investigating-logs — Claude Code skill for log analysis
The investigating-logs Claude Code skill investigates logs in a PostHog project, checks service health and traces error spikes. It runs for deploy checks, incident triage, change analysis, or a search around one trace or run.
no license 188 installs ★ 101 updated 2026-11-16
npx skills add PostHog/ai-plugin --skill investigating-logs -a claude-codeWhat investigating-logs does
The skill examines PostHog project logs to help identify service health, changes in message patterns, and reasons for error spikes. It starts with summaries and comparisons across time windows; raw log rows come later. Summaries first.
PostHog tools group entries by service, severity, and pattern, track counts over time, and retrieve context around a log line, trace, or run. A post-change check compares windows on either side of the change; it needs a time boundary to make that comparison meaningful. The skill can also locate logs tied to an alert or user complaint.
What it helps with
- check whether a service still emits logs after a deployment
- find new error patterns after a configuration change
- break an error spike down by time window
- inspect log context around a trace or run
- identify which service is involved in an incident
Example prompts for the agent
- Check the PostHog project logs after the latest deployment and compare them with the earlier period.
- Why did the error count rise? Investigate the spike in the logs.
- Find the logs around this trace and explain what happened.
How to install investigating-logs
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill investigating-logs -a claude-code2Manually: put the files in place
~/.claude/skills/investigating-logs/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/investigating-logs/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill investigating-logs -a codex2Manually: put the files in place
.agents/skills/investigating-logs/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill investigating-logs -a cursor2Manually: put the files in place
.cursor/skills/investigating-logs/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PostHog/ai-plugin skills/investigating-logs2Manually: put the files in place
.github/skills/investigating-logs/SKILL.md1Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill investigating-logs -a gemini-cli2Platform CLI
gemini skills install https://github.com/PostHog/ai-plugin --path skills/investigating-logsManually: put the files in place
.devin/skills/investigating-logs/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PostHog/ai-plugin --skill investigating-logs -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about investigating-logs
How do I install investigating-logs in Claude Code?
Run npx skills add PostHog/ai-plugin --skill investigating-logs -a claude-code. The skill file is placed at ~/.claude/skills/investigating-logs/SKILL.md.
What does investigating-logs do?
It investigates logs in a PostHog project, checking service health, comparing message patterns across time windows, and retrieving context around a trace or run. Raw rows are used for deeper investigation.
How does investigating-logs check whether a deploy caused problems?
It compares error patterns and log volume from before and after the change, then drills into suspicious rows. The comparison needs the change time as a boundary.