exploring-llm-traces
exploring-llm-traces is the official agent skill of PostHog published by posthog, listed under analytics & experiments. It lives in the PostHog/skills repository, which has 75 GitHub stars and is licensed under MIT; we last read it on 2026-09-25.
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Users can paste a trace or session URL and ask to debug various aspects such as agent tool usage, context handling, LLM decisions, and token costs.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads PostHog/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add PostHog/skills
What it connects to
Unverified means a mention in the skill’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.
Maintenance
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.
exploring-llm-traces compared with similar skills
| Skill | Publisher | What it does | Repo stars | Last update |
|---|---|---|---|---|
| exploring-llm-traces (this page) | posthog | Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session… | 75 | 2026-10-25 |
| account-handover(same repository) | posthog | Draft structured handover notes for transitioning a PostHog account from one TAM or CSM to another. Use this… | 75 | 2026-10-25 |
| adding-warehouse-person-properties(same repository) | posthog | Sync columns from a synced data warehouse table onto PostHog person or group properties, so warehouse data be… | 75 | 2026-10-25 |
| analyzing-experiment-session-replays(same repository) | posthog | Analyze session replay patterns across experiment variants to understand user behavior differences. Use when… | 75 | 2026-10-25 |
| analyzing-task-runs(same repository) | posthog | Split a completed PostHog task run into activity records — what the agent tried, whether it worked, what bloc… | 75 | 2026-10-25 |
| assessing-heatmaps(same repository) | posthog | Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scro… | 75 | 2026-10-25 |
| auditing-endpoints(same repository) | posthog | Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised ver… | 75 | 2026-10-25 |
Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.
Common questions about exploring-llm-traces
- What does exploring-llm-traces do?
- Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Users can paste a trace or session URL and ask to debug various aspects such as agent tool usage, context handling, LLM decisions, and token costs.
- How do I install exploring-llm-traces?
- Run npx skills add PostHog/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes exploring-llm-traces?
- posthog. It is named as the official skill of PostHog.
- Is exploring-llm-traces maintained, and what licence does it use?
- Its repository has 75 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-25. The repository declares the MIT licence.
More agent skills for analytics & experiments
- youtube-thumbnail-designby 101-skills
- incremental-implementationby addyosmani
- agent-observability-replay-traceby datadog-labs
- dd-browser-sdkby datadog-labs
- dd-instrument-rumby datadog-labs
- omni-ai-evalby exploreomni