# 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.

195 cards · page 2 of 5

- HTML: https://affpapa.org/en/nevibecode/by/posthog?page=2
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [exploring-ai-failures](https://affpapa.org/en/nevibecode/skills/exploring-ai-failures.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 198 installs — exploring-ai-failures reads real production traces from PostHog and returns a ranked list of the ways your LLM feature breaks.
- [exploring-llm-evaluations](https://affpapa.org/en/nevibecode/skills/exploring-llm-evaluations.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 440 installs — exploring-llm-evaluations — a skill for working with PostHog AI observability evaluations: find configs, run them against specific generations, and schedule reports.
- [exploring-llm-clusters](https://affpapa.org/en/nevibecode/skills/exploring-llm-clusters.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 436 installs — exploring-llm-clusters is a Claude Code skill that explores PostHog clusters of AI and LLM traffic, compares groups, calculates metrics, and inspects traces.
- [resolving-ingestion-warnings](https://affpapa.org/en/nevibecode/skills/resolving-ingestion-warnings.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 197 installs — resolving-ingestion-warnings walks through PostHog ingestion warnings: dropped events, rejected person merges, oversized payloads.
- [exploring-scouts](https://affpapa.org/en/nevibecode/skills/exploring-scouts.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 197 installs — exploring-scouts reads the state of PostHog Signals scouts: which ones a project has, how recent runs went, and where their reports ended up.
- [creating-experiments](https://affpapa.org/en/nevibecode/skills/creating-experiments.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 431 installs — creating-experiments walks an agent through creating an A/B test: reads the project's setup, drafts the hypothesis, picks rollout and metrics, and flags its guesses.
- [diagnosing-missing-recordings](https://affpapa.org/en/nevibecode/skills/diagnosing-missing-recordings.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 428 installs — diagnosing-missing-recordings diagnoses why PostHog session replays were not captured.
- [debugging-surveys](https://affpapa.org/en/nevibecode/skills/debugging-surveys.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 197 installs — debugging-surveys investigates why PostHog Surveys fail to appear or record complete answers.
- [authoring-scouts](https://affpapa.org/en/nevibecode/skills/authoring-scouts.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 196 installs — authoring-scouts is a Claude Code skill for creating, tuning, and testing PostHog Signals scouts that inspect project metrics on a schedule and submit findings.
- [signals](https://affpapa.org/en/nevibecode/skills/signals.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 427 installs — signals guides agents in querying PostHog's document_embeddings table with HogQL to fetch raw product observations and vector embeddings.
- [investigating-replay](https://affpapa.org/en/nevibecode/skills/investigating-replay.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 424 installs — investigating-replay gathers PostHog session replay metadata, user profiles, timeline events, and linked error tracking issues into a single report.
- [creating-online-evaluations](https://affpapa.org/en/nevibecode/skills/creating-online-evaluations.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 195 installs — creating-online-evaluations — a Claude Code skill that turns production failure modes into continuously-running online evaluations in PostHog.
- [signals-scout-insight-alerts](https://affpapa.org/en/nevibecode/skills/signals-scout-insight-alerts.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 195 installs — signals-scout-insight-alerts — a Claude Code skill for reviewing insight alert history in PostHog.
- [configuring-experiment-rollout](https://affpapa.org/en/nevibecode/skills/configuring-experiment-rollout.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 418 installs — configuring-experiment-rollout — a skill that helps the agent set variant splits and rollout percentages for PostHog experiments, and disambiguate vague requests like "roll out to 25%".
- [exploring-llm-costs](https://affpapa.org/en/nevibecode/skills/exploring-llm-costs.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 416 installs — exploring-llm-costs is a Claude Code skill that investigates LLM spend in PostHog by model, user, trace, and other dimensions.
- [signals-scout-data-warehouse](https://affpapa.org/en/nevibecode/skills/signals-scout-data-warehouse.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 195 installs — signals-scout-data-warehouse monitors warehouse imports for failures, stale data, and sharp row-count drops, then flags recurring query patterns that may merit materialized views.
- [signals-scout-mcp-tool-calls](https://affpapa.org/en/nevibecode/skills/signals-scout-mcp-tool-calls.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 194 installs — signals-scout-mcp-tool-calls — a PostHog Signals skill that sifts $mcp_tool_call telemetry for MCP tools agents struggle with, then files one report per product category.
- [feature-usage-feed](https://affpapa.org/en/nevibecode/skills/feature-usage-feed.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 410 installs — feature-usage-feed builds an LLM-judge eval that pulls canonical use cases for a PostHog feature and streams them to Slack.
- [managing-experiment-lifecycle](https://affpapa.org/en/nevibecode/skills/managing-experiment-lifecycle.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 408 installs — The managing-experiment-lifecycle skill guides experiment state changes, from launch and pausing to exposure freezes, archiving, resets, and migration to the newer engine.
- [signals-scout-web-vitals](https://affpapa.org/en/nevibecode/skills/signals-scout-web-vitals.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 194 installs — signals-scout-web-vitals tracks page p75 LCP, INP, CLS, and FCP from PostHog events, spots performance degradation against Google thresholds, and links regressions to deploys.
- [signals-scout-skills-store](https://affpapa.org/en/nevibecode/skills/signals-scout-skills-store.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 193 installs — signals-scout-skills-store audits shared PostHog agent skills for vague descriptions, oversized bodies, broken links, and leaked secrets.
- [finding-replay-for-issue](https://affpapa.org/en/nevibecode/skills/finding-replay-for-issue.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 407 installs — finding-replay-for-issue picks the session recording that actually shows what the user did before an error, instead of guessing among hundreds of linked sessions.
- [finding-experiments](https://affpapa.org/en/nevibecode/skills/finding-experiments.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 407 installs — finding-experiments resolves loose names, statuses, or relative dates into concrete PostHog experiment IDs.
- [analyzing-expensive-users](https://affpapa.org/en/nevibecode/skills/analyzing-expensive-users.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 192 installs — analyzing-expensive-users — a skill for Claude Code, Codex, Cursor and other agents that finds the top spenders in PostHog AI observability and explains what drives their costs.
- [turning-engineering-analytics-into-insights](https://affpapa.org/en/nevibecode/skills/turning-engineering-analytics-into-insights.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 189 installs — turning-engineering-analytics-into-insights — a skill for Claude Code and Codex: converts PR and CI metrics into saved PostHog insights, dashboards, and automated subscriptions.
- [setting-up-a-data-warehouse-source](https://affpapa.org/en/nevibecode/skills/setting-up-a-data-warehouse-source.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 405 installs — setting-up-a-data-warehouse-source connects databases, cloud storage buckets, and SaaS tools to PostHog's data warehouse.
- [inbox-exploration](https://affpapa.org/en/nevibecode/skills/inbox-exploration.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 401 installs — inbox-exploration — a Claude Code skill that reads clustered incident reports from PostHog Inbox and links fixes directly to open issues.
- [investigating-logs](https://affpapa.org/en/nevibecode/skills/investigating-logs.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 188 installs — The investigating-logs Claude Code skill investigates logs in a PostHog project, checks service health and traces error spikes.
- [investigating-ci-failures](https://affpapa.org/en/nevibecode/skills/investigating-ci-failures.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 188 installs — The investigating-ci-failures Claude Code skill traces an individual CI failure to its likely cause.
- [suggesting-data-imports](https://affpapa.org/en/nevibecode/skills/suggesting-data-imports.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 401 installs — The suggesting-data-imports skill suggests importing external data into PostHog when a query lacks tables for payments, subscriptions, CRM records, or bucket files.
- [diagnosing-failed-warehouse-syncs](https://affpapa.org/en/nevibecode/skills/diagnosing-failed-warehouse-syncs.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 401 installs — The diagnosing-failed-warehouse-syncs Claude Code skill investigates failed warehouse syncs and suggests a recovery action.
- [review-hog-validation-criteria](https://affpapa.org/en/nevibecode/skills/review-hog-validation-criteria.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 187 installs — review-hog-validation-criteria serves as a final PR review gate, filtering candidate findings to keep real defects while discarding speculative noise.
- [review-hog-blind-spots-general](https://affpapa.org/en/nevibecode/skills/review-hog-blind-spots-general.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 187 installs — The review-hog-blind-spots-general skill looks for concrete problems that earlier reviewers missed in a PR chunk.
- [tuning-incremental-sync-config](https://affpapa.org/en/nevibecode/skills/tuning-incremental-sync-config.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 399 installs — tuning-incremental-sync-config updates sync settings on existing PostHog warehouse schemas, including sync types, incremental keys, CDC modes, and refresh intervals.
- [triaging-visual-review-runs](https://affpapa.org/en/nevibecode/skills/triaging-visual-review-runs.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 398 installs — triaging-visual-review-runs investigates PostHog Visual Review status checks on pull requests and distinguishes legitimate UI regressions from flaky Storybook snapshots.
- [review-hog-authoring](https://affpapa.org/en/nevibecode/skills/review-hog-authoring.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 187 installs — review-hog-authoring — a guide skill for writing custom PostHog Review pieces: extra PR perspectives, your own blind-spot sweep, and the bars that decide what gets published or fixed.
- [review-hog-perspective-contracts-security](https://affpapa.org/en/nevibecode/skills/review-hog-perspective-contracts-security.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 187 installs — review-hog-perspective-contracts-security is a Claude Code skill that checks code changes for security flaws and API compatibility breaks.
- [copying-flags-across-projects](https://affpapa.org/en/nevibecode/skills/copying-flags-across-projects.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 392 installs — copying-flags-across-projects moves a PostHog feature flag from one project to other projects in the same organization.
- [exploring-apm-traces](https://affpapa.org/en/nevibecode/skills/exploring-apm-traces.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 387 installs — The exploring-apm-traces Claude Code skill examines OpenTelemetry traces through PostHog APM.
- [review-hog-perspective-performance-reliability](https://affpapa.org/en/nevibecode/skills/review-hog-perspective-performance-reliability.md) — skill · PostHog · Claude Code, Codex, Cursor +5 · 187 installs — The review-hog-perspective-performance-reliability skill reviews code for performance and reliability concerns, from database access to error recovery.

Next: https://affpapa.org/en/nevibecode/by/posthog.md?page=3

## Sets by this author
- [posthog/skills](https://affpapa.org/en/nevibecode/by/posthog/skills.md) — 112
- [posthog/ai-plugin](https://affpapa.org/en/nevibecode/by/posthog/ai-plugin.md) — 82
- [posthog/posthog](https://affpapa.org/en/nevibecode/by/posthog/posthog.md) — 1

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
