posthog / skills
★ 49A skill package that teaches your agent 126 capabilities — every one documented and browsable below, no GitHub required · by posthog.
Each skill below is one capability this package teaches your agent. Install the whole package, or open a skill to install just that one.
Draft structured handover notes for transitioning a PostHog account from one TAM or CSM to another. Use this skill when a TAM needs to hand over an account,…
4 files — installable on its own
Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with…
1 file — installable on its own
Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check,…
7 files — installable on its own
This skill produces a project-wide audit of the data warehouse pipeline. Use it when the user wants a summary of everything broken , not a deep-dive on one sync. The deep-dive on individual failures is diagnosing-failed-warehouse-syncs ; this skill is the scan that tells them where to look first.
1 file — installable on its own
Authoring an alert is a measurement problem, not a guessing problem. You are not trying to be exhaustive — you are trying to land thresholds that fire 0–3 times per week on real production patterns, on services that matter.
6 files — installable on its own
Identify and clean up stale feature flags in a PostHog project. Use when the user wants to find unused, fully rolled out, or abandoned feature flags, review…
1 file — installable on its own
Configures the analytics side of a PostHog experiment — exposure criteria (default `$feature_flag_called` vs custom exposure events), primary and secondary…
4 files — installable on its own
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 users…
3 files — installable on its own
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 a…
1 file — installable on its own
Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions…
1 file — installable on its own
When a developer says "local replay isn't working" or "recordings aren't showing up", work through these layers in order. The local replay pipeline has several moving parts and failures are usually silent.
3 files — installable on its own
Work top-down when a data warehouse source or table is failing, stuck, or producing bad data: source → schema → recovery action. Do not jump straight to "resync from scratch" — that discards synced data and restarts from zero, which is rarely the right first step.
1 file — installable on its own
When a user asks "why wasn't this session recorded?" or "why don't I have any recordings?", follow this workflow to systematically diagnose the cause.
5 files — installable on its own
When a user asks about PostHog SDK versions, outdated SDKs, or whether they should upgrade, use the pre-digested SDK Doctor report rather than reasoning about versions yourself. The backend applies smart-semver rules (grace periods, minor-count thresholds, age-based detection), traffic-percentage thresholds, and provides user-facing copy that matches the SDK Doctor UI exactly.
1 file — installable on its own
PostHog error tracking for Android
8 files — installable on its own
PostHog error tracking for Angular
8 files — installable on its own
PostHog error tracking for Flutter
8 files — installable on its own
PostHog error tracking for Go
8 files — installable on its own
PostHog error tracking for Hono
8 files — installable on its own
PostHog error tracking for Next.js
8 files — installable on its own
PostHog error tracking for Node.js
8 files — installable on its own
PostHog error tracking for Nuxt
8 files — installable on its own
PostHog error tracking for Python
8 files — installable on its own
PostHog error tracking for React
8 files — installable on its own
PostHog error tracking for React Native
8 files — installable on its own
PostHog error tracking for Ruby
8 files — installable on its own
PostHog error tracking for Ruby on Rails
8 files — installable on its own
PostHog error tracking for Svelte
8 files — installable on its own
PostHog error tracking for Web (JavaScript)
8 files — installable on its own
PostHog captures distributed traces from OpenTelemetry. Each trace is a tree of spans representing a request’s path through services.
10 files — installable on its own
if users opt in then posthog-js automatically captures clicks, form submissions, and page changes as $autocapture events. Each event records the clicked DOM element and its ancestors in the elements_chain column.
4 files — installable on its own
Inspects PostHog Web analytics Live tab data — current users online, last-30-minutes pageviews, top pages, referrers, devices, browsers, countries, bot…
1 file — installable on its own
Investigate LLM analytics clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into…
3 files — installable on its own
PostHog attaches per-call cost metadata to every $ai_generation and $ai_embedding event at ingestion time. Every cost question reduces to an aggregation over those two event types — the interesting variation is only in how you group, filter, and compare.
8 files — installable on its own
PostHog evaluations score $ai_generation events. Each evaluation is one of two types, both first-class:
1 file — installable on its own
PostHog captures LLM/AI agent activity as traces. Each trace is a tree of events representing a single AI interaction — from the top-level agent invocation down to individual LLM API calls.
12 files — installable on its own
PostHog feature flags for Android applications
5 files — installable on its own
PostHog feature flags for API applications
5 files — installable on its own
PostHog feature flags for .NET applications
5 files — installable on its own
PostHog feature flags for Elixir applications
5 files — installable on its own
PostHog feature flags for Flutter applications
5 files — installable on its own
PostHog feature flags for Go applications
5 files — installable on its own
PostHog feature flags for iOS applications
5 files — installable on its own
PostHog feature flags for Java applications
5 files — installable on its own
PostHog feature flags for Next.js applications
6 files — installable on its own
PostHog feature flags for Node.js applications
5 files — installable on its own
PostHog feature flags for PHP applications
5 files — installable on its own
PostHog feature flags for Python applications
5 files — installable on its own
PostHog feature flags for React applications
5 files — installable on its own
PostHog feature flags for React Native applications
5 files — installable on its own
PostHog feature flags for Ruby applications
5 files — installable on its own
PostHog feature flags for Rust applications
5 files — installable on its own
PostHog feature flags for Web (JavaScript) applications
5 files — installable on its own
Some PostHog features (group session summaries, single session summaries, replay AI search, error tracking AI debug, etc.) generate hundreds or thousands of LLM traces per week. Reading them by hand is not feasible. This skill covers the end-to-end pattern for turning that trace volume into a live Slack feed of canonical use cases — what users are actually doing with the feature.
1 file — installable on its own
Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with…
1 file — installable on its own
When a user says "show me a replay for this error" or "find a recording for issue X", the goal isn't just any linked session — it's the one that best shows what led to the error. Popular issues can have hundreds of linked sessions, and most are crash-only fragments or duplicate occurrences. This skill picks the most useful one.
1 file — installable on its own
The Inbox is where PostHog surfaces signal reports — clusters of related observations (signals) that have been aggregated into a single issue or trend (e.g. "Error rate spiked 3× on /checkout"). Reports come from multiple source products: error tracking, session replay, web analytics, experiments, and integrations like Linear, GitHub, and Zendesk.
1 file — installable on its own
Use this skill to add PostHog error tracking that captures and monitors exceptions in your application. Use it after implementing features or reviewing PRs to ensure errors are tracked with full stack traces and source maps. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any platform or language.
30 files — installable on its own
Use this skill to add PostHog feature flags that gate new or changed functionality. Use it after implementing features or reviewing PRs to ensure safe rollouts with feature flag controls. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any platform or language.
26 files — installable on its own
Use this skill to add the PostHog SDK to an application. Use it when setting up PostHog for the first time, or reviewing PRs that need PostHog initialization. Covers SDK installation, provider setup, and basic configuration. Supports any framework or language.
50 files — installable on its own
Use this skill to add PostHog LLM analytics that trace AI model usage in new or changed code. Use it after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any provider or framework.
40 files — installable on its own
Use this skill to add PostHog log capture for new or changed code. Use it after implementing features or reviewing PRs to ensure meaningful log events are captured with structured properties. If PostHog log export is not yet configured, this skill also covers initial OTLP exporter setup. Supports any platform or language.
18 files — installable on its own
Use this skill to add product analytics events (capture calls) that track meaningful user actions in new or changed code. Use it after implementing features or reviewing PRs to ensure key user behaviors are captured. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any framework or language.
50 files — installable on its own
PostHog integration for Android applications
9 files — installable on its own
PostHog integration for Angular applications
9 files — installable on its own
This skill helps you add PostHog analytics to Astro (Hybrid) applications.
9 files — installable on its own
PostHog integration for server-rendered Astro applications with API routes
9 files — installable on its own
PostHog integration for static Astro sites using SSG
9 files — installable on its own
PostHog integration for Astro with ClientRouter view transitions
9 files — installable on its own
PostHog integration for Django applications
9 files — installable on its own
PostHog integration for Expo applications
9 files — installable on its own
PostHog integration for FastAPI applications
9 files — installable on its own
PostHog integration for Flask applications
9 files — installable on its own
integration-javascript_node — an installable skill for AI agents, published by posthog/skills.
9 files — installable on its own
integration-javascript_web — an installable skill for AI agents, published by posthog/skills.
9 files — installable on its own
PostHog integration for Laravel applications
9 files — installable on its own
PostHog integration for Next.js App Router applications
9 files — installable on its own
PostHog integration for Next.js Pages Router applications
9 files — installable on its own
integration-nuxt-3.6 — an installable skill for AI agents, published by posthog/skills.
9 files — installable on its own
PostHog integration for Nuxt 4 applications
9 files — installable on its own
PostHog integration for any Python application using the Python SDK
10 files — installable on its own
PostHog integration for React Native applications
9 files — installable on its own
PostHog integration for React Router v6 applications
9 files — installable on its own
PostHog integration for React Router v7 - Data mode applications
9 files — installable on its own
PostHog integration for React Router v7 - Declarative mode applications
9 files — installable on its own
PostHog integration for React Router v7 - Framework mode applications
9 files — installable on its own
This skill helps you add PostHog analytics to React with TanStack Router (code-based) applications.
9 files — installable on its own
This skill helps you add PostHog analytics to React with TanStack Router (file-based) applications.
9 files — installable on its own
PostHog integration for React applications built with Vite (no router)
8 files — installable on its own
PostHog integration for any Ruby application using the Ruby SDK
9 files — installable on its own
PostHog integration for Ruby on Rails applications
10 files — installable on its own
PostHog integration for SvelteKit applications
9 files — installable on its own
PostHog integration for Swift iOS and macOS applications
9 files — installable on its own
PostHog integration for TanStack Start full-stack applications
9 files — installable on its own
PostHog integration for Vue 3 applications
9 files — installable on its own
For "why did X change?" questions about a saved insight, dashboard tile, or pasted query. Don't load this skill for plain "what is X?" questions — only when there's an observed change to explain.
14 files — installable on its own
When a user asks "what happened in this session?" or provides a recording/session ID to investigate, gather all relevant context in parallel rather than making them ask for each piece.
1 file — installable on its own
PostHog LLM analytics for all supported providers
39 files — installable on its own
PostHog logs for Datadog
9 files — installable on its own
PostHog logs for Go
9 files — installable on its own
PostHog logs for Java
9 files — installable on its own
PostHog logs for Next.js
9 files — installable on its own
PostHog logs for Node.js
9 files — installable on its own
PostHog logs for Other Languages
9 files — installable on its own
PostHog logs for Python
9 files — installable on its own
Guides experiment state transitions: launching, pausing, resuming, ending, shipping variants, archiving, resetting, and duplicating. Covers preconditions,…
1 file — installable on its own
Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots. Use when the user wants to subscribe to an…
1 file — installable on its own
Use this skill to add PostHog error tracking that captures and monitors exceptions in your application. Use it after implementing features or reviewing PRs to ensure errors are tracked with full stack traces and source maps. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any platform or language.
22 files — installable on its own
Use this skill to add PostHog feature flags that gate new or changed functionality. Use it after implementing features or reviewing PRs to ensure safe rollouts with feature flag controls. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any platform or language.
21 files — installable on its own
Use this skill to add the PostHog SDK to an application. Use it when setting up PostHog for the first time, or reviewing PRs that need PostHog initialization. Covers SDK installation, provider setup, and basic configuration. Supports any framework or language.
50 files — installable on its own
Use this skill to add PostHog LLM analytics that trace AI model usage in new or changed code. Use it after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and costs. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any provider or framework.
39 files — installable on its own
Use this skill to add PostHog log capture for new or changed code. Use it after implementing features or reviewing PRs to ensure meaningful log events are captured with structured properties. If PostHog log export is not yet configured, this skill also covers initial OTLP exporter setup. Supports any platform or language.
15 files — installable on its own
Use this skill to add product analytics events (capture calls) that track meaningful user actions in new or changed code. Use it after implementing features or reviewing PRs to ensure key user behaviors are captured. If PostHog is not yet installed, this skill also covers initial SDK setup. Supports any framework or language.
50 files — installable on its own
Debug and inspect PostHog implementations on any website. Use this skill when a user wants to understand how PostHog is implemented on a page, troubleshoot…
4 files — installable on its own
Help existing PostHog customers improve their PostHog instance. Triggers on "help [customer] improve their PostHog setup", "audit [company]'s PostHog…
8 files — installable on its own
Create and configure surveys in PostHog through guided conversation. Use this skill when a user wants to create a survey, collect user feedback, run…
7 files — installable on its own
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…
50 files — installable on its own
Use this skill when the user wants to connect an external data source to PostHog's data warehouse for the first time. The setup has a specific three-step flow (wizard → db-schema → create) — skipping steps leads to failed sources and confused users.
3 files — installable on its own
Signals are automated observations that PostHog generates by monitoring a customer's product data across multiple sources — error tracking, web analytics, experiments, session replay, and more. Each signal is a short natural-language description of something noteworthy (e.g. "Error rate spiked 3× on /checkout").
1 file — installable on its own
Skills are reusable agent workflows stored in PostHog following the Agent Skills specification — a body of instructions (SKILL.md) plus optional bundled files (scripts, references, assets), structured metadata, and an allowed_tools list.
1 file — installable on its own
Use when the user asks about revenue, payments, subscriptions, billing, CRM deals, support tickets, production database tables, or other data that PostHog does…
1 file — installable on its own
HogQL queries for PostHog analytics
10 files — installable on its own
Visual Review is PostHog's screenshot-regression product: CI captures storybook + playwright screenshots, diffs them against committed baseline hashes, and gates the PR until a human approves the visible changes. A PR with visual changes carries a visual-review GitHub status check that stays red until each diffed snapshot is approved or tolerated in the VR UI .
1 file — installable on its own
A sync's configuration lives on the ExternalDataSchema and can be changed any time via external-data-schemas-partial-update . Most changes are non-destructive (take effect on the next sync), but a few (switching sync_type, changing primary keys) require careful handling to avoid corrupting the synced data.
1 file — installable on its own
Deep dive on a PostHog user by email address. Analyze what they do, where they spend time, and what products they use.
2 files — installable on its own
Generate comprehensive workload analysis visualizations for PostHog customer accounts. Use when user requests account analysis, workload breakdown, SDK…
8 files — installable on its own
Package documentation is syncing from GitHub — check back shortly. Meanwhile, every skill in the Skills tab carries its own full instructions.
Install the whole package (126 skills):
npx skills add https://github.com/posthog/skillsOr install a single skill:
npx skills add https://github.com/posthog/skills --skill <name>Pick the skill name from the Skills tab — each entry there installs independently.