PostHog

Author a PostHog canvas with semantic HTML, CSS, and direct browser APIs — documents, articles, generative graphics, 2D canvas and WebGL experiences, and focused experiments where React components add no useful structure. Use after building-canvases has…

Author the React + Quill implementation of a PostHog canvas: the single-component contract, the allowed imports, Quill (PostHog's design system) component and composition rules, theme-aware design tokens, loading skeletons, and the in-canvas date picker. Use…

Validate and publish a canvas source project safely: the source-project shape, declared capabilities, reading the current version pointer, iterating on validation diagnostics, guarded publishing with expected_current_version_id, staging a draft build and…

How to instrument PostHog's own Metrics product from PostHog-owned code — record counters, gauges, and histograms that land in posthog.metrics, the same way customers do. Use when adding application metrics in this monorepo (web, Celery, Temporal), when asked…

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 (Stripe date versions, Shopify quarterly versions, header-pinned revisions, /vN/ URL bumps), when…

Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status), workflow-health (per-workflow CI trends), and pr-lifecycle (a single PR's timeline). Use when asked whether CI…

Guide for writing or reviewing PostHog kea logic files (`*Logic.ts` / `*Logic.tsx`). Use when creating a new logic, adding actions/reducers/selectors/listeners/loaders/forms/router bindings, choosing between reducer vs selector vs cache, deciding between…

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, or Playwright test asserts or sets up, down to one fixture or one assertion added to an existing block.…

Inspect and compare offline AI evaluation experiments, diagnose case-level regressions, and follow scorer history across application, model, or prompt changes. Use when a user asks whether an offline run improved, why a case failed, how scores changed between…

Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that cost storage and compute. Use when the user asks "which of my views are broken?", "why is this…

Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views, and HogQL catalog metrics: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL.…

Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and — crucially — estimating the credits it will spend and checking…

Finds out why a data quality check failed or errored, looks at the rows it matched, and recommends the fix. Also covers a materialized view refresh that the data quality gate did not publish. Use when asked why a check is red, what rows failed, why a view…

Designs a Replay Vision scanner that produces trustworthy observations: one visible question per scanner, a type chosen from the answer shape, a query that selects only sessions able to answer it, a prompt that demands on-screen proof and allows no or…

Runs diagnostics and a health check on a PostHog experiment whose results look wrong, biased, empty or stale. Covers 0 exposures, sample ratio mismatch, lost or uneven exposures, users in multiple variants, identity faults, significance traps (peeking, A/A,…

Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query…

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 exceptions to Slack/webhook/Linear, or evaluate which error events are worth alerting on. Covers…

Write, edit, and adapt PostHog Signals scouts: scheduled agents that scan a project and report findings. Use to change a canonical scout's scope, thresholds, schedule, or dry-run settings; add a scout for an uncovered surface; record structured output from…

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. Use when a user asks to create a dashboard, put several metrics/charts together on one page,…

Create or edit a PostHog freeform canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in PostHog and rendered by the desktop/web app. Use when a task asks to build, generate, update, or fix a…

Author the React + Quill implementation of a PostHog canvas: the single-component contract, the allowed imports, Quill (PostHog's design system) component and composition rules, theme-aware design tokens, loading skeletons, and the in-canvas date picker. Use…

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 change drafts surgically with patch operations. Use when asked to build, set up, automate, change, fix, or…

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 rolled out, or abandoned feature flags, run a feature flag hygiene review or a weekly cleanup, reduce…

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, move, resize, or remove a widget on a grid or home canvas, to compose a whole canvas of widgets from one…

Sync this fork of @anthropic-ai/claude-agent-acp (packages/agent/src/adapters/claude) with a newer upstream release: bump the claude-agent-sdk / @agentclientprotocol/sdk, port upstream bug fixes and new SDK message handling, preserve the fork's divergences,…

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 "what's in my inbox?", "what should I look at?", "which reports are actionable?", "what's PostHog flagged…

Signals scout for PostHog Tasks. Watches delivery health — failing runs clustered by repository and error class, retry storms — and, on a slower rotation, recurring demand across human-authored tasks. Skips the scout fleet's own runs.

Guides experiment state transitions: launching, pausing, resuming, freezing/unfreezing exposure, ending, shipping variants, archiving, resetting, duplicating, and copying to another project. Covers preconditions, implications for variant assignment and…

Provisions a Replay Vision scanner scoped to one experiment's exposed sessions: sets `experiment_targeting` so the API derives the person-scoped exposure filter server-side, templates a prompt that stays comparable across variants, sizes credit spend against…

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 change drafts surgically with patch operations. Use when asked to build, set up, automate, change, fix, or…

Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data…

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

Add or review PostHog feature flag checks so each flag is evaluated once, where its code and data live, for the right person.

Rank a PostHog user's first-touch acquisition channels by retained Stripe revenue and CAC payback, using ad spend from Google/Meta, saved as a reusable PostHog insight. Use this whenever someone asks which marketing channels or sources bring customers who…

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. Use when the user wants to define, model, or measure activation, the "aha…

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. Use when the user wants to model, define, or compute a conversion rate, funnel, step…

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) or an external dbt project. Use when the user wants to model…

Measure whether a specific feature rollout moved revenue: split users on feature-flag or experiment exposure and compare downstream Stripe revenue and retention between the exposed cohort and control, saved as a reusable PostHog insight. Use this whenever…

Rank a PostHog user's product features by the revenue of the customers who use them (joins Stripe MRR/invoices to feature-usage events) and save it as a reusable PostHog insight. Use this whenever someone asks which features their highest-revenue or best…

Score CRM leads (HubSpot/Salesforce) by recent product usage and surface the warmest leads sales hasn't contacted yet, a product-qualified-lead list saved as a reusable PostHog insight. Use this whenever someone wants product-qualified leads (PQLs), a lead…

Sync this fork of @anthropic-ai/claude-agent-acp (packages/agent/src/adapters/claude) with a newer upstream release: bump the claude-agent-sdk / @agentclientprotocol/sdk, port upstream bug fixes and new SDK message handling, preserve the fork's divergences,…

Merge a PR into main through the Trunk merge queue and babysit it until it lands. Enqueue with a "/trunk merge" comment, then poll the "Trunk Merge Queue" check run and the PR state until it is MERGED or FAILED, reporting the Trunk bot's failure reason if the…

Write Storybook stories for PostHog UI components. Covers the provider stack stories run inside, the key gotcha that tRPC/useHostTRPC queries never resolve in Storybook (so data-fetching components render empty), and the pure-presentational split that makes a…

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, snapshot the accessibility tree to verify changes, click/type/navigate, and screenshot the actual…

Edit the @posthog/quill design system locally and consume the change in this repo (posthog-code) before it is published to npm. Use when changing quill components/primitives/tokens, when a quill change must be tested inside the Code app, or when the user…

How and when to delegate work to subagents via the `subagent` tool (Explore, Plan, General). Use when a task involves codebase recon, implementation planning, or actual code changes that would benefit from an isolated context window instead of doing it all…

How to write JavaScript workflow scripts for the `workflow` tool - fanning work out across many isolated subagents with agent(), parallel(), and pipeline(), then synthesizing one result. Use when a task decomposes into several independent investigations or…

Add, replace, and optimize the looping demo videos in the onboarding "welcome" bento grid (packages/ui/src/features/onboarding). Covers the ffmpeg compression workflow (the scripts/optimize-onboarding-videos.mjs wrapper), the faststart + right-size best…

Watches a set of dashboards you describe in plain words. Flags tiles whose latest complete bucket moves away from its own seasonal baseline, and tiles that error, go dead, or plot the wrong thing. Keeps its watchlist current, and fixes broken tiles when it…

Daily driver for the PostHog Self-driving Inbox: a live in-flight table of the reports you are a suggested reviewer on, each mapped to its GitHub PR and issues with age, review and CI signals, and one next action; a ranked list of reports ready for Create PR;…

A starter kit for running one area of ongoing work as a living skill that agents and people share across sessions: a numbered issues/ backlog with an index, ideas/, open-prs.md, a sectioned HANDOVER.md each session overwrites, environment-notes.md for durable…

Build and run a curated layer of PostHog data-warehouse views (saved queries) with the view-* MCP tools. Covers the tool contracts (query JSON shape, edited_history_id, incremental settings, sync_frequency buckets), write-path mechanics (timeouts that still…

House style and refactoring playbook for PostHog skills-store skills, layered on the Agent Skills spec (agentskills.io) and Anthropic authoring best practices. Covers the compliance floor (spec-checklist.md: frontmatter, name format, description under 1024…

Create a GitHub pull request for the current branch using the gh CLI. Use when a user wants to open a PR and have the title, body, template, and assignee handled for them, following the repo's conventions and keeping public PRs free of PII.

Reference for the Agent Skills format specification (agentskills.io) — the open SKILL.md format used by Claude Code, Codex, Copilot, and other agents. Covers required frontmatter (name, description), optional fields (license, compatibility, allowed-tools,…

Summarize what needs attention in one GitHub repository: open pull requests, the review queue, failing checks, stale work, and what merged recently. Use at the start of a work session to decide what to pick up next.

Architectural guidance for changes to the PostHog Wizard: program and framework boundaries, agent routing, gateway admission, security, and TUI state. Read before structural changes, then load the relevant procedural skill.

Add or extend language and framework support in the PostHog wizard, including detection, framework configuration, registration, and matching context-mill content.

Add a PostHog wizard capability backed by context-mill content. Choose a skill command or native program, configure an orchestrator flow, and wire any required CLI, screens, or prerequisites.

Drive the PostHog wizard headlessly against a throwaway app through wizard-ci MCP tools, inspect decisions, and capture the real TUI. Use for detection checks and end-to-end exploration.

Build or modify the PostHog wizard's Ink screens, primitives, keyboard interactions, and session-driven screen flow. Use for TUI work in this repository.

Author or revise PostHog SDK acceptance scenarios, Gherkin features, and compliance-harness bindings. Use when adding behavioral coverage, reconciling acceptance tests with canonical OpenSpec, or making public SDK calls observable through a test adapter.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

Build, deploy, and port-forward the multi-tenant control plane on local Kubernetes. Use when you need to test duckgres in multi-tenant mode with per-team worker pools.

Promote the duckgres control-plane image to prod from the CLI — resolve the built image ref from the charts state file, fire the charts Promote-to-Prod workflow, and watch it through the approval gate. Use when the user says "promote duckgres", "ship the CP…

Tear down the multi-tenant K8s stack, kill port-forwards, and clean up worker pods. Use when done testing multi-tenant mode.

Start duckgres with DuckLake (S3-backed storage with PostgreSQL metadata) for local testing. Use when testing duckgres against DuckLake or reproducing Fivetran sync issues.

Author a new PostHog browser extension, or port a posthog-js v1 extension, against the @posthog/browser-common Client/Extension contract. Use when adding or porting an extension (autocapture, pageview, surveys, replay, exceptions, web-vitals, campaign-params,…

Cross-reference a posthog-js or rrweb change against past incident patterns before writing, reviewing, or merging it. Use when a diff touches session recording, the recorder or any lazy-loaded extension bundle (entrypoints/), session rotation or idle…

Quickly compare the posthog-js array.js bundle size in the current working tree against a git baseline using the repository's esbuild proxy. Use when asked about array.js size, bundle-size percentage changes, whether browser SDK changes increased the bundle,…

Add support for a new PostHog resource type (feature flag, cohort, action, survey, annotation, alert, …) to posthog-definitions. Walks through the eight files that must change, the tag-based identity convention, the load/diff/execute pipeline wiring, and the…

Add support for a PostHog resource that exists exactly once per project (project settings, organization billing config, plugin enablement flags, …). Singletons do not fit the tag-based identity model — they have no collection to filter, no key to…

Code review guide for choosing between Result types and thrown exceptions. Recoverable, expected failures should be returned as Result values; only unrecoverable bugs and broken invariants should throw. Use when reviewing code that introduces a new error…