Skip to main content
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

exploring-ai-failures skill exploring-ai-failures reads real production traces from PostHog and returns a ranked list of the ways your LLM feature breaks. CX Codex +1 198installs exploring-llm-evaluations skill exploring-llm-evaluations — a skill for working with PostHog AI observability evaluations: find configs, run them against specific generations, and schedule reports. CX Codex +1 440installs exploring-llm-clusters skill exploring-llm-clusters is a Claude Code skill that explores PostHog clusters of AI and LLM traffic, compares groups, calculates metrics, and inspects traces. CX Codex +1 436installs resolving-ingestion-warnings skill resolving-ingestion-warnings walks through PostHog ingestion warnings: dropped events, rejected person merges, oversized payloads. Use it when event counts look low or identify calls misbehave. CX Codex +1 197installs exploring-scouts skill exploring-scouts reads the state of PostHog Signals scouts: which ones a project has, how recent runs went, and where their reports ended up. Read-only. CX Codex +1 197installs creating-experiments skill 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. CX Codex +1 431installs diagnosing-missing-recordings skill diagnosing-missing-recordings diagnoses why PostHog session replays were not captured. It parses SDK diagnostic signals via SQL queries to isolate the exact cause. CX Codex +1 428installs debugging-surveys skill debugging-surveys investigates why PostHog Surveys fail to appear or record complete answers. Useful for support cases involving targeting, SDK behavior, and stored responses. CX Codex +1 197installs authoring-scouts skill 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. CX Codex +1 196installs signals skill signals guides agents in querying PostHog's document_embeddings table with HogQL to fetch raw product observations and vector embeddings. CX Codex +1 427installs investigating-replay skill investigating-replay gathers PostHog session replay metadata, user profiles, timeline events, and linked error tracking issues into a single report. Useful when debugging issues by session ID. CX Codex +1 424installs creating-online-evaluations skill creating-online-evaluations — a Claude Code skill that turns production failure modes into continuously-running online evaluations in PostHog. It starts when new generations need automatic scoring against specific errors. CX Codex +1 195installs signals-scout-insight-alerts skill signals-scout-insight-alerts — a Claude Code skill for reviewing insight alert history in PostHog. It scans recent alert triggers and flags material incidents that missed notifying the team. CX Codex +1 195installs configuring-experiment-rollout skill 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%". CX Codex +1 418installs exploring-llm-costs skill exploring-llm-costs is a Claude Code skill that investigates LLM spend in PostHog by model, user, trace, and other dimensions. It responds to cost-spike questions and requests for charts or alerts. CX Codex +1 416installs signals-scout-data-warehouse skill 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. CX Codex +1 195installs signals-scout-mcp-tool-calls skill 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. CX Codex +1 194installs feature-usage-feed skill feature-usage-feed builds an LLM-judge eval that pulls canonical use cases for a PostHog feature and streams them to Slack. Useful when trace volume is too high to read by hand. CX Codex +1 410installs managing-experiment-lifecycle skill The managing-experiment-lifecycle skill guides experiment state changes, from launch and pausing to exposure freezes, archiving, resets, and migration to the newer engine. CX Codex +1 408installs signals-scout-web-vitals skill 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. CX Codex +1 194installs signals-scout-skills-store skill signals-scout-skills-store audits shared PostHog agent skills for vague descriptions, oversized bodies, broken links, and leaked secrets. Produces reports with copy-ready fixes. CX Codex +1 193installs finding-replay-for-issue skill 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. CX Codex +1 407installs finding-experiments skill finding-experiments resolves loose names, statuses, or relative dates into concrete PostHog experiment IDs. It saves users from digging up raw numeric IDs manually. CX Codex +1 407installs analyzing-expensive-users skill 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. CX Codex +1 192installs turning-engineering-analytics-into-insights skill 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. Triggers when visualizing engineering team performance. CX Codex +1 189installs setting-up-a-data-warehouse-source skill setting-up-a-data-warehouse-source connects databases, cloud storage buckets, and SaaS tools to PostHog's data warehouse. Handles credential verification, table discovery, and sync modes. CX Codex +1 405installs inbox-exploration skill inbox-exploration — a Claude Code skill that reads clustered incident reports from PostHog Inbox and links fixes directly to open issues. CX Codex +1 401installs investigating-logs skill The investigating-logs Claude Code skill investigates logs in a PostHog project, checks service health and traces error spikes. It runs for deploy checks, incident triage, change analysis, or a search around one trace or run. CX Codex +1 188installs investigating-ci-failures skill The investigating-ci-failures Claude Code skill traces an individual CI failure to its likely cause. It separates PR-specific problems from default-branch breaks and flaky tests. CX Codex +1 188installs suggesting-data-imports skill The suggesting-data-imports skill suggests importing external data into PostHog when a query lacks tables for payments, subscriptions, CRM records, or bucket files. CX Codex +1 401installs diagnosing-failed-warehouse-syncs skill The diagnosing-failed-warehouse-syncs Claude Code skill investigates failed warehouse syncs and suggests a recovery action. It activates for reports of stuck tables, source errors, or incorrect warehouse data. CX Codex +1 401installs review-hog-validation-criteria skill review-hog-validation-criteria serves as a final PR review gate, filtering candidate findings to keep real defects while discarding speculative noise. CX Codex +1 187installs review-hog-blind-spots-general skill The review-hog-blind-spots-general skill looks for concrete problems that earlier reviewers missed in a PR chunk. Use it as a final pass after other review perspectives have reported their findings. CX Codex +1 187installs tuning-incremental-sync-config skill tuning-incremental-sync-config updates sync settings on existing PostHog warehouse schemas, including sync types, incremental keys, CDC modes, and refresh intervals. CX Codex +1 399installs triaging-visual-review-runs skill triaging-visual-review-runs investigates PostHog Visual Review status checks on pull requests and distinguishes legitimate UI regressions from flaky Storybook snapshots. CX Codex +1 398installs review-hog-authoring skill 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. CX Codex +1 187installs review-hog-perspective-contracts-security skill review-hog-perspective-contracts-security is a Claude Code skill that checks code changes for security flaws and API compatibility breaks. It reports contract and security findings during PR review. CX Codex +1 187installs copying-flags-across-projects skill copying-flags-across-projects moves a PostHog feature flag from one project to other projects in the same organization. Use it for staging-to-production promotion or project-level flag syncing. CX Codex +1 392installs exploring-apm-traces skill The exploring-apm-traces Claude Code skill examines OpenTelemetry traces through PostHog APM. It helps investigate slow HTTP or database spans, errors, and latency changes. CX Codex +1 387installs review-hog-perspective-performance-reliability skill The review-hog-perspective-performance-reliability skill reviews code for performance and reliability concerns, from database access to error recovery. Use it when checking a change before it ships. CX Codex +1 187installs

41–80 of 195

More in NeVibeCode

Project sponsors

Companies that keep this analytics open