Meta Ads Library

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.

Out of scope — defer to other skills

Requirements

• 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.

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

Tool surface

Critical rules

1. Public-only data. The Meta Ads Library is public. Don't attempt to bypass any access control or scrape private content.
2. Count limits differ between tools. searchfacebookads allows count up to 40. searchfacebookads_enriched caps at 20 — exceeding this returns an error.
3. getfacebookaddetails needs two IDs. Both adarchiveid and pageid are required. Both are returned in every searchfacebookads result row — pass them through together.
4. 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 searchfacebookads.
5. Apify-backed tools fail intermittently. Expect occasional "fetch failed" responses. Retry once after a short delay before reporting the source as missing.
6. 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.

Workflow

Phase 1 — Define the query

Before running anything, agree on:

1. The search query — keyword(s) competitors would target. Examples: "meal kit delivery", "AI marketing tools", "skincare for sensitive skin".
2. Country — ISO code (e.g. "US", "GB", "AU"). Default to "ALL" only if the user explicitly wants global.
3. Active vs all — active_status="active" is usually what you want. Inactive ads are historical and noisier.
4. 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").
5. The job — what is this for?

- Creative trend report → use searchfacebookads, summarize patterns across hooks, CTAs, formats. - Top advertiser snapshot → use searchfacebookads, group by pagename. - Lead list → use searchfacebookadsenriched, filter for rows with contactemail or contactwebsite.

Phase 2 — Pull the ads

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

Each result row includes: adarchiveid, pageid, pagename, isactive, startdateformatted, enddateformatted, title, body, ctatext, linkurl, caption, adlibraryurl, pagecategories, 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: contactemail, contactphone, contactwebsite, pagefollowers, page_rating, address, business hours.

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

searchfacebookads returns truncated bodies for some ads. To get the complete creative — including video URLs and images — call getfacebookad_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 searchfacebookads. Do this for the top 3–5 ads, not all 40 — each detail call is a separate Apify run.

Phase 4 — Surface the intelligence

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

Top advertisers (group by page):

Common CTAs and hooks:

Recently launched ads (last 7 days):

Lead list (enriched only):

Phase 5 — Recurring monitoring (optional)

If the user wants ongoing tracking:

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

This is when [competitor-intel](../competitor-intel) becomes the better skill — it handles multi-source diffing across many surfaces, not just Meta ads.

Output standards

• Always cite the adlibraryurl 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.