agentleFS
Sign inStart free
xhoantranxhoantran/scrapeio-agent/skills/ad-library-research/SKILL.md

ad-library-research

Skill66 starsChanged 6 days agoMITView on GitHub

Research competitors ads in the Meta (Facebook and Instagram) Ad Library, Google Ads Transparency Center and LinkedIn Ad Library - active ads, creatives, copy, landing pages and how long ads have run. Use when the user asks what ads a company runs, wants ad inspiration, or wants to find brands that advertise in a niche. Uses the ScrapeIO API.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Active first: Start with status=ACTIVE in the user's country.

    line 20
  2. Very specific:

    With the scrapeio MCP server: use the named tool when it exists (for example tiktok_profile).

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ad library research

Endpoints (use call_endpoint with the path when using MCP)

  • Meta, by company: /v1/facebook/adLibrary/company/ads (companyName or pageId, country, status: ACTIVE, media_type, sort_by: total_impressions), 1 credit per page
  • Meta, by keyword: /v1/facebook/adLibrary/search/ads (query, country, status, search_type: keyword_exact_phrase), 1 credit per page
  • Google: /v1/google/company/ads (domain or advertiser_id, region, platform, format), up to 25 credits per call, so ask first
  • LinkedIn: /v1/linkedin/ads/search (company or keyword, countries), then /v1/linkedin/ad for one ad

Pass trim=true on Meta calls when you only need the copy and creative links.

Steps

  1. Company or keyword? For named competitors use the company endpoints. To find who advertises in a niche, search Meta ads by keyword and list the advertisers.
  2. Active first. Start with status=ACTIVE in the user's country.
  3. Longest running ads win. An ad that has run for months is usually profitable. Sort and highlight by start date.
  4. Read the creatives: headline, primary text, call to action, landing page, format (video, image, carousel). Group ads by angle (price, pain point, social proof, offer).

Output

Per competitor: number of active ads, main angles with example copy (quoted), the longest running ads with start dates and links, formats used, and landing pages. End with 3 angles the user could test. Never claim spend or impression numbers the data does not include.

How to call ScrapeIO

Needs SCRAPEIO_API_KEY. If it is missing, ask the user to get a free key at https://scrapeio.com/login (100 credits, no card). Never print the key.

  • With the scrapeio MCP server: use the named tool when it exists (for example tiktok_profile). For any other path, use call_endpoint with { "path": "/v1/...", "params": { ... } }.
  • Without MCP: curl -s "https://scrapeio.com<path>?<params>" -H "x-api-key: $SCRAPEIO_API_KEY".
  • Answers are in data; lists are data.items with data.cursor and data.has_more. Fields are the same on every platform: handle, followers, plays, likes, comments, shares, created_at, url.
  • 403 (private) and 404 (not found) are free: skip and move on. Retry 502 once. 402 means the user needs credits (https://scrapeio.com/pricing).
  • Watch credits_remaining and tell the user before a step would spend more than they expect.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free