meta-ads-library

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Meta Ads Library

Meta广告库

Guide for searching the Meta Ads Library and producing structured competitor ad intelligence.

The skill's job is to turn raw scraped ads into useful summaries: top advertisers, common CTAs, recurring hooks, recently launched creatives, and (optionally) enriched lead lists. All output is presented inline in chat — there is no database or persistence layer.

搜索Meta广告库并生成结构化竞品广告情报的指南。

本Skill的作用是将抓取的原始广告转化为实用总结：顶级广告主、常见CTA、高频钩子、近期上线的创意，以及（可选）补充后的线索列表。所有输出均在聊天中直接展示——无数据库或持久化层。

Out of scope — defer to other skills

超出范围——转至其他Skill

Request	Send them to
Multi-source competitor research (site, social, search rank, etc., not just ads)	`competitor-intel`
Generating new ad creative based on what you found	`ad-creative-generation`

请求	转至
多来源竞品研究（网站、社交平台、搜索排名等，不仅限于广告）	`competitor-intel`
根据研究结果生成新广告创意	`ad-creative-generation`

Requirements

要求

Hyper MCP installed and connected. https://app.hyperfx.ai/mcp
Apify integration connected at https://app.hyperfx.ai/apps — the Meta Ads Library tools run via Apify under the hood.

search_facebook_ads

is not in the tool list, stop and tell the user to enable Hyper MCP and connect Apify.

已安装并连接Hyper MCP。https://app.hyperfx.ai/mcp
已连接Apify集成，地址为https://app.hyperfx.ai/apps——Meta广告库工具底层通过Apify运行。

如果工具列表中没有

search_facebook_ads

，请停止操作并告知用户启用Hyper MCP并连接Apify。

Tool surface

工具概览

Tool	Purpose
`search_facebook_ads`	Search the Meta Ads Library by keyword. Returns compact results (title, body, CTA, link, page name, dates, platforms). Max 40 per call.
`get_facebook_ad_details`	Get full details for a specific ad. Requires both `ad_archive_id` and `page_id` — both come from `search_facebook_ads` results.
`search_facebook_ads_enriched`	Search + enrich each result with page contact info (email, phone, website). Slower (multiple API calls per result). Max 20 per call.
`search_facebook_pages`	Search Facebook pages by category + location (not by keyword). Useful for building a lead list from a vertical.
`scrape_facebook_pages`	Scrape detailed data from specific Facebook page URLs.

工具	用途
`search_facebook_ads`	按关键词搜索Meta广告库。返回精简结果（标题、正文、CTA、链接、页面名称、日期、平台）。每次调用最多返回40条。
`get_facebook_ad_details`	获取特定广告的完整详情。需要 `ad_archive_id` 和 `page_id` ——两者均来自 `search_facebook_ads` 的结果。
`search_facebook_ads_enriched`	搜索并为每个结果补充页面联系信息（邮箱、电话、网站）。速度较慢（每个结果需多次API调用）。每次调用最多返回20条。
`search_facebook_pages`	按类别+地点搜索Facebook页面（不按关键词）。适用于从垂直领域构建线索列表。
`scrape_facebook_pages`	从特定Facebook页面URL抓取详细数据。

Critical rules

关键规则

Public-only data. The Meta Ads Library is public. Don't attempt to bypass any access control or scrape private content.
Count limits differ between tools.
```
search_facebook_ads
```
allows
```
count
```
up to 40.
```
search_facebook_ads_enriched
```
caps at 20 — exceeding this returns an error.
get_facebook_ad_details
needs two IDs. Both
```
ad_archive_id
```
and
```
page_id
```
are required. Both are returned in every
```
search_facebook_ads
```
result row — pass them through together.
Enriched search is slow. It makes a Facebook page scrape per ad and optionally a website scrape. Only use it when contact info matters (lead-gen workflows). For pure ad intelligence, use the regular
```
search_facebook_ads
```
.
Apify-backed tools fail intermittently. Expect occasional
```
"fetch failed"
```
responses. Retry once after a short delay before reporting the source as missing.
Don't over-interpret a single ad. "Brand X is running a discount" is noise. "5 of the top 10 advertisers in this query are running discounts" is signal. Always aggregate before drawing conclusions.

仅公开数据。Meta广告库是公开的。请勿尝试绕过任何访问控制或抓取私有内容。
不同工具的数量限制不同。
```
search_facebook_ads
```
允许
```
count
```
最多为40。
```
search_facebook_ads_enriched
```
上限为20——超过此限制会返回错误。
get_facebook_ad_details
需要两个ID。必须同时提供
```
ad_archive_id
```
和
```
page_id
```
。两者均在
```
search_facebook_ads
```
的每条结果中返回——需同时传入。
补充搜索速度慢。它会为每个广告抓取Facebook页面，还可选择抓取网站。仅在需要联系信息（线索生成流程）时使用。若仅需广告情报，请使用常规的
```
search_facebook_ads
```
。
基于Apify的工具可能间歇性失败。偶尔会出现
```
"fetch failed"
```
响应。在报告资源缺失前，先短暂延迟后重试一次。
不要过度解读单个广告。“X品牌正在推出折扣”属于噪音。“此查询中排名前10的广告主中有5家正在推出折扣”才是有效信号。得出结论前务必先进行汇总分析。

Workflow

工作流程

Phase 1 — Define the query

阶段1——定义查询条件

Before running anything, agree on:

The search query — keyword(s) competitors would target. Examples:
```
"meal kit delivery"
```
,
```
"AI marketing tools"
```
,
```
"skincare for sensitive skin"
```
.
Country — ISO code (e.g.
```
"US"
```
,
```
"GB"
```
,
```
"AU"
```
). Default to
```
"ALL"
```
only if the user explicitly wants global.
Active vs all —
```
active_status="active"
```
is usually what you want. Inactive ads are historical and noisier.
Time window —
```
period
```
accepts
```
"last24h"
```
,
```
"last7d"
```
,
```
"last14d"
```
,
```
"last30d"
```
, or
```
"all_time"
```
. Match the window to the user's intent (weekly digest →
```
"last7d"
```
, trend research →
```
"last30d"
```
).
The job — what is this for?
- Creative trend report → use
```
search_facebook_ads
```
  , summarize patterns across hooks, CTAs, formats.
- Top advertiser snapshot → use
```
search_facebook_ads
```
  , group by
```
page_name
```
  .
- Lead list → use
```
search_facebook_ads_enriched
```
  , filter for rows with
```
contact_email
```
  or
```
contact_website
```
  .

在运行任何操作前，需确认以下内容：

搜索关键词——竞品可能瞄准的关键词。示例：
```
"meal kit delivery"
```
、
```
"AI marketing tools"
```
、
```
"skincare for sensitive skin"
```
。
国家——ISO代码（例如
```
"US"
```
、
```
"GB"
```
、
```
"AU"
```
）。仅当用户明确需要全球范围时，默认设为
```
"ALL"
```
。
活跃广告vs全部广告——通常选择
```
active_status="active"
```
。非活跃广告为历史数据，噪音较多。
时间范围——
```
period
```
接受
```
"last24h"
```
、
```
"last7d"
```
、
```
"last14d"
```
、
```
"last30d"
```
或
```
"all_time"
```
。根据用户意图匹配时间范围（每周摘要→
```
"last7d"
```
，趋势研究→
```
"last30d"
```
）。
用途——本次操作的目的是什么？
- 创意趋势报告→使用
```
search_facebook_ads
```
  ，总结钩子、CTA、格式的模式。
- 顶级广告主快照→使用
```
search_facebook_ads
```
  ，按
```
page_name
```
  分组。
- 线索列表→使用
```
search_facebook_ads_enriched
```
  ，筛选包含
```
contact_email
```
  或
```
contact_website
```
  的条目。

Phase 2 — Pull the ads

阶段2——抓取广告

search_facebook_ads(
    query="meal kit delivery",
    country="US",
    active_status="active",
    count=40,                # max for this tool
    period="last30d"
)

Each result row includes:

ad_archive_id

page_id

page_name

is_active

start_date_formatted

end_date_formatted

title

body

cta_text

link_url

caption

ad_library_url

page_categories

publisher_platform

For more than 40 ads, paginate by re-calling with

offset=40

offset=80

, etc.

For lead-gen with contact info:

search_facebook_ads_enriched(
    query="meal kit delivery",
    country="US",
    active_status="active",
    count=20,                # max for the enriched tool
    scrape_websites=True,
    filter_spam=False
)

Enriched rows add:

contact_email

contact_phone

contact_website

page_followers

page_rating

, address, business hours.

search_facebook_ads(
    query="meal kit delivery",
    country="US",
    active_status="active",
    count=40,                # 此工具的最大值
    period="last30d"
)

每条结果包含：

ad_archive_id

、

page_id

、

page_name

、

is_active

、

start_date_formatted

、

end_date_formatted

、

title

、

body

、

cta_text

、

link_url

、

caption

、

ad_library_url

、

page_categories

、

publisher_platform

。

若需获取超过40条广告，可通过重新调用并设置

offset=40

、

offset=80

等参数进行分页。

如需带联系信息的线索生成：

search_facebook_ads_enriched(
    query="meal kit delivery",
    country="US",
    active_status="active",
    count=20,                # 补充工具的最大值
    scrape_websites=True,
    filter_spam=False
)

补充后的条目新增：

contact_email

、

contact_phone

、

contact_website

、

page_followers

、

page_rating

、地址、营业时间。

Phase 3 — Get full creative for the most interesting ads (optional)

阶段3——获取最具价值广告的完整创意（可选）

search_facebook_ads

returns truncated bodies for some ads. To get the complete creative — including video URLs and images — call

get_facebook_ad_details

on the specific ads worth a deeper look:

get_facebook_ad_details(
    ad_archive_id="559220927273823",      # from search results
    page_id="328127803978438"             # from search results
)

Both args come from the same row in

search_facebook_ads

. Do this for the top 3–5 ads, not all 40 — each detail call is a separate Apify run.

search_facebook_ads

对部分广告返回截断的正文。如需获取完整创意——包括视频URL和图片——可对值得深入研究的特定广告调用

get_facebook_ad_details

：

get_facebook_ad_details(
    ad_archive_id="559220927273823",      # 来自搜索结果
    page_id="328127803978438"             # 来自搜索结果
)

两个参数均来自

search_facebook_ads

的同一条结果。仅对排名前3-5的广告执行此操作，而非全部40条——每次详情调用都是独立的Apify任务。

Phase 4 — Surface the intelligence

阶段4——展示情报

Present the findings inline in chat. Pick the format that matches the user's job from Phase 1.

Top advertisers (group by page):

Page	Active ads	Categories	Notable angle
Brand A	12	Restaurant, Meal Kit	"Skip the grocery store" hook in 8/12 ads
Brand B	7	Software, Subscription	Heavy on UGC video, "$1 first week" offer

Common CTAs and hooks:

Pattern	Count	Examples
`Sign up` CTA	18	…
`Shop now` CTA	12	…
Price-anchor opener ("From $X/week")	9	…
Founder-story opener	4	…

Recently launched ads (last 7 days):

Page	Started	CTA	Hook	Library URL
Brand A	2026-04-28	Sign up	"Skip the grocery run this week"	<ad_library_url>

Lead list (enriched only):

Page	Email	Website	Followers	Active ads
Brand A	hello@a.com	a.com	12K	7

在聊天中直接展示研究结果。选择与阶段1中用户用途匹配的格式。

顶级广告主（按页面分组）：

页面	活跃广告数	类别	显著角度
Brand A	12	Restaurant, Meal Kit	12条广告中有8条使用“跳过杂货店采购”钩子
Brand B	7	Software, Subscription	大量使用UGC视频，主打“首周1美元”优惠

常见CTA和钩子：

模式	数量	示例
`Sign up` CTA	18	…
`Shop now` CTA	12	…
价格锚点开头（“每周仅X美元起”）	9	…
创始人故事开头	4	…

近期上线广告（过去7天）：

页面	上线时间	CTA	钩子	广告库URL
Brand A	2026-04-28	Sign up	“本周跳过杂货店采购”	<ad_library_url>

线索列表（仅补充版）：

页面	邮箱	网站	粉丝数	活跃广告数
Brand A	hello@a.com	a.com	12K	7

Phase 5 — Recurring monitoring (optional)

阶段5——定期监控（可选）

If the user wants ongoing tracking:

Save the query, country, and
```
active_status
```
settings.
Re-run weekly with
```
period="last7d"
```
.
Brief becomes a delta report — new ads since the last run, advertisers that changed posting cadence, CTA / offer shifts.

This is when

competitor-intel

becomes the better skill — it handles multi-source diffing across many surfaces, not just Meta ads.

如果用户需要持续追踪：

保存查询关键词、国家和
```
active_status
```
设置。
每周重新运行，设置
```
period="last7d"
```
。
简报变为增量报告——自上次运行以来的新广告、发布节奏变化的广告主、CTA/优惠的变动。

此时

competitor-intel

是更合适的Skill——它可处理多来源的差异对比，不仅限于Meta广告。

Output standards

输出标准

Always cite the
ad_library_url
for any specific ad referenced in the brief — the user can click through to verify.
Aggregate before quoting. Don't paste raw ad bodies; extract the pattern and quote 1–2 representative examples.
Mark interpretation explicitly. "Observation: 8 of 10 top advertisers use a 'first week free' offer. Possible interpretation: …".
Note the time window. Every brief should state the search query, country, and date range it was generated from.

始终引用
ad_library_url
——简报中提及的任何特定广告都需附上该链接，用户可点击验证。
汇总后再引用。不要粘贴原始广告正文；提取模式并引用1-2个代表性示例。
明确标注解读内容。“观察：排名前10的广告主中有8家使用‘首周免费’优惠。可能的解读：……”。
注明时间范围。每份简报都应说明生成时使用的搜索关键词、国家和日期范围。