Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query individual results, and set up scheduled reports on an evaluation.
安装
npx skills add PostHog/ai-plugin --skill exploring-llm-evaluationsnpx skills add PostHog/ai-plugin --skill exploring-llm-evaluations -a claude-code -gnpx skills add PostHog/ai-plugin --skill exploring-llm-evaluations -a codex -ggemini skills install https://github.com/PostHog/ai-plugin.git --path skills/exploring-llm-evaluationsgh skill install PostHog/ai-plugin exploring-llm-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/exploring-llm-evaluations ~/.claude/skills/exploring-llm-evaluations # Claude Code
cp -R /tmp/PostHog__ai-plugin/skills/exploring-llm-evaluations ~/.agents/skills/exploring-llm-evaluations # Codex, Cursor, Gemini CLI, Copilot, OpenCode