aso-competitors
Skill13 starsChanged 52 days agoMITView on GitHub
Use to analyze specific App Store competitors, compare listings side by side, or find keyword gaps between your app and named rival apps with the `aso` CLI. Trigger on "who are my competitors", "compare my app to X", "what keywords does Ring or Headspace rank for that I don't", or "keyword gap analysis", even if the user only names one competitor. Finds competitors via `aso search`, pulls their listings with `aso app`, and diffs keyword coverage against your app into quick-win, defend, battleground, aspirational, and ignore buckets. Not for general keyword brainstorming with no specific competitor in view, use `aso-keyword-research` for that.
In this repository7 other files it gives its agents.
- aso-auditSkill
- aso-conversionSkill
- aso-keyword-researchSkill
- aso-localizationSkill
- aso-metadataSkill
- asoSkill
- aso-trackingSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
If the user already named competitor apps, get their app IDs.
- Very specific: line 93
Don't chase difficulty far above what the app's ratings count can realistically win (see aso-keyword-research's ceiling table) just because …
≈ “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
ASO Competitor Analysis
Find keyword gaps and ranking opportunities by looking at who already ranks: not to copy them, but to find what they've validated that you haven't targeted yet.
Preflight: see the aso router skill.
Iron law
This is gap analysis, not copying. The #1 app for a term already owns it: chasing it head-on is expensive. The value is in terms they rank for that you don't, and terms where you can realistically outrank a specific competitor, not the whole field.
Step 1: Identify competitors
If the user already named competitor apps, get their app IDs. If not, find them from your own keyword data or a live search:
aso search "<core keyword>" --limit 20 -c US
aso keywords "<core keyword>" --app <yourAppId> -c US # topApps in the result are candidate competitorsPick 2-3 competitors that are: similar in function (not just category), comparable in scale (comparing a 100-review app to a 500k-review one is noise), and actively maintained.
Step 2: Pull their listings
aso app <competitorAppId> --lang en-USGives name, subtitle, developer, rating, ratings count, version, genres, description, supported languages. Extract every word from their title and subtitle: these are the keywords they've committed real estate to.
Step 3: Keyword-gap analysis
Build the word list from each competitor's title + subtitle, then score the gap terms against your own app:
aso keywords <competitor_title_words> <competitor_subtitle_words> --app <yourAppId> -c USThis returns popularity, difficulty, opportunity, and (because you passed --app) your current rank for each term. A null rank with the competitor visibly ranking is your gap.
Build the matrix:
| Keyword | Your rank | Competitor rank (from aso search) | Pop | Diff | Opportunity |
|-------------------|-----------|-------------------------------------|-----|------|-------------|
| security camera | 45 | 12 | 62 | 78 | 13.6 |
| baby cam | - | 5 | 44 | 18 | 36.1 |Get the competitor's actual position for a term with aso search "<term>" --limit 20 and locate their app ID in the results.
Step 4: Categorize
| Bucket | Condition | Action |
| Quick win | Competitor ranks, you don't; difficulty low relative to your app's authority (see the ceiling table in aso-keyword-research) | Add now |
| Defend | You outrank all watched competitors | Keep, monitor via aso-tracking |
| Battleground | Both rank, close positions, decent popularity | Consider promoting to title/subtitle |
| Aspirational | Competitor ranks well, but difficulty is well above your app's realistic ceiling | Backlog, revisit after ratings grow |
| Ignore | Low popularity and low relevance | Skip |
Step 5: Present and hand off
COMPETITIVE KEYWORD ANALYSIS: You vs Ring (ID 987654321)
QUICK WINS:
| Keyword | Their rank | Pop | Diff | Opportunity |
|------------|-----------|-----|------|-------------|
| baby cam | 5 | 44 | 18 | 36.1 |
| nanny cam | 34 | 35 | 15 | 29.8 |For quick wins, hand off to aso-metadata to actually fit them into title/subtitle/keywords and lint the result: don't edit metadata directly from this skill.
Step 6: Ongoing monitoring
Gap analysis is a snapshot; competitors keep moving. Set up a weekly or biweekly check as a standing complement to any one-off analysis, not a replacement for it:
aso app <competitorAppId> --lang en-US # re-pull title, subtitle, description, rating, ratingCountDiff against the last pull for: title/subtitle/description text changes (a competitor adding a term is a signal that term is working for them), and rating/ratingCount deltas (a sudden jump in ratings velocity often precedes or follows their own metadata or feature push). Log anything material and revisit the gap matrix if their metadata shifted meaningfully.
Rules
- Never suggest adding a competitor's brand name as a keyword. It risks App Review rejection and gains nothing Apple's algorithm rewards.
aso lintflags competitor-brand risk: trust it. - Don't chase difficulty far above what the app's ratings count can realistically win (see
aso-keyword-research's ceiling table) just because a competitor ranks there. - 2-3 competitors give a cleaner signal than a long list: more just adds noise.
- Re-run the full gap analysis after shipping quick-win keywords (2-4 weeks later, via
aso-tracking) to confirm the gap actually closed.
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.

