gemini CLI, Copilot, OpenCode