The master skill in PlanetScale's official pack: runs a full read-only best-practices assessment of a database or org, then produces one evidence-backed report.
Sentry SDK SetupSkill
Summary
Sentry's official router skill: detects your language or framework, then loads the matching Sentry SDK setup guide for error monitoring, tracing and session replay.
Features
- Detects the project's language or framework before installing anything
- Routes to one of 20+ platform-specific Sentry SDK setup skills
- Covers error monitoring, tracing and session replay configuration
- Served over HTTP at skills.sentry.dev for direct agent fetching
Install This Skill
Add this skill to your favorite AI agent in a few steps.
Skill Content
Usage Instructions
Learn how to use this skill with different AI agents.
Example Usage
Add Sentry to my Next.js app
Description
Sentry's own skill for getting Sentry into a project correctly the first time. It is a router: it inspects the project files, works out which platform you are on, tells you which SDK it recommends, and waits for confirmation before loading the dedicated SDK skill and installing anything.
That structure matters. Sentry ships more than twenty platform-specific setup skills — Next.js, Node, browser JavaScript, React, React Native, NestJS, Python, PHP, Ruby, Go, .NET, Elixir, Android, Apple/Cocoa, Flutter, Svelte, Cloudflare Workers and more — each with its own prerequisites, config file layout and integration list. A single generic "add Sentry" prompt produces plausible-looking but wrong wiring surprisingly often; the router avoids that by confirming the platform before any package is installed.
The skill explicitly instructs the agent not to guess from project files alone, not to start writing config before the user confirms, and to follow the chosen SDK skill rather than improvising. Sentry serves the whole tree over HTTP at skills.sentry.dev, so agents can fetch each SKILL.md directly instead of vendoring the repository.
Useful when you are adding error monitoring, tracing or session replay to an existing codebase and want the DSN, the instrumentation hooks and the source-map upload configured the way Sentry actually documents them.
Related Skills
Build crash-safe AI agents on AgentKit and step.ai — durable tool calls, human-in-the-loop approval, realtime progress, and when not to reach for an agent loop at all.
Inngest's durable-execution playbook as an agent skill — steps and memoisation, event and cron triggers, idempotency, cancellation, retries and non-retriable errors.
Temporal's official skill for building durable workflows — SDK patterns across seven languages, plus the determinism rules that decide whether a workflow survives a replay.