Token导航 LogoToken导航

Agent Skill · 研究检索

google-ads-open-cli(Google ADS open CLI 搜索)

google-ads-open-cli 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

google-ads-open-cli 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 56,510。

总安装 449周安装 18GitHub Stars 14下载 145核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:google-ads-open-cli(Google ADS open CLI 搜索)
来源仓库:https://github.com/bin-huang/google-ads-open-cli
仓库路径:skills/google-ads-open-cli
安装命令:
npx skills add https://github.com/bin-huang/google-ads-open-cli --skill google-ads-open-cli
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/bin-huang/google-ads-open-cli --skill google-ads-open-cli

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

google-ads-open-cli 读取 Google Ads API 数据,支持账户结构与性能查询。通过 GAQL 运行自定义报表,输出 JSON 便于分析。通过 npx skills add 安装,配置 OAuth2 用户凭证后使用。仅读权限,不影响广告操作,适合监控与分析用途。

建议限制查询范围,避免触发配额限制。

来源仓库内路径:skills/google-ads-open-cli

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/bin-huang/google-ads-open-cli --skill google-a…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

google-ads-open-cli 怎么安装?

在终端执行 npx skills add https://github.com/bin-huang/google-ads-open-cli --skill google-ads-open-cl…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

google-ads-open-cli 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

google-ads-open-cli 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

google-ads-open-cli 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

google-ads-open-cli 用的人多吗?

公开数据是累计安装 449 次,近一周安装 18 次,下载 145 次,GitHub 14 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

google-ads-open-cli 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
google-ads-open-cli

Google ADS open CLI 搜索 · 本页

44914接触敏感数据未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Google Ads CLI Skill

You have access to google-ads-open-cli, a read-only CLI for the Google Ads API (v23). Use it to query ad accounts, pull performance stats, and run custom GAQL queries.

Quick start

# Check if the CLI is available
google-ads-open-cli --help

# List accessible accounts
google-ads-open-cli customers

If the CLI is not installed, install it:

npm install -g google-ads-open-cli

Authentication

The CLI uses OAuth2 user credentials (Google Ads API does not support service accounts). Credentials are stored in ~/.config/google-ads-open-cli/credentials.json.

Before running any command, verify credentials are configured by running google-ads-open-cli customers. If it fails with a credentials error, ask the user to set up authentication:

google-ads-open-cli auth login \
  --developer-token=xxx \
  --client-id=xxx \
  --client-secret=xxx

How to get the values:

  1. developer_token: Sign in to a Google Ads manager account and open the API Center. Copy the developer token.
  2. client_id & client_secret: Go to Google Cloud Console > Credentials, create an OAuth client ID (Desktop app type). Make sure the Google Ads API is enabled.

This opens a browser for authorization. Make sure the user signs in with a Google account that has access to the Google Ads data they want to use. After approval, credentials are saved automatically. All subsequent commands work with auto-refreshing tokens.

For MCC (manager) accounts, add "login_customer_id": "1234567890" to the credentials file.

Alternative: set GOOGLE_ADS_ACCESS_TOKEN and GOOGLE_ADS_DEVELOPER_TOKEN environment variables (useful for CI/CD).

Entity hierarchy

Manager Account (MCC)
 └── Customer Account (10-digit ID, e.g. 1234567890)
      ├── Campaign
      │    └── Ad Group
      │         ├── Ad (Ad Group Ad)
      │         └── Keyword (Ad Group Criterion)
      ├── Campaign Budget
      ├── Conversion Action
      ├── User List (remarketing)
      └── Asset (images, videos, sitelinks)

Customer IDs are 10-digit numbers. Dashes are stripped automatically.

Monetary values

Google Ads uses micros: 1 currency unit = 1,000,000 micros. All cost/bid/budget values returned by the CLI are in micros. Always divide by 1,000,000 when presenting monetary values to the user.

Output format

All commands output pretty-printed JSON by default. Use --format compact for single-line JSON (useful for piping).

Built-in commands

Account discovery

# List all accessible accounts
google-ads-open-cli customers

# Get details for a specific account
google-ads-open-cli customer 1234567890

# List sub-accounts under an MCC
google-ads-open-cli account-hierarchy 1234567890

Browsing entities

# Campaigns (filter by status: ENABLED, PAUSED, REMOVED)
google-ads-open-cli campaigns 1234567890
google-ads-open-cli campaigns 1234567890 --status ENABLED

# Get a specific campaign
google-ads-open-cli campaign 1234567890 98765

# Campaign budgets
google-ads-open-cli campaign-budgets 1234567890

# Ad groups (filter by campaign, status)
google-ads-open-cli ad-groups 1234567890 --campaign 98765

# Get a specific ad group
google-ads-open-cli ad-group 1234567890 11111

# Ads (filter by campaign, ad group, status)
google-ads-open-cli ads 1234567890 --campaign 98765 --ad-group 11111

# Get a specific ad (requires ad-group-id and ad-id)
google-ads-open-cli ad 1234567890 11111 22222

# Keywords
google-ads-open-cli keywords 1234567890 --campaign 98765 --status ENABLED

All listing commands support --limit <n> (default 100).

Performance stats

Stats commands require --start and --end dates (YYYY-MM-DD):

# Campaign stats
google-ads-open-cli campaign-stats 1234567890 --start 2026-01-01 --end 2026-01-31

# Campaign stats with device segment
google-ads-open-cli campaign-stats 1234567890 --start 2026-01-01 --end 2026-01-31 --segments device

# Ad group stats (filter by --campaign and/or --ad-group)
google-ads-open-cli ad-group-stats 1234567890 --start 2026-01-01 --end 2026-01-31 --campaign 98765

# Ad-level stats (filter by --campaign and/or --ad-group)
google-ads-open-cli ad-stats 1234567890 --start 2026-01-01 --end 2026-01-31

# Keyword stats (sorted by impressions desc; filter by --campaign and/or --ad-group)
google-ads-open-cli keyword-stats 1234567890 --start 2026-01-01 --end 2026-01-31

Available segments for campaign-stats --segments: device, ad_network_type, day_of_week (comma-separated).

Stats commands default to --limit 1000.

Other commands

# Audiences and remarketing lists
google-ads-open-cli audiences 1234567890
google-ads-open-cli user-lists 1234567890

# Assets and extensions
google-ads-open-cli assets 1234567890 --type SITELINK
google-ads-open-cli extensions 1234567890 --campaign 98765

# Conversions and billing
google-ads-open-cli conversion-actions 1234567890
google-ads-open-cli billing 1234567890

# Change history
google-ads-open-cli change-status 1234567890 --limit 20

# Negative keyword lists
google-ads-open-cli negative-keywords 1234567890

Asset types: IMAGE, MEDIA_BUNDLE, TEXT, YOUTUBE_VIDEO, LEAD_FORM, CALL, CALLOUT, SITELINK, STRUCTURED_SNIPPET.

Custom GAQL queries

The query command is the escape hatch for anything not covered by built-in commands. It runs arbitrary GAQL (Google Ads Query Language) against the Google Ads API.

google-ads-open-cli query <customer-id> "<GAQL>"

GAQL syntax

SELECT field1, field2, ...
FROM resource_name
WHERE conditions
ORDER BY field [ASC|DESC]
LIMIT count
PARAMETERS key=value
  • SELECT and FROM are required. WHERE, ORDER BY, LIMIT, PARAMETERS are optional.
  • Keywords (SELECT, FROM, WHERE, etc.) are case-insensitive.
  • Field names, resource names, and enum values are case-sensitive.
  • No OR operator -- all WHERE conditions are AND-ed together.
  • No JOIN, GROUP BY, HAVING, or subqueries.

WHERE operators

OperatorExample
=, !=, >, <, >=, <=campaign.status = 'ENABLED'
IN, NOT INcampaign.status IN ('ENABLED', 'PAUSED')
LIKE, NOT LIKEcampaign.name LIKE '%brand%' (case-insensitive)
REGEXP_MATCHcampaign.name REGEXP_MATCH '(?i)brand'
BETWEEN... AND...segments.date BETWEEN '2026-01-01' AND '2026-01-31'
DURINGsegments.date DURING LAST_30_DAYS
IS NULL, IS NOT NULLad_group_ad.ad.final_urls IS NOT NULL
CONTAINS ANY/ALL/NONEFor repeated fields

Date filtering

Custom range:

WHERE segments.date BETWEEN '2026-01-01' AND '2026-01-31'

Predefined ranges (with DURING):

  • TODAY, YESTERDAY
  • LAST_7_DAYS, LAST_14_DAYS, LAST_30_DAYS (NOT including today)
  • THIS_MONTH, LAST_MONTH
  • THIS_WEEK_SUN_TODAY, THIS_WEEK_MON_TODAY
  • LAST_WEEK_SUN_SAT, LAST_WEEK_MON_SUN
  • LAST_BUSINESS_WEEK

Common resource names (FROM clause)

Entities: customer, campaign, campaign_budget, ad_group, ad_group_ad, ad_group_criterion, campaign_criterion

View resources (for metrics): keyword_view, search_term_view, geographic_view, gender_view, age_range_view, landing_page_view, ad_group_audience_view, shopping_performance_view, click_view

Other: change_status, change_event, conversion_action, asset, bidding_strategy, label, recommendation, shared_set, shared_criterion

Common metrics

Performance: metrics.impressions, metrics.clicks, metrics.cost_micros, metrics.ctr, metrics.average_cpc, metrics.average_cpm, metrics.interactions

Conversions: metrics.conversions, metrics.conversions_value, metrics.all_conversions, metrics.cost_per_conversion, metrics.conversion_rate, metrics.value_per_conversion

Impression share: metrics.search_impression_share, metrics.search_budget_lost_impression_share, metrics.search_rank_lost_impression_share, metrics.absolute_top_impression_percentage, metrics.top_impression_percentage

Video: metrics.video_views, metrics.video_view_rate, metrics.average_cpv

Common segments

Date: segments.date, segments.week, segments.month, segments.quarter, segments.year, segments.hour_of_day, segments.day_of_week

Device/network: segments.device, segments.ad_network_type, segments.slot, segments.click_type

Conversion: segments.conversion_action, segments.conversion_action_name, segments.conversion_action_category

Important GAQL rules

  1. Date range required with date segments. If segments.date (or segments.week, segments.month, etc.) is in SELECT, a finite date range filter MUST be in WHERE.
  2. Non-date segments in WHERE must be in SELECT. Exception: date segments can appear in WHERE without being in SELECT.
  3. Removed entities are included by default. The API does NOT filter out removed entities. Add campaign.status!= 'REMOVED' (or equivalent) to match Google Ads UI behavior.
  4. Field compatibility. Not all fields can be selected together. If you get an error about incompatible fields, remove fields one at a time or consult the Google Ads API field compatibility documentation.
  5. ORDER BY fields must be in SELECT. You can only order by fields that appear in the SELECT clause.
  6. Attributed resources. You can select parent entity fields without them being in FROM. For example, campaign.name is available when FROM ad_group.

GAQL query examples

Search terms that triggered ads:

google-ads-open-cli query 1234567890 "SELECT search_term_view.search_term, search_term_view.status, campaign.name, ad_group.name, metrics.clicks, metrics.impressions, metrics.ctr, metrics.cost_micros FROM search_term_view WHERE segments.date DURING LAST_30_DAYS ORDER BY metrics.impressions DESC LIMIT 50"

Campaign performance by device:

google-ads-open-cli query 1234567890 "SELECT campaign.name, segments.device, metrics.impressions, metrics.clicks, metrics.ctr, metrics.cost_micros, metrics.conversions FROM campaign WHERE segments.date DURING LAST_30_DAYS AND campaign.status != 'REMOVED'"

Impression share analysis:

google-ads-open-cli query 1234567890 "SELECT campaign.name, metrics.search_impression_share, metrics.search_budget_lost_impression_share, metrics.search_rank_lost_impression_share, metrics.clicks, metrics.impressions, metrics.cost_micros FROM campaign WHERE segments.date DURING LAST_7_DAYS AND campaign.status = 'ENABLED' ORDER BY metrics.search_budget_lost_impression_share DESC"

Landing page performance:

google-ads-open-cli query 1234567890 "SELECT landing_page_view.unexpanded_final_url, metrics.clicks, metrics.impressions, metrics.ctr, metrics.cost_micros, metrics.conversions FROM landing_page_view WHERE segments.date DURING LAST_30_DAYS ORDER BY metrics.clicks DESC LIMIT 20"

Demographics -- age breakdown:

google-ads-open-cli query 1234567890 "SELECT ad_group_criterion.age_range.type, campaign.name, metrics.clicks, metrics.impressions, metrics.ctr, metrics.cost_micros FROM age_range_view WHERE segments.date DURING LAST_30_DAYS"

Geographic performance (by user location):

google-ads-open-cli query 1234567890 "SELECT geographic_view.country_criterion_id, geographic_view.location_type, campaign.name, metrics.clicks, metrics.impressions, metrics.cost_micros FROM geographic_view WHERE segments.date DURING LAST_30_DAYS ORDER BY metrics.clicks DESC LIMIT 50"

Ad copy performance (responsive search ads):

google-ads-open-cli query 1234567890 "SELECT ad_group_ad.ad.responsive_search_ad.headlines, ad_group_ad.ad.responsive_search_ad.descriptions, ad_group_ad.ad.final_urls, ad_group_ad.status, metrics.clicks, metrics.impressions, metrics.ctr, metrics.cost_micros FROM ad_group_ad WHERE segments.date DURING LAST_30_DAYS AND ad_group_ad.status != 'REMOVED' AND ad_group_ad.ad.type = 'RESPONSIVE_SEARCH_AD' ORDER BY metrics.clicks DESC LIMIT 20"

Conversion actions audit:

google-ads-open-cli query 1234567890 "SELECT conversion_action.name, conversion_action.type, conversion_action.status, conversion_action.category, conversion_action.counting_type, conversion_action.click_through_lookback_window_days, conversion_action.view_through_lookback_window_days FROM conversion_action WHERE conversion_action.status = 'ENABLED'"

Shopping product performance:

google-ads-open-cli query 1234567890 "SELECT segments.product_item_id, segments.product_title, metrics.clicks, metrics.impressions, metrics.ctr, metrics.cost_micros, metrics.conversions, metrics.conversions_value FROM shopping_performance_view WHERE segments.date DURING LAST_30_DAYS ORDER BY metrics.conversions_value DESC LIMIT 50"

Account-level daily trend:

google-ads-open-cli query 1234567890 "SELECT segments.date, metrics.clicks, metrics.impressions, metrics.ctr, metrics.cost_micros, metrics.conversions, metrics.conversions_value FROM customer WHERE segments.date DURING LAST_30_DAYS ORDER BY segments.date"

Workflow guidance

When the user asks for a quick overview

  1. Run google-ads-open-cli customers to find accessible accounts
  2. Use campaign-stats with a recent date range for a performance snapshot
  3. Present the data with costs converted from micros to currency

When the user asks for deep analysis

  1. Start with campaign-stats to identify the scope
  2. Drill down with ad-group-stats or keyword-stats for underperforming campaigns
  3. Use custom GAQL queries for specific analysis (search terms, demographics, impression share, landing pages)
  4. Cross-reference with conversion-actions to verify tracking setup

When the user asks about specific metrics not in built-in commands

Use the query command with GAQL. Common scenarios:

  • Search terms report -- use search_term_view
  • Geographic data -- use geographic_view
  • Demographics -- use gender_view, age_range_view
  • Landing pages -- use landing_page_view
  • Impression share -- select metrics.search_impression_share and related fields from campaign
  • Shopping products -- use shopping_performance_view
  • Change history -- use change_event for detailed logs

Error handling

  • Authentication errors -- ask the user to verify their access token and developer token
  • "field is not compatible" -- some fields cannot be selected together; remove incompatible fields and retry
  • Empty results -- check date range, status filters, and whether the account has data for the requested entities
  • "MISALIGNED_DATE_FOR_FILTER" -- when filtering segments.month or segments.quarter, the date must be the first day of the period

API documentation references

平台分布

Codex

38.89%
按下载量换算56

Claude

28.89%
按下载量换算42

Cursor

18.82%
按下载量换算27

Gemini CLI

9.62%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

未通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills