Post-processing layer for browser-trace that turns captured network traffic into OpenAPI 3.1 specs. You run browser-trace to capture CDP events, optionally snapshot response bodies with browse network on, then this parses the JSONL buckets to pair requests with responses, templatize URLs, and infer JSON schemas from observed samples. The HTML report it generates is genuinely useful, each endpoint gets an expandable card with curl examples and a typed client snippet. Built-in noise filtering drops tracking pixels and bot defense junk automatically. It even decomposes multiplexed GraphQL endpoints by operationName. The two-step workflow is clean: capture traffic however you want, then run discover.mjs offline. Best for reverse engineering undocumented APIs or building clients against third-party sites that don't publish specs.
npx skills add https://github.com/browserbase/skills --skill browser-to-api