parallel-cli-setup

作者: parallel-web

设置和维护 Parallel CLI(安装、认证、余额、技能安装)

npx skills add https://github.com/parallel-web/parallel-agent-skills --skill parallel-cli-setup

Parallel CLI Setup

Set up or maintain parallel-cli with minimal friction. If you are running this prompt, your goal is to follow the instructions below and set up parallel-cli for the user so that they can execute searches, run extracts, deep research, etc.

Step 1: Install or upgrade the CLI

Check whether the CLI exists:

command -v parallel-cli

If missing, install with any of these methods:

  1. macOS only: brew install parallel-web/tap/parallel-cli
  2. Linux/macOS/Windows (uv): uv tool install "parallel-web-tools[cli]"
  3. Linux/macOS/Windows (npm): npm install -g parallel-web-cli
  4. Linux/macOS/Windows (pipx): pipx install "parallel-web-tools[cli]" && pipx ensurepath

When parallel-cli is present, require version >=0.9.2. If older, identify the install method before advising an update. Use command -v parallel-cli, then inspect readlink "$(command -v parallel-cli)" if it is a symlink. Paths under ~/.local/share/uv/ tools/ indicate uv tool install; paths under ~/.local/share/parallel-cli/ indicate the standalone installer.

Upgrade commands (choose based on how it was installed):

  • standalone: parallel-cli update
  • uv: uv tool upgrade parallel-web-tools[cli]
  • pipx: pipx upgrade parallel-web-tools[cli]
  • npm: npm update -g parallel-web-cli
  • homebrew: brew update && brew upgrade parallel-web/tap/parallel-cli

Step 2: Authenticate

Check auth status:

parallel-cli auth --json

You will get a response like:

{
  "authenticated": true,
  "method": "oauth",
  "env_var_set": false,
  "has_stored_credentials": true,
  "stored_overridden_by_env": false,
  "token_file": "xxx",
  "version": 1,
  "selected_org_id": "legacy",
  "selected_org_name": null,
  "has_control_api_tokens": false
}

If authenticated is false or selected_org_id is legacy, prompt the user to log in:

parallel-cli login --json

If this is a headless session, append --no-browser.

This triggers device OAuth. The user will be prompted to go to a web browser and input the code the CLI outputs.

When invoking from an agent harness, prefer streaming stdout via a Monitor-style tool over blocking on completion.

The output will look like:

{"event": "auth_start"}
{"event": "device_code", "verification_uri": "http://localhost:3000/getServiceKeys/device", "verification_uri_complete": "http://localhost:3000/getServiceKeys/device?user_code=CHQX-NQKP&onboard_variant=agent", "user_code": "CHQX-NQKP", "expires_in": 600, "browser_open_attempted": true, "browser_opened": true}
{"event": "auth_waiting"}
{"event": "auth_success"}

{"event": "auth_success"} is emitted only after the user has successfully authorized the CLI. Otherwise it blocks at {"event": "auth_waiting"}.

Step 3: Check balance

After authentication, check the current balance:

parallel-cli balance get

If zero, prompt the user to add balance:

parallel-cli balance add <AMOUNT_IN_CENTS>

Make it clear that a payment method should have been added to the organization. If not, the user can go to https://platform.parallel.ai/settings to add one.

Step 4: Install the Parallel skills

Install the skills for the user:

parallel-cli skills install

The user may need to restart their agent if it doesn't support hot reloading.

Step 5: Suggest a first run

Prompt the user to use the newly installed skills to run a search or extract right away. Suggest one of (use $ instead of / for Codex):

  • /parallel-web-search <query> — fast web search
  • /parallel-web-extract <url> — extract content from a URL
  • /parallel-deep-research <topic> — comprehensive research
  • /parallel-data-enrichment <list> — enrich a list of entities

来自 parallel-web 的更多技能

parallel-monitor
parallel-web
持续按固定频率追踪网页变化。当用户要求“监控”、“追踪变化”、“关注”或“提醒我”某内容时使用…
migrate-to-parallel
parallel-web
将Exa、Tavily、Perplexity或Firecrawl的网页数据集成完全迁移到相应的Parallel产品,同时保持应用程序行为不变。使用…
parallel-data-enrichment
parallel-web
批量丰富公司、人员或产品数据,通过网页来源字段(如CEO姓名、融资信息、联系方式)进行补充。支持内联JSON数据或CSV文件输入,并将丰富后的结果输出为CSV。异步运行,通过监控URL和轮询命令跟踪进度。需要parallel-cli工具和互联网访问,可处理大型数据集并配置超时时间。通过自然语言意图描述(例如“CEO姓名和成立年份”)支持灵活的字段请求。
parallel-deep-research
parallel-web
针对复杂主题的详尽研究,支持可配置的深度、延迟与成本权衡。三个处理层级(pro-fast、ultra-fast、ultra)耗时从30秒到25分钟不等,成本按基准的1倍至3倍递增。异步执行与轮询机制:即时启动研究,通过URL监控进度,就绪后获取结果且不阻塞流程。输出格式化的Markdown报告与JSON元数据;执行摘要打印至标准输出以便快速概览。专为显式...
parallel-findall
parallel-web
发现与自然语言描述匹配的实体(公司、人物、产品等)。当用户要求“找出所有X”或“列出每个Y,这些Y……”时使用。
parallel-memory
parallel-web
在可能有用时,回忆过去的Parallel Task、Monitor和FindAll运行记录;在接到请求时,清除运行记录或清空记忆。
parallel-web-extract
parallel-web
从多个URL并行提取内容,高效利用令牌。通过单条命令处理网页、文章、PDF及JavaScript密集型网站。在分叉上下文中运行,相比内置WebFetch减少令牌开销。支持批量提取多个URL,可设置可选聚焦目标。需安装parallel-cli并完成认证;提取内容以Markdown格式输出至本地文件,便于后续查询。
parallel-web-search
parallel-web
快速网络搜索,用于获取当前信息、进行研究及事实核查。可执行单一目标查询或并行多个关键词搜索,返回最多10条结果,包含摘要和元数据。支持通过--after-date进行时效性过滤,以及使用--include-domains进行特定域名搜索。输出结构化JSON,包含标题、URL、发布日期和摘要,便于解析和后续查询。要求每条声明使用Markdown格式的内联引用...