agentleFS
adswipefileadswipefile/adswipefile-plugin/skills/competitor-ads/SKILL.md

competitor-ads

Skill0 starsChanged 27 days agoMITView on GitHub

Show what ads a brand or competitor is running in the AdSwipeFile ad library, and sum up the formats, hooks, angles and offers it repeats, with a link to every ad cited. Use for "what ads is {brand} running", "show me my competitor's Facebook ads", competitor research, spying on a competitor's creatives, or a brand creative teardown.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Call list_ads with the brand slug (limit 20 to 30).

    line 19
  2. Very specific:

    Read a sample of five to eight ads with get_ad, spread across the formats you counted, for their copy and audiences.

    line 21
  3. Very specific:

    If the user follows the brand on AdSwipeFile, list_followed_ads adds its newest Meta ads, launched since the library last filed them.

    line 30
  4. Distinctive:

    Never state an ad's results: spend, ROAS, conversions, or that one ad beat another.

    line 39
  5. Very specific:

    If get_ad returns an ad without its copy, with a line saying so, base the angles on the ad's name, description and formats, and pass that …

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Competitor ads

Needs the AdSwipeFile connector. This skill reads the AdSwipeFile ad library of Meta ads through its MCP server. If no AdSwipeFile tools (search_library, list_ads) are available, say so before anything else and give the step for this host. Claude Code: claude mcp add --transport http adswipefile https://adswipefile.com/api/mcp. claude.ai or ChatGPT: add https://adswipefile.com/api/mcp as a custom connector. Other clients: https://adswipefile.com/docs/mcp?utm_source=agent-skill&utm_medium=referral&utm_campaign=competitor-ads. Connecting opens a sign-in to an AdSwipeFile account. Steps that need only the user's own material can go on; never invent ads, brands or links in place of the library.

  1. Find the brand with search_library. If no brand matches, say the library does not have it; do not tear down a similar brand instead.
  2. Call list_ads with the brand slug (limit 20 to 30). Count the formats and niches across the results.
  3. Read a sample of five to eight ads with get_ad, spread across the formats you counted, for their copy and audiences. Keep to that sample; do not read every ad.
  4. Report:
    • Formats: which ones the brand leans on, with counts from step 2.
    • Angles and hooks: the recurring promises, pains and openings, each with a link to an ad that shows it.
    • Offers: discounts, bundles, guarantees or free trials that appear.
    • Audiences: who the ads address, from the audiences field.
  5. If the user follows the brand on AdSwipeFile, list_followed_ads adds its newest Meta ads, launched since the library last filed them. Cite each with its url.

Rules

  • Base every claim on an ad you listed or read, and link that ad's url.
  • Say the teardown covers the brand's ads in this library, not everything the brand has run.
  • Never state an ad's results: spend, ROAS, conversions, or that one ad beat another. The library holds no such data. "Winning" in this library means an ad the brand kept running and that was filed as worth studying; a long run (sort: "longest_running") or many variants is a reason to study an ad, not proof that it performed.
  • If get_ad returns an ad without its copy, with a line saying so, base the angles on the ad's name, description and formats, and pass that line on once.

Keep watching it

Offer, once, to follow the brand (follow_brand) so its new ads show up in list_followed_ads and the weekly review, and to save the ads cited (save_ad) or put them on a board for this competitor (create_board, add_ad_to_board). Only on a yes.

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.