PostHog/posthog agent skills, page 4

Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform.

PostHog/posthog

Inspect and compare offline AI evaluation experiments, diagnose case-level regressions, and follow scorer history across application, model, or prompt changes.

PostHog/posthog

Split a completed PostHog task run into activity records — what the agent tried, whether it worked, what blocked it — and record each one through the reportactivity tool.

PostHog/posthog

Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations.

PostHog/posthog

Creates and launches PostHog surveys through MCP, including NPS/CSAT popovers, hosted feedback forms, and headless surveys.

PostHog/posthog

Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded…

PostHog/posthog

Guides PostHog engineers through dashboard platform and scene changes.

PostHog/posthog

Create and manage scheduled PostHog subscriptions for insight snapshots, dashboard snapshots, and AI prompt reports.

PostHog/posthog

Migrates an LLM caller from services/llm-gateway to PostHog/ai-gateway.

PostHog/posthog

Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an external dbt project.

PostHog/posthog

Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.

PostHog/posthog

Build reusable dimension / lookup tables for a star schema — country/region, timezone, currency, date, plan/product, and other descriptive attributes — on either PostHog data-warehouse views (HogQL)…

PostHog/posthog

Build reusable product-usage and engagement models — retention, stickiness, and lifecycle — on either PostHog data-warehouse views (HogQL) or an external dbt project.

PostHog/posthog

Shared foundations for building reusable data models in PostHog, on either of two stacks: PostHog-native data-warehouse views / materialized views (HogQL, via the view- MCP tools), or an external…

PostHog/posthog

Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production.

PostHog/posthog

Signals scout that watches the project's most-viewed dashboards and insights for anomalies — bursts, drops, flat-lines, and trend breaks — against each insight's own seasonality-matched baseline.

PostHog/posthog

Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two…

PostHog/posthog

Shapes a PR body into something a reviewer understands at a glance.

PostHog/posthog

Write English that a reader cannot misread: one meaning per word, active voice, simple tenses, one idea per sentence, short sentences.

PostHog/posthog

Structure and abstraction rules for PostHog UI code — any React component or frontend file under frontend/src/ or products//frontend/.

PostHog/posthog

Add a new warehouse-backed source to the PostHog Desktop Self-driving Inbox (the feature that ships GitHub, Linear, Zendesk, pganalyze, Jira).

PostHog/posthog

A skill your agent uses when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under .github/ — new CI jobs, triggers, matrices, checkout/clone tuning, action…

PostHog/posthog

Investigate AI observability evaluations — hog (deterministic code-based), llmjudge (LLM-prompt-based), and sentiment (user-message sentiment).

PostHog/posthog

Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed.

PostHog/posthog

Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo.

PostHog/posthog

Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends.

PostHog/posthog

Plan and execute product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture.

PostHog/posthog

Provisions a Replay Vision scanner scoped to one experiment's exposed sessions: sets experimenttargeting so the API derives the person-scoped exposure filter server-side, templates a prompt that…

PostHog/posthog

Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks.

PostHog/posthog

Guidance for adding an API scope object to posthog/scopes.py and making it work for personal API keys, OAuth tokens and MCP clients.

PostHog/posthog

Authenticate a new or changed service to ClickHouse with the rotating ch-podauth ServiceAccount token instead of a static password.

PostHog/posthog

Write, edit, and adapt PostHog Signals scouts: scheduled agents that scan a project and report findings.

PostHog/posthog

Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP.

PostHog/posthog

Explains what a member or a role can do in a PostHog project, using the access control MCP tools.

PostHog/posthog

Synthesizes recent organizational activity into a durable context wiki.

PostHog/posthog

Copy a PostHog endpoint (a saved HogQL/insight query exposed as an API route) to another project in the same organization, or duplicate it under a new name in the same project.

PostHog/posthog

Finds out why a data quality check failed or errored, looks at the rows it matched, and recommends the fix.

PostHog/posthog

Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the @posthog/mcp and posthog.mcp SDKs plus the mcpanalytics product).

PostHog/posthog

Guides PostHog engineers through subscription product changes.

PostHog/posthog

Runs diagnostics and a health check on one PostHog experiment: its setup, exposures, results and changes during the run.

PostHog/posthog

Keep heavy imports off the django.setup() path that every process (web, celery, temporal, migrate, shell, CI) pays for.

PostHog/posthog

Finds and ranks callers that could move from services/llm-gateway to PostHog/ai-gateway.

PostHog/posthog

A skill your agent uses when deciding whether an endpoint, settings section, or UI flow should require recent authentication (re-auth), when adding TimeSensitiveActionPermission or its exemptions…

PostHog/posthog

Investigate logs in a PostHog project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream is saying.

PostHog/posthog

Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, read and patch its code, start and stop its sandbox, poll status, list…

PostHog/posthog

Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production.

PostHog/posthog

Workflow for optimizing ClickHouse and HogQL queries. An agent skill from PostHog/posthog.

PostHog/posthog

Scopes work to the desktop app at products/desktop — a nested standalone pnpm/turbo/Biome workspace imported from the now-archived PostHog/code repo, with posthog/posthog the only source of truth…

PostHog/posthog