Browser to API consumes a `browser-trace` capture to generate OpenAPI 3.1 documents and coverage reports. It's ideal for users who need to extract endpoints and JSON schemas from websites that lack a formal API specification.
$ npx skills add https://github.com/browserbase/skills --skill browser-to-apiBrowser to API analyzes HTTP traffic captured during browser automation to automatically generate OpenAPI 3.1 documentation and coverage reports. By processing browser-trace captures—which include DevTools protocol data, screenshots, and DOM snapshots—the skill extracts observable API endpoints and infers JSON schemas without requiring access to backend source code. This is particularly valuable for reverse-engineering APIs from websites that lack public specifications, integrating with undocumented services, or documenting legacy web applications. Teams building integrations, API clients, or testing tools can use this skill to quickly understand and document the actual API surface of any website.
Install with `$ npx skills add https://github.com/browserbase/skills --skill browser-to-api` and use as needed.
Generate OpenAPI documents for third-party websites
Extract endpoints and schemas from browser-trace captures
Build clients for sites without published specs
Provide coverage reports for API flows
$ npx skills add https://github.com/browserbase/skills --skill browser-to-apigit clone https://github.com/browserbase/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Check the GitHub repository or documentation for usage examples.
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan