agentleFS
adswipefileadswipefile/adswipefile-plugin/skills/map-competitors/SKILL.md

map-competitors

Skill0 starsChanged 27 days agoMITView on GitHub

List a brand's direct competitors, indirect competitors and the brands whose ads are worth admiring, each with why it is on the list, its Facebook page and whether the AdSwipeFile ad library holds its ads. Use when setting up a brand, before tracking competitor ads, or for "who are my competitors", "map my competitors" or a competitor list.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep a candidate when you can say in one line why a customer would choose it instead (direct), what job it does instead (indirect), or what …

    line 40
  2. Distinctive:

    Never state how a competitor's ads performed.

    line 67
  3. Distinctive:

    Keep calls few: one search per brand, no ad reads in this skill.

    line 68

≈ “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

Map competitors

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=map-competitors. 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.

A competitor list decides whose reviews the user reads and whose ads they study, so each entry says why it is on the list and carries what the next skills need. Words and evidence rules: the creative-strategy skill's REFERENCE.md.

Three lists

  • Direct: same category, same buyer, a real alternative at checkout. Their ads are followed and their reviews read.
  • Indirect: a different category doing the same job, or the habit the product replaces (the failed fixes customers name). Their reviews explain switching; their ads are studied, not followed.
  • Admired: any category, kept for how they make ads (a format, a mechanic, a voice). Ads only.

1. Collect candidates

  • From the user: their product, buyer and offer, the competitors they already name, and what their customers say they tried before (reviews, support emails, survey answers). Ask them to paste, upload or link it, or read it from another connector they have.
  • From the product's own site and store page, when the user shares them.
  • Who advertises the category: search_library with two or three category words, then list_brands with the niche it names.

2. Qualify each one

Keep a candidate when you can say in one line why a customer would choose it instead (direct), what job it does instead (indirect), or what to learn from its ads (admired). Drop anything you can only justify by its name. Aim for three to eight direct, a handful of indirect, three to five admired; say when the market is thin.

For each kept brand, note what later steps need:

  • AdSwipeFile: whether the library has it (search_library with the plain name; a brand hit returns its slug). Check the hit is the brand, not a namesake. For the brands it lacks, offer to report them with submit_feedback (one call naming each brand and its Facebook page) so the library can add them; only on a yes.
  • Facebook page: its name and link, so a brand the library lacks can still be followed by name or page link on adswipefile.com/app/track.
  • Review pages: App Store or Google Play listing, Trustpilot, Amazon or the reviews section of its site. The user reads or exports these; label every review with the competitor's name.

3. Hand over the map

  1. One row per brand: name, list, the one-line reason, website, Facebook page, AdSwipeFile slug or "not in library", review pages, date checked. Put it in the reply, or a file when the client can write files.
  2. Show the map to the user before anything is followed: the lists decide what the next steps pull.

Rules

  • Base "in the library" on a search_library hit, never on a guess.
  • Competitors' customers and reviews stay labelled as the competitor's.
  • Never state how a competitor's ads performed; the library holds no results.
  • Keep calls few: one search per brand, no ad reads in this skill.

Done when every brand on the map has its list, its reason and the ids it has, and the user has seen it. Next: track-competitor-ads, then map-personas.

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.