Agent Skills
Instruction packs that give your AI agent know-how — some work anywhere, some only with the tool they came with.
✦ Standalone skills3,297
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons438
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
🔌 Needs setup first142
Each relies on something you set up separately — such as an app, a command-line tool or an account — and its page names what that is.
github · Development
1,553 standalone skills
error-tracking-svelte
★ 49by posthog
PostHog error tracking for Svelte
integration-expo
★ 49by posthog
PostHog integration for Expo applications
logs-datadog
★ 49by posthog
PostHog logs for Datadog
feature-flags-rust
★ 49by posthog
PostHog feature flags for Rust applications
integration-react-tanstack-router-code-based
★ 49by posthog
PostHog integration for React applications using TanStack Router with code-based routing
integration-fastapi
★ 49by posthog
PostHog integration for FastAPI applications
integration-flask
★ 49by posthog
PostHog integration for Flask applications
integration-python
★ 49by posthog
PostHog integration for any Python application using the Python SDK
auditing-experiments-flags
★ 49by posthog
Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.
omnibus-instrument-logs
★ 49by posthog
Add PostHog log capture to track application logs. Use after implementing features or reviewing PRs to ensure meaningful log events are captured with structured properties. Also handles initial OTLP exporter setup if not yet configured.
error-tracking-web
★ 49by posthog
PostHog error tracking for Web (JavaScript)
omnibus-instrument-integration
★ 49by posthog
Add PostHog SDK integration to your application. Use when setting up PostHog for the first time or reviewing PRs that need PostHog initialization. Covers SDK installation, provider setup, and basic configuration for any framework.
omnibus-instrument-error-tracking
★ 49by posthog
Add PostHog error tracking to capture and monitor exceptions. Use after implementing features or reviewing PRs to ensure errors are tracked with stack traces and source maps. Also handles initial PostHog SDK setup if not yet installed.
feature-flags-ruby
★ 49by posthog
PostHog feature flags for Ruby applications
feature-flags-go
★ 49by posthog
PostHog feature flags for Go applications
logs-python
★ 49by posthog
PostHog logs for Python
integration-vue-3
★ 49by posthog
PostHog integration for Vue 3 applications
integration-react-react-router-7-declarative
★ 49by posthog
PostHog integration for React Router v7 - Declarative mode applications
integration-nuxt-3.6
★ 49by posthog
PostHog integration for Nuxt versions 3.0 to 3.6
integration-nextjs-pages-router
★ 49by posthog
PostHog integration for Next.js Pages Router applications
integration-laravel
★ 49by posthog
PostHog integration for Laravel applications
integration-javascript_web
★ 49by posthog
PostHog integration for client-side web JavaScript applications using posthog-js
integration-javascript_node
★ 49by posthog
PostHog integration for server-side Node.js applications using posthog-node
integration-django
★ 49by posthog
PostHog integration for Django applications
integration-astro-view-transitions
★ 49by posthog
PostHog integration for Astro with ClientRouter view transitions
integration-nextjs-app-router
★ 49by posthog
PostHog integration for Next.js App Router applications
error-tracking-react-native
★ 49by posthog
PostHog error tracking for React Native
error-tracking-nuxt
★ 49by posthog
PostHog error tracking for Nuxt
feature-flags-python
★ 49by posthog
PostHog feature flags for Python applications
exploring-llm-traces
★ 49by posthog
Debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.