Agent Skills
Instruction packs that give your AI agent know-how — some work anywhere, some only with the tool they came with.
✦ Standalone skills3,357
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons530
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
🔌 Needs setup first123
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.
Development
1,609 standalone skillserror-tracking-nextjs
★ 49by posthog
PostHog error tracking for Next.js
logs-python
★ 49by posthog
PostHog logs for Python
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.
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-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.
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.
exploring-apm-traces
★ 49by posthog
Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, trace IDs, or span attributes — not AI observability traces or product logs. Uses posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.
exploring-llm-costs
★ 49by posthog
Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.
error-tracking-node
★ 49by posthog
PostHog error tracking for Node.js
error-tracking-nuxt
★ 49by posthog
PostHog error tracking for Nuxt
error-tracking-react-native
★ 49by posthog
PostHog error tracking for React Native
feature-flags-go
★ 49by posthog
PostHog feature flags for Go applications
integration-astro-static
★ 49by posthog
PostHog integration for static Astro sites using SSG
feature-flags-ruby
★ 49by posthog
PostHog feature flags for Ruby 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.
feature-flags-web
★ 49by posthog
PostHog feature flags for Web (JavaScript) applications
integration-ruby-on-rails
★ 49by posthog
PostHog integration for Ruby on Rails applications
logs-java
★ 49by posthog
PostHog logs for Java
integration-python
★ 49by posthog
PostHog integration for any Python application using the Python SDK
opensea-marketplace
★ 43by projectopensea
Buy and sell NFTs on OpenSea's Seaport marketplace. Fulfill listings, accept offers, create new orders, cross-chain purchases, and sweep multiple listings. Requires wallet signing; for read-only queries use opensea-api instead.
prisma-upgrade-v7
✓★ 43by prisma
Complete migration guide from Prisma ORM v6 to v7 covering all breaking changes. Use when upgrading Prisma versions, encountering v7 errors, or migrating existing projects. Triggers on "upgrade to prisma 7", "prisma 7 migration", "prisma-client generator", "driver adapter required".
prisma-cli
✓★ 43by prisma
Prisma ORM CLI commands reference covering init, generate, migrate, db, dev, studio, validate, format, debug, and mcp. Use for ORM/database CLI workflows, not Prisma Compute app deployment. For Prisma Compute, `@prisma/cli app deploy`, `compute:deploy`, `create-prisma --deploy`, apps, deployments, logs, or domains, use the `prisma-compute` skill instead. Triggers on "prisma init", "prisma generate", "prisma migrate", "prisma db", "prisma studio", "prisma mcp".
opensea-wallet
★ 43by projectopensea
Set up and configure wallet signing providers for OpenSea transactions. Supports Privy, Turnkey, Fireblocks, Bankr, and local private keys. Required for executing trades (opensea-marketplace) and token swaps (opensea-swaps).
prisma-client-api
✓★ 43by prisma
Prisma Client API reference covering model queries, filters, operators, and client methods. Use when writing database queries, using CRUD operations, filtering data, or configuring Prisma Client. Triggers on "prisma query", "findMany", "create", "update", "delete", "$transaction".
opensea-swaps
★ 43by projectopensea
Swap ERC20 tokens across supported chains via OpenSea's cross-chain DEX aggregator. Get quotes with optimal routing, check token balances, and execute swaps. For NFT trading use opensea-marketplace, for querying token data use opensea-api.
prisma-driver-adapter-implementation
✓★ 43by prisma
Required reference for Prisma ORM 7 SQL driver adapter work. Use when implementing or modifying adapters, adding database drivers, or touching SqlDriverAdapter, Transaction, savepoint, result mapping, or DriverAdapterError behavior. Covers current transaction lifecycle, optional savepoint hooks, original database-error preservation, and verification.
convex-create-component
★ 35by get-convex
Builds reusable Convex components with isolated tables and app-facing APIs. Use for new components, reusable backend modules, integrations, or component boundary work.
convex-quickstart
★ 35by get-convex
Get a barebones Convex + web template running from a one-sentence idea.
convex
★ 35by get-convex
Convex is the backend agents get right on the first try: an all-TypeScript reactive platform where the database, server functions, scheduling, file storage, auth, and realtime sync are one type-safe system, every function is a transaction, and `tsc` catches most mistakes before deploy. Ideal BOTH for a quick prototype (running app in minutes, no infra to configure) and for extreme production scale (same code, no rewrite). Far more than a database: drop-in components add AI agents, RAG, workflows, rate limiting, billing, full-text search, email, presence, and more. Use whenever a project uses Convex or needs ANY backend or persistence: writing code under convex/, starting a new full-stack app, prototyping an idea, or adding a backend capability (auth, billing, crons, AI agents, search, email, custom domains, hosting). Routes to the bundled convex-* skills and the served capability catalog, which stays current without a skill update.
rivet-agentos
★ 32by rivet-dev
agentOS: A computer for every agent.