NeVibeCode · author · 195 items
posthog: skills, plugins and MCP servers
Every card from posthog repositories on GitHub: what each one does, an install command and example prompts. Inside: 193 skills, 1 MCP server and 1 plugin. They install into Claude Code, Codex and Cursor.
Repositories3
- posthog/skills 112 · ★ 80
- posthog/ai-plugin 82 · ★ 101
- posthog/posthog 1
PostHog MCP Server MCP server Connects PostHog analytics and feature flag management to AI assistants via Streamable HTTP.
CX Codex +1
★ 41,008repo stars
instrument-product-analytics skill The instrument-product-analytics Claude Code skill adds PostHog events to product code. Run it after building a feature or reviewing a PR; it can also set up the SDK when the project lacks it.
CX Codex +1
912installs
querying-posthog-data skill querying-posthog-data — a skill that tells your agent how to query PostHog: typed runners for product analytics, HogQL/SQL when the task actually needs it.
CX Codex +1
890installs
authoring-error-tracking-alerts skill authoring-error-tracking-alerts guides your agent in configuring PostHog error tracking notifications, selecting lifecycle triggers, and connecting them to Slack or webhooks.
CX Codex +1
209installs
building-a-dashboard skill building-a-dashboard — a skill for Claude Code, Codex, and Cursor that builds and updates PostHog dashboards via MCP tools. Coordinates insight reuse and grid layout.
CX Codex +1
208installs
instrument-integration skill The instrument-integration Claude Code skill integrates the PostHog SDK into an application and configures it for the detected framework. It runs during a first-time PostHog setup or when reviewing a PR that needs initialization.
CX Codex +1
761installs
instrument-feature-flags skill instrument-feature-flags — a Claude Code skill that gates new functionality with PostHog feature flags. Runs after implementing features or during PR reviews to safeguard rollouts.
CX Codex +1
630installs
filtering-bot-traffic skill filtering-bot-traffic splits human traffic from bots and AI crawlers in PostHog. Use it to clean a metric or to see how much of the traffic runs on autopilot.
CX Codex +1
208installs
investigating-metric-anomalies skill investigating-metric-anomalies turns a PostHog Metrics symptom (rising lag, error spike, falling throughput) into a probable cause backed by logs and traces.
CX Codex +1
206installs
instrument-llm-analytics skill The instrument-llm-analytics Claude Code skill adds PostHog AI Observability to track language-model calls. Run it after building LLM features or while reviewing a PR.
CX Codex +1
615installs
instrument-error-tracking skill The instrument-error-tracking Claude Code skill configures PostHog exception tracking. Run it after adding a feature or reviewing a PR to instrument errors.
CX Codex +1
546installs
choosing-trend-or-slope-view skill choosing-trend-or-slope-view — a skill that settles what “change over time” means before a chart gets built: the full trend interval by interval, or only the gap between the two ends.
CX Codex +1
204installs
auditing-warehouse-source-health skill auditing-warehouse-source-health audits PostHog data warehouse sources and syncs to pinpoint broken connectors, failed schemas, and degraded webhooks.
CX Codex +1
204installs
configuring-experiment-analytics skill The configuring-experiment-analytics Claude Code skill configures analytics for PostHog experiments. It sets exposure criteria and metrics, then helps interpret experiment results.
CX Codex +1
425installs
managing-subscriptions skill managing-subscriptions configures recurring PostHog reports for insights and dashboards sent to Slack, Teams, or email. Handles schedules, test dispatches, and delivery troubleshooting.
CX Codex +1
531installs
signals-scout-product-analytics skill signals-scout-product-analytics — a skill for Claude Code and Codex monitoring core product analytics flows in PostHog. Detects derived-rate regressions across funnels and retention while entrant volume holds steady.
CX Codex +1
204installs
auditing-warehouse-view-health skill auditing-warehouse-view-health runs a project-wide check on PostHog materialized views: lists the ones that failed to refresh and points at materialized views nobody queries.
CX Codex +1
204installs
diagnosing-sdk-health skill diagnosing-sdk-health finds outdated PostHog SDKs in your project and tells you how to fix them. Handy when events or features start acting up.
CX Codex +1
523installs
investigate-metric skill investigate-metric — a skill for Claude Code that diagnoses why product metrics dropped, spiked, or plateaued in PostHog. It triggers on anomaly questions or requests to walk through a dashboard chart.
CX Codex +1
505installs
building-workflows skill building-workflows is a Claude Code skill for building, patching, and testing PostHog automation graphs over MCP before publishing them in the visual editor.
CX Codex +1
204installs
exploring-replay-vision-observations skill The exploring-replay-vision-observations skill guides an agent through Replay Vision scanner results, from recurring patterns to individual session recordings. Use it to review findings and decide what to investigate next.
CX Codex +1
203installs
instrument-logs skill The instrument-logs Claude Code skill adds application log capture in PostHog with structured properties. Run it after implementing a feature or reviewing a PR; it can also set up OTLP export when none exists.
CX Codex +1
490installs
exploring-autocapture-events skill exploring-autocapture-events guides exploration of $autocapture data from posthog-js. It helps agents find resilient CSS selectors, inspect click uniqueness, and build action filters.
CX Codex +1
470installs
signals-scout-customer-analytics skill The signals-scout-customer-analytics skill tracks account-level engagement in PostHog and spots churn-risk or expansion patterns. Use it for recurring customer-health checks.
CX Codex +1
203installs
exploring-mcp-sessions skill exploring-mcp-sessions investigates PostHog MCP sessions to inspect tool call sequences, agent intent, and run failures.
CX Codex +1
202installs
exploring-live-traffic skill exploring-live-traffic — a skill that teaches the agent to read PostHog's Live tab: who is on the site right now, which bots are crawling, and where visitors go.
CX Codex +1
469installs
cleaning-up-stale-feature-flags skill cleaning-up-stale-feature-flags finds stale feature flags in a PostHog project and removes the code that checks them. Useful when flags pile up and you need to know which ones can go.
CX Codex +1
466installs
exploring-mcp-tool-quality skill exploring-mcp-tool-quality reads PostHog MCP analytics to rank tools by failure share, latency and reach, then drills into the ones that break.
CX Codex +1
202installs
exploring-mcp-intent-clusters skill exploring-mcp-intent-clusters analyzes PostHog MCP agent intent clusters to reveal what agents attempt to do, tool failure patterns, and semantic routing competition.
CX Codex +1
202installs
analyzing-experiment-session-replays skill analyzing-experiment-session-replays guides coding agents through reviewing PostHog session recordings across experiment variants to spot UX flaws and understand user differences.
CX Codex +1
463installs
auditing-experiments-flags skill auditing-experiments-flags runs configuration audits on PostHog experiments and feature flags, flagging staleness and best-practice violations. Useful before you trust an A/B test result.
CX Codex +1
462installs
managing-reminders skill managing-reminders is a Claude Code skill that creates and manages private PostHog reminders with one-time or repeating schedules. It can nudge you about a task or resource.
CX Codex +1
202installs
signals-scout-apm skill signals-scout-apm watches OpenTelemetry traces in PostHog for error-rate and latency shifts per service, new error signatures and traffic drops, and files a report only on a confirmed change.
CX Codex +1
202installs
skills-store skill Discovers, loads, and manages shared team skills stored in PostHog. Helpful when agents need to fetch workflows and bundled scripts on demand.
CX Codex +1
449installs
formatting-insight-axes skill formatting-insight-axes picks the right y-axis unit when you create or update a PostHog insight: seconds, milliseconds, percentages, currency. Stops the agent from adding formulas just to convert units.
CX Codex +1
444installs
exploring-mcp-tool-usage skill exploring-mcp-tool-usage — a routing skill for PostHog MCP analytics: it offers a menu of questions about tool calls, then hands you to the query that answers it.
CX Codex +1
200installs
checking-deploy-timing skill checking-deploy-timing tells you when a commit or PR reached prod-us or prod-eu by reading PostHog's hidden deploy annotations and matching them against the merge commit on GitHub.
CX Codex +1
200installs
managing-path-cleaning-rules skill managing-path-cleaning-rules guides agents in auditing fragmented PostHog URL paths, writing re2 normalization rules, and collapsing dynamic IDs into clean aliases.
CX Codex +1
444installs
exploring-llm-traces skill exploring-llm-traces is a Claude Code skill that investigates LLM agent traces through PostHog MCP tools. It activates for trace or session links and questions about errors, tool calls, context, tokens, or cost.
CX Codex +1
440installs
setting-up-a-custom-rest-source skill setting-up-a-custom-rest-source — a skill for Claude Code and Codex that links arbitrary REST APIs to the PostHog data warehouse using a JSON manifest. Activates when importing custom endpoints without native connectors.
CX Codex +1
199installs
1–40 of 195