agentleFS
Sign inStart free
AppmanAI-comAppmanAI-com/AppmanAi-MCP/skills/competitor-gap/SKILL.md

competitor-gap

Skill3 starsChanged 50 days agoMITView on GitHub

Find the keywords competitors rank for that a given app does not, ranked by how reachable each one is. Use when asked for a keyword gap analysis, what rivals rank for, or where an app is losing search traffic to competitors. Requires the AppmanAi MCP connector.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. Ryze-AI-Adgent/open-seo-mcp-skills★ 8.4ksame name
    2. semrush/skills★ 13same name
    3. DarynaRodriguez/seo-skills★ 1same name
    4. try-era/geo-skills★ 1same name
    5. eduardmur/searcherries-claude-plugin★ 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.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    2 · Establish the competitor set: If the user named competitors, resolve each with app_search (2 each).

    line 25
  2. Distinctive:

    A gap is not automatically an opportunity: Always pair it with demand and difficulty before recommending it.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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 keyword gap

The classic ASO question: what are they getting that we aren't?

Inputs

  • app — yours, as a package id or a name
  • competitors — optional; derive them if not given
  • store — ios or android
  • country — two-letter code, default US

Cost

Roughly 35–60 credits with a derived competitor set. Say the estimate before step 3.

Steps

1 · Resolve your app. app_search (2) if you were given a name; confirm the match.

2 · Establish the competitor set. If the user named competitors, resolve each with app_search (2 each). Otherwise app_similar (5) — the store's own notion of adjacency, which is cheaper and less biased than guessing.

Cap the set at three to five apps. Show it and get a nod before spending on it. A set the user disagrees with makes every later number worthless.

3 · Pull each side's keyword surface. keyword_app_suggestions (6) for your app and for each competitor. keyword_app_overlap (7) answers the overlap question directly when there are exactly two apps — prefer it for a head-to-head.

4 · Compute the gap. Terms that appear for one or more competitors and not for you. Rank by how many competitors hold each term: a keyword three rivals rank for is a stronger signal than one only a single app holds.

5 · Size it. keyword_metrics_sap_batch (9) over the gap list in one call. Drop the terms with no real demand — a gap nobody searches for is not a gap.

6 · Check reachability. keyword_metrics (4 each) on the top 5–8 by demand, and keyword_top_apps (5) on the two or three most attractive to see who actually holds the top slots. A term owned by three entrenched giants is not the same opportunity as one held by apps your size.

7 · Report. A table: keyword · how many competitors rank · SAP · difficulty · who holds the top slots · verdict. Then a short paragraph naming the two or three terms worth acting on this quarter, and why the rest can wait.

Rules

  • Get the competitor set agreed before spending. It is the one decision every later number depends on.
  • A gap is not automatically an opportunity. Always pair it with demand and difficulty before recommending it.
  • Name the holders. "You'd be displacing X and Y" is more useful than a difficulty score alone.
  • Batch the demand check. One keyword_metrics_sap_batch call, never a loop.

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.

Check your setup, free