菜单
Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.
Audit the developer experience of a product, SDK, docs site, or SKILL.md by dropping multiple Claude subagents at it with only a tiny task prompt and real tools (WebFetch, Bash, Write). Agents must discover the docs themselves, install deps, ask for credentials if needed, and attempt real execution. The skill captures each agent's trace — tool calls, retries, wall time, errors — and scores on Setup Friction, Speed, Efficiency, Error Recovery, and Doc Quality, then emits an HTML report with an A–F grade and concrete fixes. Use when the user asks to audit agent experience, test a skill, audit docs for agents, check if a SDK is agent-friendly, validate a SKILL.md, measure agent DX, or benchmark how painful onboarding is for an AI agent. Triggers: 'audit agent experience', 'test this skill', 'audit docs for agents', 'is my SDK agent-friendly', 'run a DX audit', 'agent experience test', 'test my docs', 'how do agents do with my product'.
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
Turn a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a `browser-trace` capture. Use when the user wants to discover/extract API endpoints from a browser session, build an OpenAPI doc from network traffic, or document a third-party site's XHR/fetch surface for client integration.
Company discovery and deep research skill. Researches a company's product and ICP, discovers target companies to sell to using Browserbase Search API, deeply researches each using a Plan→Research→Synthesize pattern, and scores ICP fit — compiled into a scored research report and CSV. Supports depth modes (quick/deep/deeper) for balancing scale vs intelligence. Use when the user wants to: (1) find companies to sell to, (2) research potential customers, (3) discover companies matching an ICP, (4) build a target company list, (5) do market research on prospects. Triggers: "find companies to sell to", "company research", "find prospects", "ICP research", "target companies", "who should we sell to", "market research", "lead research", "prospect list".
Event prospecting skill. Takes a conference / event speakers URL, extracts the people, filters their companies against the user's ICP, then deep-researches only the speakers at ICP-fit companies. Outputs a person-first HTML report where each card answers "why should the AE talk to this person?" with all public links and a one-click DM opener. Use when the user wants to: (1) find leads at a specific conference, (2) prep for an event, (3) research event speakers, (4) build a target list from a sponsor/exhibitor page, (5) scrape conference speakers and rank by ICP fit. Triggers: "find leads at {event}", "research speakers at", "prospect this conference", "stripe sessions leads", "ai engineer summit prospects", "event prospecting", "scrape conference speakers", "who should I meet at".
Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers, follow redirects, or get page source for simple scraping. Prefer it over a browser when JavaScript rendering and page interaction are not needed. Supports proxies and redirect control.
| name | cookie-sync |
| description | Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase. |
| compatibility | Requires Node.js 22+, a local Chromium-based browser (Chrome, Brave, Edge) with remote debugging enabled, and BROWSERBASE_API_KEY. Run `npm install` in the skill directory before first use. |
| license | MIT |
| allowed-tools | Bash |
Exports cookies from your local Chrome and saves them into a Browserbase persistent context. After syncing, use the browse CLI to open authenticated sessions with that context.
Supports domain filtering (only sync cookies you need) and context reuse (refresh cookies without creating a new context).
chrome://flags/#allow-remote-debugging, enable it and restart the browser--remote-debugging-port=9222 --user-data-dir=/tmp/chrome-debug and set CDP_URL=ws://127.0.0.1:9222BROWSERBASE_API_KEYInstall dependencies before first use:
cd .claude/skills/cookie-sync && npm install
node .claude/skills/cookie-sync/scripts/cookie-sync.mjs
Creates a persistent context with all your Chrome cookies. Outputs a context ID.
node .claude/skills/cookie-sync/scripts/cookie-sync.mjs --domains google.com,github.com
Matches the domain and all subdomains (e.g. google.com matches accounts.google.com, mail.google.com, etc.)
node .claude/skills/cookie-sync/scripts/cookie-sync.mjs --context ctx_abc123
Re-injects fresh cookies into a previously created context. Use this when cookies have expired.
node .claude/skills/cookie-sync/scripts/cookie-sync.mjs --verified
Enables Browserbase Identity with a Verified browser to improve access on protected sites. Recommended for sites like Google that fingerprint browsers.
node .claude/skills/cookie-sync/scripts/cookie-sync.mjs --proxy "San Francisco,CA,US"
Routes through a residential proxy in the specified location. Format: "City,ST,Country" (state is 2-letter code). Helps match your local IP's geolocation so auth cookies aren't rejected.
node .claude/skills/cookie-sync/scripts/cookie-sync.mjs --domains github.com,google.com --verified --proxy "San Francisco,CA,US"
After syncing, use the browse CLI with the context ID:
SESSION_JSON="$(browse cloud sessions create --context-id <ctx-id> --persist --keep-alive)"
SESSION_ID="$(echo "$SESSION_JSON" | jq -r .id)"
CONNECT_URL="$(echo "$SESSION_JSON" | jq -r .connectUrl)"
browse open https://mail.google.com --cdp "$CONNECT_URL"
The --persist flag on browse cloud sessions create saves any new cookies or state changes back to the context when the cloud session is released, keeping the session fresh for next time.
Full workflow example:
# Step 1: Sync cookies for Twitter
node .claude/skills/cookie-sync/scripts/cookie-sync.mjs --domains x.com,twitter.com
# Output: Context ID: ctx_abc123
# Step 2: Browse authenticated Twitter
SESSION_JSON="$(browse cloud sessions create --context-id ctx_abc123 --persist --keep-alive)"
SESSION_ID="$(echo "$SESSION_JSON" | jq -r .id)"
CONNECT_URL="$(echo "$SESSION_JSON" | jq -r .connectUrl)"
browse open https://x.com/messages --cdp "$CONNECT_URL"
browse snapshot
browse screenshot
browse stop
browse cloud sessions update "$SESSION_ID" --status REQUEST_RELEASE
Contexts persist across sessions, making them ideal for scheduled/recurring tasks:
browse cloud sessions create --context-id <ctx-id> --persist --keep-alive, then attach with browse open <url> --cdp <connectUrl> — no local Chrome needed--context <ctx-id> to refreshchrome://flags/#allow-remote-debugging if your browser build exposes it, or launch with --remote-debugging-port=9222 and set CDP_URL=ws://127.0.0.1:9222--context <id> to refresh--verified and/or --proxy with a location near you