Runs diagnostics and a health check on one PostHog experiment: its setup, exposures, results and changes during the run. Covers 0 exposures, sample ratio mismatch, lost or uneven exposures, users in multiple variants, identity faults, who the experiment counts, significance traps (peeking, A/A, 'target reached', Bayesian vs Frequentist, sequential, CUPED), mid-run edits, pause and freeze, and…
Install
npx skills add PostHog/ai-plugin --skill diagnosing-experiment-healthnpx skills add PostHog/ai-plugin --skill diagnosing-experiment-health -a claude-code -gnpx skills add PostHog/ai-plugin --skill diagnosing-experiment-health -a codex -ggemini skills install https://github.com/PostHog/ai-plugin.git --path skills/diagnosing-experiment-healthgh skill install PostHog/ai-plugin diagnosing-experiment-healthgit 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/diagnosing-experiment-health ~/.claude/skills/diagnosing-experiment-health # Claude Code
cp -R /tmp/PostHog__ai-plugin/skills/diagnosing-experiment-health ~/.agents/skills/diagnosing-experiment-health # Codex, Cursor, Gemini CLI, Copilot, OpenCode