Menú
Browser automation for documentation discovery. Use when curl fails on JS-rendered sites, when detecting available browser tools, or when configuring browser-based documentation collection.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Generic BAML patterns for type-safe LLM prompting. Covers schema design, DTO generation, client wrappers, and cross-language codegen. Framework-agnostic.
C4 architectural modeling for documenting software architecture. Use when creating architecture diagrams, planning new systems, communicating with stakeholders, or conducting architecture reviews.
Debug and analyze web applications using Chrome DevTools MCP. Use for console log inspection, network request monitoring, performance analysis, and debugging authenticated sessions. For basic browser automation (screenshots, form filling), use browser-discovery skill instead.
Patterns and techniques for analyzing brownfield codebases. Use when onboarding to unfamiliar code, preparing for refactoring, conducting architecture reviews, or identifying technical debt.
Detect new imports in modified files and auto-install missing dependencies. Works with npm, uv, pip, cargo, go mod, and other package managers. Triggers after code implementation to keep manifests in sync.
Navigate hierarchical ai-docs indexes to find documentation. Check local docs FIRST for speed and curated context before web searching. Covers Claude Code, BAML, MCP, and other tracked libraries.
| name | browser-discovery |
| description | Browser automation for documentation discovery. Use when curl fails on JS-rendered sites, when detecting available browser tools, or when configuring browser-based documentation collection. |
Detect and use browser automation tools for documentation discovery when static fetching fails.
| Variable | Default | Description |
|---|---|---|
| PREFERRED_TOOL | auto | auto, antigravity, cursor, playwright |
| WAIT_TIMEOUT | 3 | Seconds to wait for JS rendering |
| MAX_PAGES | 50 | Maximum pages to discover per site |
MANDATORY - Follow the Workflow steps below when browser automation is needed.
js_required: true is setDo you need browser automation?
│
├─ Curl returns full content? ──────────► NO - Use curl (docs-fetch-url)
│
├─ Curl returns <1KB or 403? ───────────► YES - Continue below
│
Which browser tool to use?
│
├─ browser_subagent available? ─────────► antigravity-browser.md
│
├─ In Cursor IDE? ──────────────────────► cursor-browser.md
│
├─ Chrome debugging on :9222? ──────────► playwright-browser.md (wrapper)
│
└─ No browser tool? ────────────────────► See "No Browser Available" section
If you're about to:
STOP -> Check the appropriate cookbook -> Then proceed
js_required: true in config?| Priority | Tool | Detection | Best For |
|---|---|---|---|
| 1 | Antigravity browser_subagent | Tool in tool list | Zero-config native |
| 2 | Cursor MCP (in-IDE) | mcp__cursor__browser_* | In Cursor IDE |
| 3 | Cursor CLI | which cursor-agent | Delegation from CLI |
| 4 | Playwright (wrapper) | curl localhost:9222/json/version | Full automation |
browser_subagent tool availablecookbook/antigravity-browser.mdcursor-agent availablecookbook/cursor-browser.mdcookbook/playwright-browser.mdSigns that a site requires browser automation:
__NEXT_DATA__, window.__remixContext, window.__NUXT__If no browser tool is detected:
No browser automation tool detected.
Setup options:
1. Antigravity IDE: Built-in (zero config)
2. Cursor: cursor-agent available when installed
3. Claude Code: Launch Chrome with debugging:
google-chrome --remote-debugging-port=9222
Then use the Playwright wrapper:
python3 .claude/ai-dev-kit/dev-tools/mcp/wrappers/playwright_wrapper.py navigate "https://..."
Return discovered pages as structured data:
{
"pages": [
{"url": "...", "title": "...", "section": "..."}
],
"nav_structure": "sidebar | tabs | accordion",
"js_required": true
}