PostHogOfficial·150 Agent Skills Included

posthog-foss

Operate and debug PostHog product analytics with AI agents

Guides AI agents through real PostHog workflows: triaging error issues, cleaning up feature flags, exporting data, investigating APM traces, and analyzing MCP tool usage. Eliminates manual dashboard digging, unsafe flag deletions, and guesswork when events or errors look wrong. Each skill encodes verified queries, safety checks, and step-by-step procedures so agents complete analytics tasks correctly the first time.

713|118

↗

npx skills add PostHog/posthog-foss --all -g -y

Available:

Gives the AI agent the PostHog monorepo's operating rules — how to run tests and builds, navigate the codebase, and follow commit and PR conventions when working in this repository.

All Skills in This Repository (150)

Pure Emerald Level Indicators

📦 In Repo

PostHog

query-examples

Provide HogQL query examples and schema references for PostHog data analysis.

implementing-mcp-tools

Expose PostHog API endpoints as MCP tools via YAML configurations and TypeScript handlers.

django-migrations

Generate and validate Django database migrations with conflict resolution.

react-doctor

Diagnose React codebase health issues and generate a 0-100 score with diagnostics.

hogli

Run, build, test, and lint the PostHog codebase via a unified CLI.

implementing-warehouse-sources

Implement PostHog Data Warehouse import sources with datasets, endpoints, and incremental sync.

ingestion-pipeline-doctor-nodejs

Outline PostHog event ingestion pipeline architecture and diagnostic agent mapping.

writing-skills

Provides a standardized framework for creating AI agent skills in PostHog.

improving-drf-endpoints

Audit Django REST Framework viewsets and serializers for type safety and OpenAPI documentation.

clickhouse-autoresearch-campaign

Runs autonomous ClickHouse query optimization campaigns with baseline capture, correctness checks, and lane-based hypothesis testing.

investigating-metric-anomalies

Diagnoses server metric anomalies by correlating metrics, logs, and traces to root causes.

downloading-batch-export-files

Export PostHog events, persons, sessions, or HogQL query results and download Parquet or JSONLines files.

Official

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install posthog-foss skills?▼

Run `npx skills add PostHog/posthog-foss --all -g -y` in your terminal to install all skills in this suite globally.

What can AI agents do with PostHog skills?▼

Agents can triage error tracking issues, clean up stale feature flags, export event data, investigate APM traces, analyze MCP tool quality, and verify SDK instrumentation on live sites.

How do I clean up stale feature flags safely?▼

The cleaning-up-stale-feature-flags skill finds unused or fully rolled-out flags, generates code cleanup instructions, and only disables flags after your code changes are deployed and approved.

Can AI debug why PostHog events are missing?▼

Yes. The resolving-ingestion-warnings skill diagnoses dropped events, rejected merges, and oversized payloads, while the traffic-sim skills verify your SDK actually fires events on real pages.

Do these skills work with Claude Code and other agents?▼

Yes. All skills follow the standard SKILL.md format and work in Claude Code, Cursor, and any MCP-compatible agent connected to PostHog.