spy
Skill20 starsChanged 4 months agoMITView on GitHub
Research competitor ads using the ad library. Use when the user wants to spy on competitor ads, see what ads a brand is running, browse competitor creatives, find top-performing ads, or do ad library research. Also use when the user mentions "ad library", "what ads is X running", "competitor creatives", or wants to track a new advertiser. Not for creating campaigns or pulling your own performance data.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Biznomad/claude-skillstheir own version, first seen Jul 14, 2026
- giovani-junior-dev/trafego-packtheir own version, first seen Jul 5, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- giovani-junior-dev/trafego-pack★ 1same name
- Biznomad/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- Very specific: line 18
Use a projectId from adkit_projects.
- Very specific: line 64
Add --json for automation.
≈ “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.
Files
Spy on Competitor Ads
The ad library (adkit_library) lets you search advertisers and browse their ads across platforms.
Requires AdKit to be connected — run /ads:setup first if needed.
Use a projectId from adkit_projects. Pass it at the top level of library calls to choose whose watchlist to read or change.
1. Find the advertiser
Search by name:
adkit_library entity: "advertisers" action: "search" projectId: "<projectId>" params: { query: "Notion" }Or browse by industry:
adkit_library entity: "advertisers" action: "list" params: { industry: "SaaS", sort: "spend" }Advertiser actions
| Action | Key params |
list | scope (library/watchlist), industry, category, platform, sort (name/newest/spend; default: newest), limit, page |
search | query (required), plus any list filters |
get | Top-level id — full advertiser details and stats |
similar | advertiserId — find similar advertisers |
add | website or a platform library URL required; name optional — find or create an advertiser and save it to the project watchlist |
track | Top-level id — save an existing advertiser to the project watchlist |
untrack | Top-level id — remove it from this project only |
My Watchlist
Omitted scope (or library) includes all advertisers. Use watchlist to match the selected project's My Watchlist in the dashboard. Filters, pagination, and totals apply inside that scope.
adkit_library entity: "advertisers" action: "list" projectId: "<projectId>" params: { scope: "watchlist" }
adkit_library entity: "advertisers" action: "track" projectId: "<projectId>" id: "<advertiserId>"
adkit_library entity: "advertisers" action: "untrack" projectId: "<projectId>" id: "<advertiserId>"Track/untrack return advertiserId and tracked: true/false. Repeating either is safe. Tracking requires an existing advertiser; untracking also removes stale membership for deleted advertisers. Untracking keeps the shared advertiser and other projects' watchlists. With only a name, search first and track the returned ID.
CLI equivalents:
adkit library advertisers list --scope watchlist --project <projectId>
adkit library advertisers search Notion --scope watchlist --project <projectId>
adkit library advertisers add --website notion.so --project <projectId>
adkit library advertisers track <advertiserId> --project <projectId>
adkit library advertisers untrack <advertiserId> --project <projectId>Add --json for automation.
2. Browse their ads
adkit_library entity: "ads" action: "search" params: { advertiser: "<advertiserId>", sort: "score" }Ad search params
| Param | Description |
advertiser | Advertiser ID filter |
query | Free text search across ad copy |
platform | meta, google, or linkedin |
format | image, video, or carousel |
sort | random, newest, oldest, score, most-used, longest, spend |
Advanced filters (min-days, min-spend, min-score, language) available via adkit_help path: "library ads search".
Get full details: adkit_library entity: "ads" action: "get" id: "<adId>" — returns creative content, copy, metadata, and landing page.
3. Clone an ad
Found an ad worth replicating? Clone it via the studio skill:
adkit_studio entity: "ads" action: "generate" params: { mode: "clone", aspectRatio: "1:1", references: [{ type: "library-ad", id: "<adId>" }] }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.