browserbase-cli
Use the Browserbase CLI (`bb`) for Browserbase Functions and platform API workflows. Use when the user asks to run `bb`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, search the web through the Browserbase Search API, or scaffold starter templates. Prefer the Browser skill for interactive browsing; use `bb browse` only when the user explicitly wants the Browserbase CLI path.
- License 许可
- MIT
- 最近更新
- 2026-05-16
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- browserbase-cli
- license
- MIT
- description
- Use the Browserbase CLI (`bb`) for Browserbase Functions and platform API workflows. Use when the user asks to run `bb`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, search the web through the Browserbase Search API, or scaffold starter templates. Prefer the Browser skill for interactive browsing; use `bb browse` only when the user explicitly wants the Browserbase CLI path.
- allowed-tools
- Bash
- compatibility
- Requires the Browserbase CLI (`npm install -g @browserbasehq/cli`). API commands require `BROWSERBASE_API_KEY`. `BROWSERBASE_PROJECT_ID` is only needed for `bb functions dev` and `bb functions publish`. `bb browse` additionally requires `npm install -g @browserbasehq/browse-cli`.
02 资源文件 2
- 许可证LICENSE.txt1.0 KB
- 参考文档REFERENCE.md7.3 KB
03 SKILL.md 正文
Browserbase CLI
Use the official bb CLI for Browserbase platform operations, Functions workflows, and Fetch API calls.
Setup check
Before using the CLI, verify it is installed:
which bb || npm install -g @browserbasehq/cli
bb --help
For authenticated commands, set the API key:
export BROWSERBASE_API_KEY="your_api_key"
If using bb functions dev or bb functions publish, also set:
export BROWSERBASE_PROJECT_ID="your_project_id"
When to use this skill
Use this skill when the user wants to:
- run Browserbase commands through
bb - scaffold, develop, publish, or invoke Browserbase Functions
- inspect or manage Browserbase sessions, projects, contexts, or extensions
- fetch a page through Browserbase without opening a browser session
- search the web through Browserbase without opening a browser session
- browse or scaffold starter templates with
bb templates
When not to use this skill
- For interactive browsing, page inspection, screenshots, clicking, typing, or login flows, prefer the
browserskill. - For simple HTTP content retrieval where the user does not care about using the CLI specifically, the dedicated
fetchskill is often a better fit. - Use
bb browse ...only when the user explicitly wants the CLI wrapper or is already working in abb-centric workflow.
Command selection
bb functionsfor local dev, packaging, publishing, and invocationbb sessions,bb projects,bb contexts,bb extensionsfor Browserbase platform resourcesbb fetch <url>for Fetch API requestsbb search "<query>"for Search API requestsbb templatesto browse and scaffold starter templatesbb browse ...to forward to the standalonebrowsebinary (requires@browserbasehq/browse-cli)bb skills installto install Browserbase agent skills for Claude Code
For bb browse, the standalone browse CLI behavior is the source of truth: bb browse env local uses a clean isolated local browser by default, and bb browse env local --auto-connect opts into reusing an existing local Chrome session.
Common workflows
Functions
bb functions init my-function
cd my-function
bb functions dev index.ts
bb functions publish index.ts
bb functions invoke <function_id> --params '{"url":"https://example.com"}'
Use bb functions invoke --check-status <invocation_id> to poll an existing invocation instead of creating a new one.
Platform APIs
bb projects list
bb sessions create --proxies --advanced-stealth --region us-east-1
bb sessions create --solve-captchas --context-id ctx_abc --persist
bb sessions get <session_id>
bb sessions downloads get <session_id> --output session-artifacts.zip
bb contexts create --body '{"region":"us-west-2"}'
bb extensions upload ./my-extension.zip
Fetch API
bb fetch https://example.com
bb fetch https://example.com --allow-redirects --output page.html
Search API
bb search "browser automation"
bb search "web scraping" --num-results 5
bb search "AI agents" --output results.json
Templates
bb templates list
bb templates list --language python
bb templates clone form-filling --language typescript
bb templates clone amazon-product-scraping --language python ./my-scraper
Best practices
- Prefer
bb --helpand subgroup--helpbefore guessing flags. - Use dash-case flags exactly as shown in CLI help.
- Use
--output <file>onbb fetchandbb searchto save results to a file. - Use environment variables for auth unless the user explicitly wants one-off overrides.
- Pass structured request bodies with JSON strings in
--bodyor--params. - Remember that
bb functions ...uses--api-url, while platform API commands use--base-url. - If
bb browsefails becausebrowseis missing, either install@browserbasehq/browse-clior switch to thebrowserskill.
Troubleshooting
- Missing API key: set
BROWSERBASE_API_KEYor pass--api-key - Missing project ID on
bb functions devorbb functions publish: setBROWSERBASE_PROJECT_IDor pass--project-id - Unknown flag: rerun the relevant command with
--helpand use the exact dash-case form bb browseinstall error: runnpm install -g @browserbasehq/browse-cli
For command-by-command reference and more examples, see REFERENCE.md.
04 同仓库更多 Skills
qedgen
Formally verify programs by writing Lean 4 proofs. Trigger this skill whenever the user wants to formally verify code, generate Lean 4 proofs, prove properties about algorithms or smart contracts, verify invariants, convert program logic into formal specifications, or anything involving Lean 4 and formal verification. Also trigger when the user mentions "qedgen", "lean proof", "formal proof", "verify my code", "prove correctness", "formal verification", or wants mathematical guarantees about their implementation.
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
clawd-code-skill
Control Clawd via MCP protocol. Trigger with "plan" to write a precise execution plan then feed it to Clawd. Also supports direct commands, persistent sessions, agent teams, and advanced tool control.
solana-clawd
solana-clawd — an open-source Solana AI agent framework built from Clawd Code's leaked agentic engine and the SolanaOS operator runtime. TypeScript MCP server for Clawd Desktop, Cursor, VS Code, or headless node. 31+ tools for Solana trading, on-chain intelligence, wallet management, Pump.fun scanning, MawdBot trading agents, Honcho v3 memory, Privy agentic wallets, and multi-venue perp execution (Hyperliquid + Aster). Use when asked about Solana trading, memecoin analysis, Pump.fun launches, MawdBot operations, OODA loops, wallet management, token research, agentic wallets, or any SolanaOS/solana-clawd surface.
qedgen
Formally verify programs by writing Lean 4 proofs. Trigger this skill whenever the user wants to formally verify code, generate Lean 4 proofs, prove properties about algorithms or smart contracts, verify invariants, convert program logic into formal specifications, or anything involving Lean 4 and formal verification. Also trigger when the user mentions "qedgen", "lean proof", "formal proof", "verify my code", "prove correctness", "formal verification", or wants mathematical guarantees about their implementation.
solana-dev-skill-main
暂无简介