@skills · Owner

Agent skills by posthog

375 skills indexed from github.com/posthog. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• .agents · Collection · 37,539 stars
• .claude · Collection · 37,539 stars
• adapters · Collection · 37,539 stars
• adding-inbox-sources · Skill · 37,539 stars

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

• adding-ingestion-warnings · Skill · 37,539 stars

  How to add a new ingestion warning type to the event ingestion pipeline. Use when emitting a new warning from nodejs ingestion code (emitIngestionWarning,

• adding-mcp-store-servers · Skill · 37,539 stars

  Add a third-party MCP server (Linear, Notion, GitHub, ...) to the PostHog MCP store catalog. Use when asked to "add X to the MCP store", expand the MCP ser

• adding-personhog-rpc · Skill · 37,539 stars

  Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js c

• adding-product-alerting · Skill · 37,539 stars

  Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines, Aler

• adding-project-secret-api-key-auth · Skill · 37,539 stars

  How to gate a PostHog API endpoint with project secret API key (PSAK) auth — a project-scoped, user-less service credential. Use when adding PSAK support t

• adopting-generated-api-types · Skill · 37,539 stars

  Use when migrating frontend code from manual API client calls (`api.get`, `api.create`, `api.surveys.get`, `api.dashboards.list`, `new ApiRequest()`) and h

• agent · Collection · 37,539 stars
• ai_observability · Collection · 37,539 stars
• analyzing-expensive-users · Skill · 37,539 stars

  Analyze the most expensive users in AI observability and explain why they cost so much. Use when the user asks about top spenders, expensive users, per-use

• analyzing-experiment-query-performance · Skill · 37,539 stars

  Pull and interpret production experiment query-performance data from the staff-only `/api/debug_ch_queries` endpoints backing the `/experiments/staff` scen

• analyzing-experiment-session-replays · Skill · 37,539 stars

  Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with

• analyzing-insights-across-teams · Skill · 37,539 stars

  Analyze PostHog insights, dashboards, or teams beyond the current project by querying the prod Postgres replicas synced into the dogfood data warehouse (US

• assessing-heatmaps · Skill · 37,539 stars

  Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot element

• auditing-endpoints · Skill · 37,539 stars

  Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints

• auditing-experiments-flags · Skill · 37,539 stars

  Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-che

• auditing-llm-gateway-parity · Skill · 37,539 stars

  Audits services/llm-gateway against PostHog/ai-gateway and updates services/llm-gateway/PARITY.md from current implementation evidence. Use when either gat

• auditing-warehouse-source-coverage · Skill · 37,539 stars

  Audit already-implemented Data warehouse import sources for endpoints, schemas, and tables the vendor's API offers but we never wired up. Use when asked wh

• auditing-warehouse-source-health · Skill · 37,539 stars

  Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channe

• auditing-warehouse-view-health · Skill · 37,539 stars

  Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views

• authoring-ci-workflows · Skill · 37,539 stars

  Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under `.github/` — new CI jobs, triggers, matrices, checkout/c

• authoring-error-tracking-alerts · Skill · 37,539 stars

  Author error tracking alerts that fire when an issue is created, reopened, or starts spiking. Use when the user asks to set up error notifications, route e

• authoring-log-alerts · Skill · 37,539 stars

  Author useful, low-noise log alerts on services in a PostHog project. Use when the user asks to set up alerts for their logs, suggest alerts they should ad

• authoring-scouts · Skill · 37,539 stars

  How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use to customize

• autoresolving-pr-conflicts · Skill · 37,539 stars

  Operating procedure for the conflict-autoresolver agent: sweep open PostHog/posthog PRs that conflict with master, resolve the trivial conflicts (generated

• batch_exports · Collection · 37,539 stars
• building-a-dashboard · Skill · 37,539 stars

  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

• building-canvases · Skill · 37,539 stars

  Create or edit a PostHog freeform canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in PostHog

• building-html-canvases · Skill · 37,539 stars

  Author a PostHog canvas with semantic HTML, CSS, and direct browser APIs — documents, articles, generative graphics, 2D canvas and WebGL experiences, and f

• building-product-empty-states · Skill · 37,539 stars

  Guide for adding a product setup empty state — the skippable first-run screen a product scene shows until real data arrives, built on the shared ProductEmp

• building-react-quill-canvases · Skill · 37,539 stars

  Author the React + Quill implementation of a PostHog canvas: the single-component contract, the allowed imports, Quill (PostHog's design system) component

• building-workflows · Skill · 37,539 stars

  Build, edit, test, enable, and monitor PostHog workflows over MCP. Author the action/edge graph so it runs and opens cleanly in the visual editor, then cha

• canvas · Collection · 37,539 stars
• check-posthog-loading · Skill · 37,539 stars

  Inspect how the PostHog JavaScript SDK is loaded across a list of URLs. Use to confirm consistent installation across pages, find pages missing the snippet

• checking-deploy-timing · Skill · 37,539 stars

  Determine when a PostHog code change reached a given environment by reading the hidden GIT deploy annotations in the project and correlating them with the

• choosing-trend-or-slope-view · Skill · 37,539 stars

  Clarify how to visualize change over a time range before building a trend. Use whenever the user asks how much something changed, grew, dropped, improved,

• cleaning-up-stale-feature-flags · Skill · 37,539 stars

  Identify stale feature flags in a PostHog project and clean up the code that checks them. Use when the user wants to find, audit, or remove unused, fully r

• clickhouse-autoresearch-campaign · Skill · 37,539 stars

  Run a ClickHouse query optimization campaign on one git branch using pi-autoresearch, dynamic lanes and hypotheses, baseline result capture, correctness ch

• clickhouse-migrations · Skill · 37,539 stars

  ClickHouse migration patterns and rules. Use when creating or modifying ClickHouse migrations.

• configuring-experiment-analytics · Skill · 37,539 stars

  Configures the analytics side of a PostHog experiment — exposure criteria (server-resolved default exposure event vs custom exposure events), primary and s

• configuring-experiment-rollout · Skill · 37,539 stars

  Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many u

• consuming-endpoints-from-client-code · Skill · 37,539 stars

  Wire a PostHog endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts

• conversations · Collection · 37,539 stars
• copying-endpoints-across-projects · Skill · 37,539 stars

  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

• copying-flags-across-projects · Skill · 37,539 stars

  Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote

• creating-ai-subscription · Skill · 37,539 stars

  Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email or Slac

• creating-an-endpoint · Skill · 37,539 stars

  Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name

• creating-experiments · Skill · 37,539 stars

  Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisi

• creating-online-evaluations · Skill · 37,539 stars

  Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evalu

• creating-replay-vision-scanners · Skill · 37,539 stars

  Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the Rec

• dashboards · Collection · 37,539 stars
• data_catalog · Collection · 37,539 stars
• data_modeling · Collection · 37,539 stars
• data_warehouse · Collection · 37,539 stars
• debugging-ci-failures · Skill · 37,539 stars

  Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?"

• debugging-local-replay · Skill · 37,539 stars

  Debugs why session recordings aren't appearing in the local dev environment. Use when a developer reports that local replay ingestion isn't working, record

• debugging-local-task-agent-runs · Skill · 37,539 stars

  Debug the output of local PostHog task runs — the wizard cloud-run path that executes inside a Docker sandbox under the local Temporal `process-task` workf

• debugging-mcp-analytics · Skill · 37,539 stars

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

• debugging-signals-pipeline · Skill · 37,539 stars

  Debug the signals pipeline locally end-to-end. Covers emitting test signals from fixtures, monitoring Temporal workflows via the REST API, reading sandbox

• debugging-surveys · Skill · 37,539 stars

  Debug, support, and build PostHog Surveys across the backend and all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native). Use whenever a Survey

• depot-container-builds · Skill · 37,539 stars

  Configures and runs Depot remote container builds using `depot build` and `depot bake`. Use when building Docker images, creating Dockerfiles with Depot, p

• depot-github-runners · Skill · 37,539 stars

  Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners. Use when setting up or migrating GitHub Actions workflo

• designing-email-templates · Skill · 37,539 stars

  Author, save, and edit email templates in the PostHog workflows library — compose email design JSON with Liquid personalization and create and round-trip-e

• desktop · Collection · 37,539 stars
• diagnosing-ci-and-merge-bottlenecks · Skill · 37,539 stars

  Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status), workflo

• diagnosing-endpoint-performance · Skill · 37,539 stars

  Diagnose why a PostHog endpoint is slow or expensive and propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rew

• diagnosing-experiment-results · Skill · 37,539 stars

  Diagnoses bias, anomalies, and strange results on a PostHog experiment. Covers 0-exposure experiments, sample ratio mismatch, identity fragmentation, multi

• diagnosing-failed-warehouse-syncs · Skill · 37,539 stars

  Diagnose why a data warehouse sync is failing and recommend the right recovery action. Use when the user asks "why isn't my Stripe/Postgres/Hubspot sync wo

• diagnosing-missing-recordings · Skill · 37,539 stars

  Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wan

• diagnosing-sdk-health · Skill · 37,539 stars

  Diagnoses the health of a project's PostHog SDK integrations — which SDKs are out of date and how to fix them. Use when a user asks about PostHog SDK versi

• diagnosing-stacktrace-symbolication · Skill · 37,539 stars

  Help users debug PostHog Error Tracking stack-trace symbolication for any supported platform — JavaScript/TypeScript web, React Native (Hermes), Android (P

• django-migrations · Skill · 37,539 stars

  Django migration patterns and safety workflow for PostHog. Use when creating, adjusting, or reviewing Django/Postgres migrations, including non-blocking in

• django-startup-time · Skill · 37,539 stars

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

• documenting-warehouse-sources · Skill · 37,539 stars

  Write or update the user-facing posthog.com documentation for a PostHog Data warehouse import source. Use when adding a new source doc, fixing an inconsist

• downloading-batch-export-files · Skill · 37,539 stars

  Export PostHog events, persons, sessions, or the results of a HogQL query on demand and download the resulting files. Use when the user asks to download/ex

• endpoints · Collection · 37,539 stars
• engineering_analytics · Collection · 37,539 stars
• error_tracking · Collection · 37,539 stars
• establishing-code-ownership · Skill · 37,539 stars

  Determine which PostHog team owns a file, directory, or code path, or enumerate all code a team owns (via distributed `owners.yaml`, `products/*/product.ya

• experiments · Collection · 37,539 stars
• exploring-ai-failures · Skill · 37,539 stars

  Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand

• exploring-apm-traces · Skill · 37,539 stars

  Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTT

• exploring-autocapture-events · Skill · 37,539 stars

  Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes), eva

• exploring-endpoint-execution-logs · Skill · 37,539 stars

  Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint i

• exploring-live-traffic · Skill · 37,539 stars

  Inspects PostHog Web analytics Live tab data — current users online, last-30-minutes pageviews, top pages, referrers, devices, browsers, countries, bot tra

• exploring-llm-clusters · Skill · 37,539 stars

  Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into

• exploring-llm-costs · Skill · 37,539 stars

  Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost

• exploring-llm-evaluations · Skill · 37,539 stars

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

• exploring-llm-traces · Skill · 37,539 stars

  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

• exploring-mcp-intent-clusters · Skill · 37,539 stars

  Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-cent

• exploring-mcp-sessions · Skill · 37,539 stars

  Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong.

• exploring-mcp-tool-quality · Skill · 37,539 stars

  Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP too

• exploring-mcp-tool-usage · Skill · 37,539 stars

  Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks

• exploring-replay-vision-observations · Skill · 37,539 stars

  Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, dril

• exploring-scouts · Skill · 37,539 stars

  How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a use

• extending-personhog-test-harness · Skill · 37,539 stars

  When and how to add scenarios, chaos events, and invariants to the personhog e2e test harness (rust/personhog-test-harness). Use after fixing a bug or regr

• extensions · Collection · 37,539 stars
• feature_flags · Collection · 37,539 stars
• feature-usage-feed · Skill · 37,539 stars

  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.

• filtering-bot-traffic · Skill · 37,539 stars

  Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification surface (the isLikely

• finding-deleted-feature-flags · Skill · 37,539 stars

  Find feature flags that were soft-deleted in the active project within a recent time window. Use when the user asks "what flags were deleted in the last N

• finding-experiments · Skill · 37,539 stars

  Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disa

• finding-llm-gateway-migration-candidates · Skill · 37,539 stars

  Finds and ranks callers that could move from services/llm-gateway to PostHog/ai-gateway. Use when asked what to migrate next, to find low-risk gateway migr

• finding-replay-for-issue · Skill · 37,539 stars

  Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay

• finding-sessions-to-watch · Skill · 37,539 stars

  Guides a user from "I want to watch recordings but don't know which ones" to a short, high-signal list of sessions worth watching. Use when the user asks w

• fixing-flaky-tests · Skill · 37,539 stars

  Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI b

• formatting-insight-axes · Skill · 37,539 stars

  Pick the right y-axis unit when creating or updating an insight via `posthog:insight-create` or `posthog:insight-update` — both TrendsQuery (`trendsFilter.

• gating-production-deploys · Skill · 37,539 stars

  Use when adding or editing a GitHub Actions workflow that pushes a container image to a registry (ECR/ghcr/Docker Hub via build-push-action) or dispatches

• generating-clickhouse-query-performance-reports · Skill · 37,539 stars

  Produce and structure slow-query performance reports for PostHog's production ClickHouse (US and EU). Use when asked for a slow query report, query perform

• grouping-noisy-errors · Skill · 37,539 stars

  Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints. Use when the user asks "why do I have so ma

• growth · Collection · 37,539 stars
• harness · Collection · 37,539 stars
• hogli · Skill · 37,539 stars

  PostHog developer CLI and repo tooling reference. Use when the user mentions hogli, asks about repo CLI tools, bin scripts, Makefiles, how to run/build/tes

• implementing-mcp-tools · Skill · 37,539 stars

  Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML c

• implementing-mcp-ui-apps · Skill · 37,539 stars

  Guide for adding MCP UI apps — interactive visualizations that render tool results in MCP clients like Claude Desktop. Use when adding a new detail or list

• implementing-warehouse-sources · Skill · 37,539 stars

  Implement and extend PostHog Data warehouse import sources. Use when adding a new source under products/warehouse_sources/backend/temporal/data_imports/sou

• improving-drf-endpoints · Skill · 37,539 stars

  Use when editing, reviewing, or auditing DRF viewsets and serializers in PostHog. Triggers on files in posthog/api/, products/*/backend/api/, products/*/ba

• improving-mcp-tools · Skill · 37,539 stars

  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 prob

• inbox-exploration · Skill · 37,539 stars

  Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends. Use when the user asks "wha

• ingestion · Collection · 37,539 stars
• ingestion-pipeline-doctor-nodejs · Skill · 37,539 stars

  Ingestion pipeline architecture overview and convention reference. Use when you need a quick orientation to the pipeline framework or want to know which do

• instrumenting-first-party-metrics · Skill · 37,539 stars

  How to instrument PostHog's own Metrics product from PostHog-owned code — record counters, gauges, and histograms that land in posthog.metrics, the same wa

• investigate-metric · Skill · 37,539 stars

  Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations que

• investigating-ci-failures · Skill · 37,539 stars

  Investigates a specific CI failure to a verdict: whose fault, which commit, who wrote it, and whether it's fixed. Use for "who broke master", "why did this

• investigating-error-issue · Skill · 37,539 stars

  Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and w

• investigating-logs · Skill · 37,539 stars

  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 stre

• investigating-metric-anomalies · Skill · 37,539 stars

  Investigates server/infrastructure metric anomalies in PostHog Metrics — from "this metric is rising/dropping/spiking" or a fired alert to a probable cause

• investigating-replay · Skill · 37,539 stars

  Investigates a session recording by gathering metadata, person profile, same-session events, and linked error tracking issues in one pass. Use when a user

• isolating-product-facade-contracts · Skill · 37,539 stars

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

• logs · Collection · 37,539 stars
• manage-dashboard-widgets · Skill · 37,539 stars

  Guides PostHog engineers through dashboard widget platform work — ship a new widget_type (WIDGET_REGISTRY, catalog, run_widgets, WidgetCard) or update a sh

• managed_migrations · Collection · 37,539 stars
• managing-endpoint-versions · Skill · 37,539 stars

  Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query

• managing-experiment-lifecycle · Skill · 37,539 stars

  Guides experiment state transitions: launching, pausing, resuming, freezing/unfreezing exposure, ending, shipping variants, archiving, resetting, duplicati

• managing-github-actions-secrets · Skill · 37,539 stars

  Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API

• managing-path-cleaning-rules · Skill · 37,539 stars

  Inspects URL paths and proposes, tests, orders, and applies project-level path cleaning rules so dynamic segments (numeric IDs, UUIDs, slugs, dates) collap

• managing-reminders · Skill · 37,539 stars

  Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource.

• managing-streamlit-apps · Skill · 37,539 stars

  Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, start and stop its sandbox, poll st

• managing-subscriptions · Skill · 37,539 stars

  Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots, optionally with an AI-written summary attac

• mcp · Collection · 37,539 stars
• mcp_analytics · Collection · 37,539 stars
• mcp-servers · Skill · 37,539 stars

  Install, configure, authenticate, and troubleshoot MCP (Model Context Protocol) servers for this agent. Use when the user asks to add/install/remove an MCP

• merging-prs · Skill · 37,539 stars

  Merge a PR into `master` through the Trunk merge queue and babysit it until it lands. Enqueue with a `/trunk merge` comment, then watch `trunk merge status

• metrics · Collection · 37,539 stars
• migrating-llm-gateway-callers · Skill · 37,539 stars

  Migrates an LLM caller from services/llm-gateway to PostHog/ai-gateway. Use when adding a gateway caller, converting an existing Python gateway integration

• modeling-activation-metrics · Skill · 37,539 stars

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

• modeling-conversion-metrics · Skill · 37,539 stars

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

• modeling-dimension-tables · Skill · 37,539 stars

  Build reusable dimension / lookup tables for a star schema — country/region, timezone, currency, date, plan/product, and other descriptive attributes — on

• modeling-product-usage-metrics · Skill · 37,539 stars

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

• modeling-revenue-metrics · Skill · 37,539 stars

  Build reusable revenue models — MRR, ARR, gross revenue, new/expansion/contraction/churn, ARPU, LTV, and per-customer/per-account revenue — on either PostH

• modeling-warehouse-foundations · Skill · 37,539 stars

  Shared foundations for building reusable data models in PostHog, on either of two stacks: PostHog-native data-warehouse views / materialized views (HogQL,

• modifying-taxonomic-filter · Skill · 37,539 stars

  Guides safe changes to the TaxonomicFilter, PostHog's picker for events, actions, properties, cohorts, and more. Use when adding features, fixing bugs, imp

• monitoring-capture-service · Skill · 37,539 stars

  Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production. Use when investigating latency, event loss, Kafka

• monitoring-ingestion-pipeline · Skill · 37,539 stars

  Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production. Use when investigating event lag, drops, pipe

• optimizing-clickhouse-and-hogql-queries · Skill · 37,539 stars

  Workflow for optimizing ClickHouse and HogQL queries. Use when a HogQL query, query runner, insight, or report is too slow; when a hand-written ClickHouse

• packages · Collection · 37,539 stars
• pi_plugin · Collection · 37,539 stars
• planning-voice-agent-user-interviews · Skill · 37,539 stars

  Plan a round of user interviews conducted by PostHog''s AI voice agent (a "robo interviewer") — the automated voice-agent interview product. Captures a Use

• playwright-test · Skill · 37,539 stars

  Write a playwright test, make sure it runs, and is not flaky.

• posthog · Collection · 37,539 stars
• posthog_ai · Collection · 37,539 stars
• posthog-desktop · Skill · 37,539 stars

  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

• product_analytics · Collection · 37,539 stars
• products · Collection · 37,539 stars
• qa-frontend · Skill · 37,539 stars

  Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI

• qa-team · Skill · 37,539 stars

  Multi-agent QA review team for code changes. This skill should be used when the user asks to "review my code", "run QA", "qa-team", "review this branch", "

• query_performance_ai · Collection · 37,539 stars
• query-performance-ai · Collection · 37,539 stars
• querying-canvas-data · Skill · 37,539 stars

  Get PostHog data into a canvas correctly: the host-injected `ph` SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hie

• querying-local-postgres · Skill · 37,539 stars

  Run read-only SQL against the local Postgres app database (SELECT, EXPLAIN, EXPLAIN ANALYZE on SELECT). Default local URL postgres://posthog:posthog@localh

• querying-posthog-data · Skill · 37,539 stars

  Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregatio

• querying-tophog · Skill · 37,539 stars

  Query tophog — the ingestion pipeline's heavy-hitter store in ClickHouse — to identify hot or expensive actors (team_id, distinct_id, session_id, partition

• quill-code · Skill · 37,539 stars

  Edit the @posthog/quill design system locally and consume the change in products/desktop before it is published to npm. Use when changing quill components/

• react-doctor · Skill · 37,539 stars

  Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.

• reminders · Collection · 37,539 stars
• replay · Collection · 37,539 stars
• replay_vision · Collection · 37,539 stars
• resolving-ingestion-warnings · Skill · 37,539 stars

  Diagnoses and resolves PostHog ingestion warnings — problems recorded while ingesting events (dropped events, rejected person merges, oversized payloads, i

• review_hog · Collection · 37,539 stars
• review-hog-authoring · Skill · 37,539 stars

  How to author custom PostHog Review skills: the review perspectives, blind-spot checks, validation criteria, and resolution criteria that drive PostHog Rev

• review-hog-blind-spots-general · Skill · 37,539 stars

  The general blind-spot check for PostHog Review, the final sweep that runs after every enabled review perspective has reviewed a chunk. Hunts for real, hig

• review-hog-perspective-contracts-security · Skill · 37,539 stars

  The Contracts & Security review perspective for PostHog Review. Verifies that changed code is safe and maintains compatibility: API contracts and breaking

• review-hog-perspective-logic-correctness · Skill · 37,539 stars

  The Logic & Correctness review perspective for PostHog Review. Verifies that changed code does what it is supposed to do: business logic, edge cases, data

• review-hog-perspective-performance-reliability · Skill · 37,539 stars

  The Performance & Reliability review perspective for PostHog Review. Verifies that changed code will perform and hold up in production: resource efficiency

• review-hog-validation-criteria · Skill · 37,539 stars

  The validation criteria for PostHog Review, the bar for deciding whether a flagged PR issue is worth keeping. Keeps real, user-affecting correctness / secu

• reviewing-personhog-protocol · Skill · 37,539 stars

  The full review process for personhog coordination-protocol changes — leases, fencing, handoffs, supervisors, failure budgets, warming, and changelog seman

• run-posthog · Skill · 37,539 stars

  Start, inspect, and drive the PostHog dev stack. Use for /run and /verify on this repo — when asked to launch PostHog, check whether the stack is healthy,

• running-ci-preflight · Skill · 37,539 stars

  Catch the deterministic CI failures reachable from your diff before pushing, with `hogli ci:preflight`. Use when the pre-push hook blocks a push, before re

• sandboxed_autoresearch_agent · Collection · 37,539 stars
• scanning-experiments-with-replay-vision · Skill · 37,539 stars

  Provisions a Replay Vision scanner scoped to one experiment's exposed sessions: sets `experiment_targeting` so the API derives the person-scoped exposure f

• scene-menu-bar · Skill · 37,539 stars

  Conventions for adding or editing the SceneMenuBar above a scene's <SceneTitleSection>. Use when adding new menu items, moving items between menus, gating

• security-audit · Skill · 37,539 stars

  Focused security audit of code, calibrated to surface real exploitable bugs and suppress theoretical findings. Use when the user asks to "audit", "security

• sending-notifications · Skill · 37,539 stars

  How to send real-time in-app notifications from PostHog backend code. Use when integrating notifications into a new feature, wiring up a notification sourc

• setting-feature-flags-in-storybook · Skill · 37,539 stars

  Use when writing a Storybook story for a component gated on a feature flag — boolean flags or multivariate/experiment-arm variants. Covers the `featureFlag

• setting-up-a-custom-rest-source · Skill · 37,539 stars

  Connect an arbitrary REST API to the PostHog data warehouse as a Custom source by authoring a JSON manifest, with no per-source code. Use when the user poi

• setting-up-a-data-warehouse-source · Skill · 37,539 stars

  Guide the user through connecting a new data warehouse source — Postgres, MySQL, Stripe, Hubspot, MongoDB, Salesforce, BigQuery, Snowflake, and so on. Use

• setting-up-data-catalog · Skill · 37,539 stars

  Populates and maintains a project's data catalog (semantic layer): canonical metrics, trust marks (certifications) on warehouse tables/views, and reviewed

• setting-up-devbox · Skill · 37,539 stars

  Guide a PostHog engineer through spinning up, connecting to, running commands on, and mirroring local code to a remote devbox (a Coder workspace running th

• setting-up-support-slack-locally · Skill · 37,539 stars

  Connect a real Slack workspace to local PostHog Conversations (the SupportHog Slack app) so Slack messages become support tickets and replies post back. Us

• setup-web-tests · Skill · 37,539 stars

  Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python v

• signals · Skill · 37,539 stars

  How to query the document_embeddings table for raw signal data using HogQL. Use when you need to perform semantic search over signals, fetch every signal t

• signals · Collection · 37,539 stars
• signals-scout-ai-observability · Skill · 37,539 stars

  Signals scout for PostHog AI observability. Watches LLM traces for cost, latency, error, volume, and eval-performance regressions.

• signals-scout-anomaly-detection · Skill · 37,539 stars

  Signals scout that watches the project's most-viewed dashboards and insights for anomalies — bursts, drops, flat-lines, and trend breaks — against each ins

• signals-scout-apm · Skill · 37,539 stars

  Signals scout for PostHog distributed tracing (APM / OpenTelemetry spans). Watches per-service RED metrics for error-rate and latency regressions, new erro

• signals-scout-conversations · Skill · 37,539 stars

  Signals scout for PostHog Conversations (support inbox). Watches `$conversation_*` ticket- lifecycle events for SLA breach steps, first-response latency bl

• signals-scout-csp-violations · Skill · 37,539 stars

  Signals scout for Content Security Policy violations. Watches `$csp_violation` events for blocked-URL clusters, per-directive bursts, post-deploy regressio

• signals-scout-customer-analytics · Skill · 37,539 stars

  Signals scout for PostHog Customer analytics (Accounts). Watches per-account engagement for churn-risk shapes — engagement cliffs, dormancy, champion depar

• signals-scout-customer-analytics-billing-and-usage · Skill · 37,539 stars

  Signals scout for per-account product-mix shifts. Watches each staked account's usage and forecasted MRR per product for one product dropping or spiking ag

• signals-scout-data-pipelines · Skill · 37,539 stars

  Signals scout for PostHog data pipelines — CDP destinations and transformations, batch exports, and hog flows. Watches for delivery failures, degraded func

• signals-scout-data-warehouse · Skill · 37,539 stars

  Signals scout for warehouse imports. Watches external data sources, sync schemas, webhook push channels, and materialized views for failures, silent stalen

• signals-scout-error-tracking · Skill · 37,539 stars

  Signals scout for PostHog error tracking. Watches `$exception` bursts, stuck loops, multi- fingerprint clusters, and status regressions.

• signals-scout-experiments · Skill · 37,539 stars

  Signals scout for PostHog A/B experiments. Watches running experiments for validity threats — sample ratio mismatch, contamination, exposure stalls, mid-ru

• signals-scout-feature-flags · Skill · 37,539 stars

  Signals scout for PostHog feature flags. Watches the flag roster and the `$feature_flag_called` stream for evaluation cliffs, ghost flags, response-distrib

• signals-scout-general · Skill · 37,539 stars

  Cross-product Signals scout. Looks for cross-product correlations and explores the surfaces the per-product specialist scouts don't cover.

• signals-scout-health-checks · Skill · 37,539 stars

  Signals scout over PostHog's own health checks. Bundles the project's active health issues by kind, weights them by blast radius, and surfaces the ones wor

• signals-scout-inbox-validation · Skill · 37,539 stars

  Follow-up Signals scout for the inbox itself. Re-measures the problems behind recently resolved reports after a soak window and reports when a fix didn't h

• signals-scout-insight-alerts · Skill · 37,539 stars

  Signals scout over the project's configured insight alerts. Reads each alert's recent firing history and surfaces the firings a human likely missed.

• signals-scout-logs · Skill · 37,539 stars

  Signals scout for PostHog logs. Watches for emerging and rate-shifted message patterns, volume bursts, severity-distribution shifts, service silence, and t

• signals-scout-mcp-tool-calls · Skill · 37,539 stars

  Signals scout for PostHog MCP tool calls. Watches `$mcp_tool_call` telemetry for tools that need improvement — broad-reach failure rates, retry hammering,

• signals-scout-observability-gaps · Skill · 37,539 stars

  Signals scout for observability gaps — significant event volumes with no insight, dashboard, or alert coverage. Recommends new insights, dashboards, or ale

• signals-scout-product-analytics · Skill · 37,539 stars

  Signals scout for core product-analytics flows — funnels, retention, lifecycle, stickiness, and paths. Watches the team's saved flows for a derived-rate re

• signals-scout-replay-vision · Skill · 37,539 stars

  Signals scout for PostHog Replay Vision scanners. Watches that enabled scanners keep observing (throughput and quota cliffs) and that aggregate score shift

• signals-scout-revenue-analytics · Skill · 37,539 stars

  Signals scout for PostHog revenue analytics. Watches for upstream failures (Stripe sync stalls, capture regressions), config drift, and goal-miss escalatio

• signals-scout-session-replay · Skill · 37,539 stars

  Signals scout for PostHog session replay. Watches that sessions keep recording (capture cliffs) and surfaces friction inside recordings — rage/dead-click c

• signals-scout-skills-store · Skill · 37,539 stars

  Skill-hygiene scout for the team's PostHog skills store. Watches recently-changed and most- used skills for authoring violations — vague descriptions, bloa

• signals-scout-surveys · Skill · 37,539 stars

  Signals scout for PostHog surveys. Watches active surveys for score regressions, response- volume drops, abandonment spikes, and targeting drift, and aggre

• signals-scout-tasks · Skill · 37,539 stars

  Signals scout for PostHog Tasks. Watches delivery health — failing runs clustered by repository and error class, retry storms — and, on a slower rotation,

• signals-scout-web-analytics · Skill · 37,539 stars

  Signals scout for PostHog web traffic. Watches per-channel session volume, attribution breakage, and landing-page health (bounce and 404 steps) against the

• signals-scout-web-vitals · Skill · 37,539 stars

  Signals scout for Core Web Vitals (`$web_vitals`). Watches each page's p75 LCP / INP / CLS / FCP against Google's thresholds and its own history — poor-ban

• simulate-new-user · Skill · 37,539 stars

  Send synthetic first-time-visitor traffic to a URL and confirm that PostHog $pageview events fire. Use when a customer wants to verify that anonymous visit

• simulate-returning-user · Skill · 37,539 stars

  Send synthetic single-session multi-page traffic to a URL and confirm PostHog $pageview events fire across page views. Use when verifying that cookies pers

• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills · Collection · 37,539 stars
• skills-store · Skill · 37,539 stars

  Discover and use shared team skills stored in PostHog. Use when the user asks to list, browse, load, or manage "shared skills", "team skills", or reference

• src · Collection · 37,539 stars
• src · Collection · 37,539 stars
• stacking-prs · Skill · 37,539 stars

  Create and manage GitHub native Stacked PRs in this repo with the `gh stack` CLI. Use when asked to stack PRs, split a large change into a stack, add a lay

• storybook-stories · Skill · 37,539 stars

  Write Storybook stories for PostHog UI components. Covers the provider stack stories run inside, the key gotcha that tRPC/useHostTRPC queries never resolve

• streamlit_apps · Collection · 37,539 stars
• subscriptions · Collection · 37,539 stars
• suggesting-data-imports · Skill · 37,539 stars

  Use when the user asks about revenue, payments, subscriptions, billing, CRM deals, support tickets, ad spend, production database tables, or other data Pos

• suggesting-path-cleaning-rules · Skill · 37,539 stars

  Runs and reasons about the automated AI health check that suggests path-cleaning rules for web-analytics teams. Use when asked to generate path-cleaning su

• suppressing-noisy-errors · Skill · 37,539 stars

  Create PostHog error tracking suppression rules to drop high-volume, low-value errors at ingestion. Use when the user asks "stop capturing this error", "dr

• survey-sdk-audit · Skill · 37,539 stars

  Audit PostHog survey SDK features and version requirements

• surveys · Collection · 37,539 stars
• tasks · Collection · 37,539 stars
• test-electron-app · Skill · 37,539 stars

  Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222,

• testing-mcp-tools-locally · Skill · 37,539 stars

  Set up the local dev environment, seed data, and API keys to test the staff-only managed migrations MCP tools (managed-migrations-support-list, managed-mig

• tools · Collection · 37,539 stars
• tracing · Collection · 37,539 stars
• traffic-sim · Collection · 37,539 stars
• triaging-error-issues · Skill · 37,539 stars

  Triage PostHog error tracking issues during a daily or on-call review. Use when the user asks "what's broken?", "what new errors do we have?", "show me top

• triaging-visual-review-runs · Skill · 37,539 stars

  Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot

• triaging-web-analytics-support · Skill · 37,539 stars

  Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into

• tuning-incremental-sync-config · Skill · 37,539 stars

  Change the sync configuration of an existing data warehouse schema — switch sync_type, pick a different incremental_field, set primary_key_columns, choose

• turning-engineering-analytics-into-insights · Skill · 37,539 stars

  Converts engineering analytics (PR / CI) data into saved PostHog insights, dashboards, and subscriptions, and explains how to query the product data direct

• upgrade-claude-adapter · Skill · 37,539 stars

  Sync this fork of @anthropic-ai/claude-agent-acp (packages/agent/src/adapters/claude) with a newer upstream release: bump the claude-agent-sdk / @agentclie

• user_interviews · Collection · 37,539 stars
• using-kea-disposables · Skill · 37,539 stars

  Use when adding timers (`setInterval`, `setTimeout`), event listeners (`window.addEventListener`, `document.addEventListener`, `MediaQueryList.addEventList

• validating-and-publishing-canvases · Skill · 37,539 stars

  Validate and publish a canvas source project safely: the source-project shape, declared capabilities, reading the current version pointer, iterating on val

• verify-posthog-instrumentation · Skill · 37,539 stars

  Use this skill to verify that PostHog instrumentation is firing correctly on a website. Drives a real browser at one or more URLs, observes which PostHog e

• visual_review · Collection · 37,539 stars
• visualizing-change-over-time · Skill · 37,539 stars

  Helps PostHog engineers and agents pick the right chart when a request is about visualizing change over time, before/after comparisons, or period-over-peri

• warehouse_sources · Collection · 37,539 stars
• warehouse-source-new-version · Skill · 37,539 stars

  Add support for a new vendor API version to an existing Data warehouse import source, or deprecate an old one. Use when a vendor ships a new API version (S

• web_analytics · Collection · 37,539 stars
• workflows · Collection · 37,539 stars
• working-with-scouts · Skill · 37,539 stars

  How to get real jobs done with PostHog Signals scouts — the scheduled agents that watch a project and write reports into the Signals inbox — and how to ste

• working-with-skills · Skill · 37,539 stars

  Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, esp

• working-with-task-comments · Skill · 37,539 stars

  Read and use comments attached to the current PostHog task, its artifacts, and its canvases through the PostHog MCP exec dispatcher. Use when the user ment

• writing-clickhouse-queries · Skill · 37,539 stars

  Guide for writing performant ClickHouse queries in PostHog product code. Use when writing HogQL query runners, designing a ClickHouse table for a new produ

• writing-code-comments · Skill · 37,539 stars

  Gates whether a code comment should exist and forces the ones that stay to explain why, not what. Use ALWAYS before writing or editing a comment in any lan

• writing-evals · Skill · 37,539 stars

  Teaches how to write and run evals on the `products/posthog_ai/eval_harness/` harness — sandboxed agent suites that execute the real coding agent in a Dock

• writing-kea-logics · Skill · 37,539 stars

  Guide for writing or reviewing PostHog kea logic files (`*Logic.ts` / `*Logic.tsx`). Use when creating a new logic, adding actions/reducers/selectors/liste

• writing-pr-descriptions · Skill · 37,539 stars

  Shapes a PR body into something a reviewer understands at a glance. Use ALWAYS before writing or editing a PR description, before `gh pr create` or `gh pr

• writing-skills · Skill · 37,539 stars

  Guide for writing PostHog agent skills — job-to-be-done templates that teach agents how to use MCP tools to achieve a goal. Use when adding new product fun

• writing-streamlit-apps · Skill · 37,539 stars

  Write Streamlit app source code that runs well in a PostHog sandbox — the posthog_apps.query() bridge for reading PostHog data, the packages baked into the

• writing-tests · Skill · 37,539 stars

  Gates whether a new test should exist and forces it to be efficient, protecting CI from low-value test bloat. Use before any change to what a pytest, Jest,

• writing-user-facing-copy · Skill · 37,539 stars

  Sets the voice and word choices for any text a person reads in PostHog: UI labels, buttons, tooltips, empty and error states, notifications, in-app message

• posthog-for-claude · Collection · 12 stars
• posthog-instrumentation · Skill · 12 stars

  Automatically add PostHog analytics instrumentation to code. Triggers when user asks to add tracking, instrument events, add analytics, or implement featur

• skills · Collection · 12 stars
• access_control · Collection
• adding-activity-logging · Skill

  Adds or changes activity logging (the audit trail) for a Django model in PostHog. Use when a model's writes must show in the Activity side panel or the adv

• adding-warehouse-person-properties · Skill

  Sync columns from a synced data warehouse table onto PostHog person or group properties, so warehouse data becomes usable anywhere person and group propert

• analyzing-experiment-precompute-canary · Skill

  Analyze the experiment precompute result-consistency canary across prod-US and prod-EU, deep-dive any issues, and produce an actionable report. Sweeps the

• analyzing-task-runs · Skill

  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 repor

• announcing-behavior-changes · Skill

  Decides whether a behavior-changing fix needs an in-app notice, then builds one that reaches only the affected users and can be removed later. Use when a c

• authoring-data-quality-checks · Skill

  Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views: not-null, uniqueness, accepted values,

• billing · Collection
• checking-member-access · Skill

  Explains what a member or a role can do in a PostHog project, using the access control MCP tools. Use when the user asks what someone can see or edit, who

• composing-grid-canvases · Skill

  Compose PostHog grid canvases — widget grids (including the user's home canvas) built from reusable component canvases. Use when a task asks to add, fill,

• context_layer · Collection
• context-layer-consolidation · Skill

  Keep the context wiki coherent using the deterministic lint report queue

• context-layer-dreaming · Skill

  Synthesizes recent organizational activity into a durable context wiki. Use when running a nightly or incremental context-layer dream, or when updating sou

• context-layer-health-check · Skill

  Semantic review of context wiki quality after deterministic consolidation

• creating-box-plot-insights · Skill

  Creates product analytics or SQL-backed box plot insights in PostHog. Use when a user asks to create, build, or save a box plot, visualize a numeric distri

• creating-surveys · Skill

  Creates and launches PostHog surveys through MCP, including NPS/CSAT popovers, hosted feedback forms, and headless surveys. Guides survey type selection, a

• customer_analytics · Collection
• data_quality · Collection
• debugging-experiments · Skill

  Debug and support PostHog Experiments (A/B tests) for a customer looking at their own results. Use whenever an experiment support ticket is pasted or a cus

• debugging-table-access-denied · Skill

  Debugs a TableAccessDeniedError from an error tracking issue, Slack alert, or user report. Use when investigating why HogQL denied a system or warehouse ta

• depot-ci · Skill

  Configures and manages Depot CI, a drop-in replacement for GitHub Actions that runs workflows entirely within Depot. Use when migrating GitHub Actions work

• dynamic-workflows · Skill

  Designs and runs task-specific JavaScript harnesses with the `workflow` tool. Use for broad, long-running, highly structured, or adversarial work that bene

• exploring-mcp-tool-original-user-motive · Skill

  Build a starting-point taxonomy for an MCP tool — what users were trying to accomplish before they reached the tool — and publish it as a PostHog notebook.

• extending-hobby-smoke-tests · Skill

  Design, extend, review, or debug PostHog Hobby end-to-end smoke tests in bin/hobby-ci.py and .github/workflows/ci-hobby.yml. Use when adding an ingestion r

• integrating-with-posthog-ai · Skill

  Wire a PostHog product surface into the PostHog AI agent from the frontend. Use when attaching scene or entity context, injecting instructions to steer the

• maintaining-python-tests · Skill

  Maintains existing pytest and Django test suites without weakening correctness. Use when asked to reduce Python test runtime or CI work, investigate slow p

• managing-dashboards · Skill

  Guides PostHog engineers through dashboard platform and scene changes. Use when changing Dashboard, DashboardTile, dashboardLogic, dashboard layouts, dashb

• orchestration · Collection
• organizing-conversations-code · Skill

  File layout for the conversations product. Use when adding, moving, renaming, or reviewing files under products/conversations/ — especially frontend compon

• placing-product-frontend-code · Skill

  Decide which tree a frontend file belongs in — `products/<name>/frontend/` or `frontend/src/scenes/<name>/` — and explain why the boundary is real rather t

• profiling-slow-api-endpoints · Skill

  Profiles slow PostHog API endpoints when the main cost is in Postgres or Python. Use when a screen, picker, or list is slow; a Django endpoint has high tai

• querying-production-databases-via-metabase · Skill

  Runs read-only production database analysis through PostHog's internal Metabase instances. Use for ClickHouse query logs, slow query cost, Postgres query p

• review-hog-resolution-criteria · Skill

  The resolution criteria for PostHog Review's resolution stage: the bar for deciding, per unresolved review thread, whether the ask is worth implementing an

• skills · Collection
• skills · Collection
• skills · Collection
• skills · Collection
• skills · Collection
• splitting-oversized-modules · Skill

  Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanicall

• subagent-orchestration · Skill

  How and when to delegate work to subagents via the `subagent` tool (Explore, Plan, General). Use when a task involves codebase recon, implementation planni

• triaging-merge-queue-failures · Skill

  Decision procedure for a PR that failed or was removed from the Trunk merge queue: classify the kick (superseded by a newer commit, not mergeable, a gate t

• triaging-warehouse-sync-tickets · Skill

  Debug a customer's data warehouse source, schema, or table from a support ticket, using PostHog's own production data. Use when a ticket says a warehouse t

• understanding-billing-usage · Skill

  Explains PostHog billing usage and spend from the customer's visible Billing MCP tools. Use when the user asks why usage or spend is high, which product or

• using-redis-token-buckets · Skill

  Use when adding a bucket-like rate limit backed by Redis: a per-caller budget with burst capacity and continuous refill, a refund path for requests that di

• working-with-charts · Skill

  Guides consumers of @posthog/quill-charts through chart selection, data, themes, sizing, and composition. Use when adding or changing a chart built with th

• writing-dataclasses · Skill

  House rules for Python dataclasses in PostHog: when to reach for one instead of a tuple or `dict[str, Any]`, which decorator to use (`@frozen` from `postho

• writing-simplified-technical-english · Skill

  Write English that a reader cannot misread: one meaning per word, active voice, simple tenses, one idea per sentence, short sentences. Based on ASD-STE100

• writing-ui-components · Skill

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

Browse the @skills marketplace