exploring-llm-traces
Originally fromposthog/ai-plugin
Installation
SKILL.md
Exploring LLM traces with MCP tools
PostHog captures LLM/AI agent activity as traces. Each trace is a tree of events representing a single AI interaction — from the top-level agent invocation down to individual LLM API calls.
Available tools
| Tool | Purpose |
|---|---|
posthog:query-llm-traces-list |
Search and list traces (compact — no large content) |
posthog:query-llm-trace |
Get a single trace by ID with full event tree |
posthog:execute-sql |
Ad-hoc SQL for complex trace analysis |
Event hierarchy
See the event reference for the full schema.
$ai_trace (top-level container)
Related skills
More from posthog/skills
posthog-debugger
Debug and inspect PostHog implementations on any website. Use this skill when a user wants to understand how PostHog is implemented on a page, troubleshoot tracking issues, verify configuration, check what events are being sent, or audit a PostHog setup. Works with Chrome DevTools MCP and Playwright MCP to inspect live websites.
106integration-nextjs-app-router
PostHog integration for Next.js App Router applications
100instrument-product-analytics
>-
90feature-flags-nextjs
PostHog feature flags for Next.js applications
88instrument-feature-flags
>-
86error-tracking-nextjs
PostHog error tracking for Next.js
85