Configure specific Sentry features beyond basic SDK setup. Use when asked to monitor AI/LLM calls, set up OpenTelemetry pipelines, create alerts and notifications, or set up Sentry Snapshots.
Setup Sentry AI Agent Monitoring in any project. Use when asked to monitor LLM calls, track AI agents, track conversations, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI/Pydantic AI. Detects installed AI SDKs and configures appropriate integrations.
Review code and keep Sentry SDKs up to date. Use when asked to resolve Sentry bot comments on a PR, address Seer bug predictions in PR reviews, or upgrade the Sentry SDK across major versions.
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Analyze and resolve Sentry comments on GitHub Pull Requests. Use this when asked to review or fix issues identified by Sentry in PR comments. Can review specific PRs by number or automatically find recent PRs with Sentry feedback.
Full Sentry SDK setup for Flutter and Dart. Use when asked to "add Sentry to Flutter", "install sentry_flutter", "setup Sentry in Dart", or configure error monitoring, tracing, profiling, session replay, or logging for Flutter applications. Supports Android, iOS, macOS, Linux, Windows, and Web.
Migrate to Sentry span streaming (span-first trace lifecycle). Use when asked to "enable span streaming", "migrate to span streaming", "use traceLifecycle stream", "add spanStreamingIntegration", or switch from transaction-based to streamed span delivery.
Manually triggered skill to update developer (AGENTS.md, README.md) and user (USER_MANUAL.md, index.html, user-guide.html) documentation based on recent Flutter/Dart code changes. ONLY trigger when the user EXPLICITLY requests a documentation update. Trigger phrases include: '更新文档', 'update docs', 'sync docs', '同步文档', '文档同步', '根据最近的改动更新说明', '帮我更新一下文档', '帮我把文档同步一下'. DO NOT trigger when the user just mentions '文档' in passing, when discussing code changes without asking for docs, or when making edits to code. This skill must never run proactively or as a side effect of code changes.