PostHog

Skills from PostHog

• analyzing-experiment-session-replays

  This skill enables agents to analyze session recordings from experiment variants to identify behavioral differences between control and test groups.

  Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago

• analyzing-offline-evaluations

  This skill inspects and compares offline AI evaluation experiments stored in PostHog, diagnoses case-level regressions, and tracks scorer changes across…

  Claude Code, Codex, Cursor +4 · about 1.5K tokens · pinned 6 days ago

• auditing-warehouse-view-health

  Audits materialized views in a PostHog data warehouse to identify failed views and flag unused ones that waste compute resources.

  Claude Code, Codex, Cursor +4 · about 1.4K tokens · pinned 6 days ago

• authoring-data-quality-checks

  This skill adds data quality checks (like dbt tests) on warehouse tables, views, and HogQL metrics, supporting assertions such as not-null, uniqueness…

  Claude Code, Codex, Cursor +4 · about 2.5K tokens · pinned 6 days ago

• authoring-scouts

  This skill helps engineers write, edit, and adapt PostHog Signals scouts, scheduled agents that scan projects and report findings to an inbox.

  Claude Code, Codex, Cursor +4 · about 10.6K tokens · pinned 6 days ago

• building-a-dashboard

  This skill constructs or modifies PostHog dashboards by selecting and arranging insight tiles.

  Claude Code, Codex, Cursor +4 · about 2.1K tokens · pinned 6 days ago

• configuring-experiment-analytics

  Configures how PostHog measures experiment impact by setting exposure criteria (who counts in the analysis), choosing metrics to track (mean, funnel, ratio…

  Claude Code, Codex, Cursor +4 · about 3.4K tokens · pinned 6 days ago

• configuring-experiment-rollout

  Configures variant split and overall rollout percentage for PostHog experiments, determining who sees which test variant and what percentage of users enter…

  Claude Code, Codex, Cursor +4 · about 3.6K tokens · pinned 6 days ago

• creating-replay-vision-scanners

  Guides agents through creating Replay Vision scanners, LLM probes that watch session recordings on a schedule and log findings as observations.

  Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago

• debugging-experiments

  Diagnoses A/B test results problems by pulling experiment data, matching symptoms to known causes (uneven exposures, missing traffic, identity fragmentation…

  Contains scripts

  Claude Code, Codex, Cursor +3 · about 5.2K tokens · pinned 6 days ago

• debugging-failed-data-quality-checks

  This skill debugs failed or errored data quality checks by examining their run history, displaying matching rows, and identifying root causes in either the…

  Claude Code, Codex, Cursor +4 · about 1.9K tokens · pinned 6 days ago

• designing-replay-vision-scanners

  This skill guides design of Replay Vision scanners that generate reliable observations by defining a focused question, selecting appropriate answer types…

  Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago

• diagnosing-experiment-health

  This skill diagnoses problems with a PostHog experiment's setup, exposures, results, and changes during its run.

  Claude Code, Codex, Cursor +4 · about 5.6K tokens · pinned 6 days ago

• exploring-llm-evaluations

  This skill enables agents to investigate, create, and manage AI observability evaluations in PostHog.

  Claude Code, Codex, Cursor +4 · about 5.6K tokens · pinned 6 days ago

• exploring-replay-vision-observations

  This skill guides agents through reading observations from Replay Vision scanners, understanding their findings across session recordings, and taking action…

  Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago

• exploring-scouts

  Explore and understand PostHog Signals scouts through read-only tools, examining fleet configuration, recent runs, performance metrics, and durable team…

  Contains scripts

  Claude Code, Codex, Cursor +3 · about 11K tokens · pinned 6 days ago

• finding-deleted-feature-flags

  This skill finds feature flags that were soft-deleted in a PostHog project within a specified time window, revealing who deleted each flag and when.

  Contains scripts

  Claude Code, Codex, Cursor +3 · about 1.8K tokens · pinned 6 days ago

• finding-experiments

  This skill resolves natural language references to PostHog experiments into concrete experiment IDs by searching the experiment-list tool.

  Claude Code, Codex, Cursor +4 · about 630 tokens · pinned 6 days ago

• investigating-replay

  Gathers session recording metadata, user profile, event timeline, and linked error issues in parallel to give a complete investigation when a user provides a…

  Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago

• managing-experiment-lifecycle

  Manages experiment lifecycle transitions including launching, pausing, resuming, ending, shipping variants, archiving, resetting, duplicating, copying to…

  Claude Code, Codex, Cursor +4 · about 4.5K tokens · pinned 6 days ago

• managing-streamlit-apps

  Manage Streamlit apps running in PostHog sandboxes through the full lifecycle: create, set or edit source code, start and stop the sandbox, poll status, and…

  Claude Code, Codex, Cursor +4 · about 1.4K tokens · pinned 6 days ago

• modeling-dimension-tables

  This skill builds reusable lookup tables (dimensions) like country, plan, and date for star-schema analytics on PostHog or dbt.

  Claude Code, Codex, Cursor +4 · about 1.1K tokens · pinned 6 days ago

• modeling-product-usage-metrics

  This skill helps build reusable product engagement models, retention, stickiness, and lifecycle, using either PostHog HogQL or dbt.

  Claude Code, Codex, Cursor +4 · about 1.1K tokens · pinned 6 days ago

• modeling-revenue-metrics

  Build revenue models for MRR, ARR, gross revenue, churn, ARPU, and LTV on PostHog managed revenue views or dbt marts.

  Claude Code, Codex, Cursor +4 · about 1.8K tokens · pinned 6 days ago

• querying-posthog-data

  This skill teaches the agent how to query PostHog data using typed runners for product analytics or SQL for complex analysis.

  Claude Code, Codex, Cursor +4 · about 4K tokens · pinned 6 days ago

• resolving-ingestion-warnings

  This skill diagnoses and resolves PostHog ingestion warnings that occur during event processing.

  Claude Code, Codex, Cursor +4 · about 6.8K tokens · pinned 6 days ago

• scanning-experiments-with-replay-vision

  Provisions a Replay Vision scanner targeted to an experiment's exposed sessions by setting experiment_targeting for server-side exposure filtering, templating…

  Claude Code, Codex, Cursor +4 · about 5.7K tokens · pinned 6 days ago

• setting-up-a-custom-rest-source

  Enables the agent to connect arbitrary REST APIs to PostHog's data warehouse by authoring a JSON manifest.

  Claude Code, Codex, Cursor +4 · about 2.8K tokens · pinned 6 days ago

• setting-up-data-catalog

  This skill populates and maintains a project's data catalog by creating canonical metrics, certifying trusted data sources, and documenting table relationships.

  Claude Code, Codex, Cursor +4 · about 2K tokens · pinned 6 days ago

• signals-scout-feature-flags

  This skill monitors PostHog feature flags for evaluation anomalies and cleanup opportunities.

  Claude Code, Codex, Cursor +3 · about 13.4K tokens · pinned 6 days ago

• signals-scout-general

  This skill operates as a cross-product Signals scout within PostHog, examining correlations across analytics features that specialized scouts do not cover…

  Claude Code, Codex, Cursor +3 · about 2.1K tokens · pinned 6 days ago

• signals-scout-inbox-validation

  This skill validates that merged fixes actually resolve the reported problems by re-measuring the underlying metrics after a soak period, attaches…

  Claude Code, Codex, Cursor +3 · about 8.4K tokens · pinned 6 days ago

• signals-scout-product-analytics

  This skill monitors product analytics behavioral flows (funnels, retention, lifecycle, stickiness, paths) for regressions in conversion or retention rates…

  Claude Code, Codex, Cursor +3 · about 6.2K tokens · pinned 6 days ago

• signals-scout-replay-vision

  This skill monitors PostHog Replay Vision scanners to detect when observation throughput drops unexpectedly and to surface aggregate patterns across sessions…

  Claude Code, Codex, Cursor +3 · about 7.9K tokens · pinned 6 days ago

• signals-scout-revenue-analytics

  This skill monitors PostHog's revenue analytics for upstream failures and configuration issues.

  Claude Code, Codex, Cursor +3 · about 5.6K tokens · pinned 6 days ago

• signals-scout-web-analytics

  This skill monitors PostHog web traffic for acquisition and site-health changes invisible in aggregate metrics.

  Claude Code, Codex, Cursor +3 · about 8.9K tokens · pinned 6 days ago

• triaging-visual-review-runs

  Inspects PostHog Visual Review screenshot regression runs that gate pull requests, helping engineers triage diff results, identify flaky stories, and decide…

  Claude Code, Codex, Cursor +4 · about 8.9K tokens · pinned 6 days ago

• authoring-scouts

  This skill teaches how to author, edit, and adapt PostHog Signals scouts: scheduled agents that scan projects and emit findings to an inbox.

  Claude Code, Codex, Cursor +4 · about 10.6K tokens · pinned 6 days ago

• configuring-experiment-analytics

  Configures how PostHog measures experiment impact by setting exposure criteria (which users count in analysis), choosing metric types (mean, funnel, ratio…

  Claude Code, Codex, Cursor +4 · about 3.4K tokens · pinned 6 days ago

• configuring-experiment-rollout

  Configures how PostHog experiment traffic is distributed across variants and what percentage of users enter the experiment.

  Claude Code, Codex, Cursor +4 · about 3.6K tokens · pinned 6 days ago

• creating-replay-vision-scanners

  This skill guides agents through creating Replay Vision scanners, which are standing LLM probes that automatically scan future session recordings on a…

  Claude Code, Codex, Cursor +4 · about 3.2K tokens · pinned 6 days ago

• exploring-llm-evaluations

  This skill investigates and manages AI observability evaluations in PostHog, covering three evaluation types: hog (code-based deterministic checks), llm_judge…

  Claude Code, Codex, Cursor +4 · about 5.5K tokens · pinned 6 days ago

• querying-posthog-data

  This skill teaches agents how to query PostHog data using typed tools for product analytics or SQL when needed.

  Claude Code, Codex, Cursor +4 · about 3.9K tokens · pinned 6 days ago

• resolving-ingestion-warnings

  This skill helps diagnose and fix PostHog ingestion warnings, events that are dropped, rejected, or modified during data ingestion.

  Claude Code, Codex, Cursor +4 · about 6.8K tokens · pinned 6 days ago

• signals-scout-inbox-validation

  This skill validates that merged fixes for resolved reports actually resolved the underlying problems.

  Claude Code, Codex, Cursor +3 · about 7.9K tokens · pinned 6 days ago

• signals-scout-product-analytics

  This skill monitors saved product-analytics behavioral flows, funnels, retention, lifecycle, stickiness, paths, and alerts when a flow's conversion rate…

  Claude Code, Codex, Cursor +3 · about 5.4K tokens · pinned 6 days ago

• triaging-visual-review-runs

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

  Claude Code, Codex, Cursor +4 · about 8.9K tokens · pinned 6 days ago

• authoring-scouts

  Write and adapt PostHog Signals scouts, scheduled agents that scan projects, detect issues, and file reports to the inbox on a configurable schedule.

  Claude Code, Codex, Cursor +4 · about 10.6K tokens · pinned 6 days ago

• configuring-experiment-analytics

  Configures how PostHog measures experiment impact by setting exposure criteria (which users count in results), adding or editing metrics to track outcomes…

  Claude Code, Codex, Cursor +4 · about 3.4K tokens · pinned 6 days ago

• querying-posthog-data

  This skill guides the agent on how to query PostHog analytics data using typed query tools or SQL, finding PostHog entities, and working with governed…

  Claude Code, Codex, Cursor +4 · about 4K tokens · pinned 6 days ago