Browser To Api

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.

skills.sh installs: 2K
GitHub stars: 3.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add browserbase/skills --skill browser-to-api --agent claude-code

Installs into .claude/skills of the current project.

Files

Browser to API

Replay-driven API discovery. Consume a browser-trace capture, pair its CDP request / response events, templatize observed URLs, infer JSON schemas from samples, and emit an OpenAPI 3.1 document plus a human-readable coverage report.

This skill does not capture traffic. It is purely offline post-processing on top of browser-trace's cdp/network/*.jsonl buckets. The two skills compose:

browser-trace    →  .o11y/<run>/cdp/network/{requests,responses}.jsonl
browser-to-api   →  .o11y/<run>/api-spec/index.html + openapi.yaml + client.mjs

When to use

The user wants an OpenAPI document for a third-party or undocumented website API.
The user has a browser-trace run and wants endpoints + schemas extracted from it.
The user is building a client/SDK against a site that doesn't publish a spec.
The user wants a coverage report showing which flows would broaden the spec.

If the user wants to capture traffic, send them to browser-trace first.

Two-step workflow

1. Capture with `browser-trace` (and optionally bodies via `browse network on`)

# Local example against an existing debuggable Chrome target
TARGET=9222

SKILL.md on GitHub

Details

Repository: github.com/browserbase/skills
Categories: Backend & APIs, DevOps & CI/CD, Documentation, Automation & Workflows, Marketing & SEO
First seen: Jun 3, 2026

More from browserbase/skills

All 14