track-competitor-ads
Skill0 starsChanged 27 days agoMITView on GitHub
Follow a brand's competitors on AdSwipeFile so their new Meta ads show up, and read what each one keeps running: brand patterns, longest-running ads, hooks, formats and offers. Use after mapping competitors, when setting up a brand, or for "track my competitors' ads", "follow these brands", "watch competitor ads" or "pull a competitor's ads".
In this repository14 other files it gives its agents.
- audit-ad-creativeSkill
- competitor-adsSkill
- creative-strategySkill
- find-winning-adsSkill
- generate-ad-conceptsSkill
- get-startedSkill
- map-competitorsSkill
- map-personasSkill
- pick-creative-mechanicSkill
- record-creative-learningSkill
- review-saved-adsSkill
- teach-ad-breakdownSkill
- weekly-competitor-reviewSkill
- write-hooks-from-adsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
Not in the library: the user can find and follow it by name or Facebook page link on adswipefile.com/app/track, and, with their go-ahead, …
- Very specific: line 46
Write a short section per brand: what it keeps running (with run lengths), its most common structure from brand_patterns, and the moves …
- Very specific: line 56
Keep calls few: one longest-running page and one get_ads call per brand.
≈ “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.
Files
Track 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: addhttps://adswipefile.com/api/mcpas a custom connector. Other clients: https://adswipefile.com/docs/mcp?utm_source=agent-skill&utm_medium=referral&utm_campaign=track-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.
Following puts a competitor's new ads in front of the user; the library reads and tags them
(breakdowns, brand patterns) for study. Neither says how a competitor's ad performed: a long run is a
reason to study it. Words and evidence rules: the creative-strategy skill's REFERENCE.md.
Input: the direct and admired brands from map-competitors, or the brands the user names.
1. Follow them
search_librarywith each plain name. Check the hit is the brand, not a namesake.- In the library: with the user's go-ahead,
follow_brandits slug, so its new ads show inlist_followed_ads. For an agency, follow in the client'sworkspace(list_workspacesonce), so each client keeps its own competitors.list_followed_brandsshows who is already followed. If the answer says nothing was followed, relay it once and do not retry. - Not in the library: the user can find and follow it by name or Facebook page link on
adswipefile.com/app/track, and, with their go-ahead, you can ask for it to be added to the
library with
submit_feedback(one call naming every missing brand and its Facebook page). Say which brands need this; do not tear down a similar brand instead.
2. First read
For each followed library brand. With more than three, get_usage first says how many calls
are left; read the brands that matter most first.
list_adswithbrand(the first page carriesbrand_patterns): the most common structure, top visual format and hook tactic, and the share of read ads with each trait. When it carries anoteinstead, pass it on once with its link and work from the ads.list_adswithbrandandsort: "longest_running",limit10.get_adson three to six of those, spread across formats: hook tactic, visual format, mechanic (read fromstructureandbreakdown), offer.
Write a short section per brand: what it keeps running (with run lengths), its most common
structure from brand_patterns, and the moves worth borrowing, each with a linked ad. Put it in the
reply, or a file when the client can write files. Offer to keep the best references with save_ad
or on a board (create_board, add_ad_to_board); write only when the user agrees.
Rules
- Shares of read ads, run lengths and dates only; never spend, results or "what works for them".
- Link every ad cited by its
url. - Say the read covers the brand's ads in this library, not everything it has run.
- Keep calls few: one longest-running page and one
get_adscall per brand.
Done when every direct and admired brand that advertises is followed on AdSwipeFile or handed to the
user to follow or request, and has its first-read notes. Weekly after that:
weekly-competitor-review; audit-ad-creative or teach-ad-breakdown for the ads worth a closer
look.
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
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.

