Diagnose why a PostHog endpoint is slow or expensive and propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rewrite the query. Use when the user says "this endpoint is slow", "my endpoint times out", "we're hitting the cost cap on this one", or asks "should I materialise this?". Focuses on a single named endpoint, not a project-wide audit.
Install
npx skills add PostHog/ai-plugin --skill diagnosing-endpoint-performancenpx skills add PostHog/ai-plugin --skill diagnosing-endpoint-performance -a claude-code -gnpx skills add PostHog/ai-plugin --skill diagnosing-endpoint-performance -a codex -ggemini skills install https://github.com/PostHog/ai-plugin.git --path skills/diagnosing-endpoint-performancegh skill install PostHog/ai-plugin diagnosing-endpoint-performancegit 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-endpoint-performance ~/.claude/skills/diagnosing-endpoint-performance # Claude Code
cp -R /tmp/PostHog__ai-plugin/skills/diagnosing-endpoint-performance ~/.agents/skills/diagnosing-endpoint-performance # Codex, Cursor, Gemini CLI, Copilot, OpenCode