PostHogProduct analytics platform, 40k+ GitHub stars345 installs on skills.shExploring LLM Traces
Debug and inspect LLM/AI agent traces using PostHog's MCP tools.
3 static scans, 0 counted findings.
Edge checks it again each time your agent loads it.
What it does
- 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.
Why PostHog
Open-source product analytics company. Each fact links its public source.
- Main repo
The posthog repo has 40k+ GitHub stars.
GitHub repo - Docs site repo
The posthog.com repo has 1.1k+ GitHub stars.
GitHub repo
How it works
- 1Copy
Try for free gives you one prompt.
- 2Paste
Paste it into Claude Code, Codex or Cursor.
- 3Ask
Ask for the outcome. Your agent loads Exploring LLM Traces.
3 static scans, 0 counted findings.
Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.
State definitionsSelect the Files tab to load SKILL.md.
Skill details
Security scansReviewed
3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.
Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .
Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 1.
Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .
- Edge static checks
- Pass · 0 counted findings · 2026-09-27
- Cisco skill-scanner
- Pass · 0 counted findings · 2026-09-27
- Semgrep Edge rules
- Pass · 0 counted findings · 2026-09-27
Creator, source & licenceposthog
From the posthog public repository. Edge did not write or edit this skill.
- Repository
- posthog/skills
- Skill file
- View source at revision
- Revision
- 835ceac8ec56af5ca9af647c815abc2fa6f9b330
- Package hash
- sha256:89e4e524a4dec451dc4273c0918d1a72e8af3419c022f5645c23b65347ac62c9
- Licence
- MIT
- Description
- 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.
Quoted from the skill’s own description
Read skill files10 files
10 files, 51.8 KB at revision 835ceac8ec56.
Questions about Exploring LLM Traces
What does Exploring LLM Traces do?
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Published by PostHog (posthog/skills).
Is Exploring LLM Traces safe to use?
Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.
How do I use Exploring LLM Traces in Claude Code, Codex or Cursor?
Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.