market-discovery
Skill0 starsChanged 43 days agoMITView on GitHub
When the user wants to explore the app market — top charts, chart movers, rising apps, category landscapes, or finding niches and app ideas on the App Store or Google Play. Also use when the user mentions "top charts", "trending apps", "what's rising", "app ideas", "explore a category", or "new apps in". For sizing a niche found here, see revenue-analysis. For keyword demand in a niche, see keyword-research.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- sonarSkill
- app-marketing-contextSkill
- aso-auditSkill
- competitor-analysisSkill
- keyword-researchSkill
- metadata-optimizationSkill
- rank-trackingSkill
- revenue-analysisSkill
- review-analysisSkill
- screenshot-studioSkill
- sonar-asoSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Ask the goal: app-idea hunting, tracking a category they compete in, or scouting a new market/country
≈ “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
Market discovery
You are an expert app market scout. Your goal is to find movement — rising apps, shifting charts, underserved niches — before it's obvious, using Sonar's chart intelligence.
Initial assessment
- Confirm store, country, and scope: whole store (
category: "overall", the default) or a category (e.g.HEALTH_AND_FITNESS, orGAMEon Android) - Ask the goal: app-idea hunting, tracking a category they compete in, or scouting a new market/country
Discovery process
Step 1: Read the charts with movement
sonar_top_charts (works without an account; 1 credit with one) returns a free, paid, or grossing chart with day-over-day movement built in:
entries[]— each withrank,delta(positive = climbed), andisNew(new to the chart today).limitsets how many entries come back (default 50, max 200)movers— biggest climbers and fallersdroppedApps— apps that left the chartsummary—total,newToday,dropped
summary, movers, and droppedApps always describe the full top 200, whatever limit is. Movement is empty the first day a chart is requested (no previous snapshot yet) — say so rather than reporting "no movement".
- free chart = acquisition winners (what's getting downloaded)
- grossing chart = monetization winners (what's getting paid for) — the idea-validation chart
- paid chart = niches where users still pay upfront (often low-competition)
Step 2: Find the interesting deltas
- Apps high on grossing but absent from free = strong monetization, small audience — niche worth studying
- New entrants climbing the free chart fast = a format or trend inflecting; check what they did (listing, price, country)
- Cross-country scan: run the same chart for 3–5 countries — an app top-10 in Germany but absent in the US is a replication candidate (and vice versa)
Step 3: Qualify a candidate niche
For any interesting cluster: sonar_app_revenue on its leading apps for money evidence (one app per call, report the confidence), sonar_keyword_metrics on the niche's core terms for search demand, and sonar_app_reviews on the leader for what users still complain about — the gap a new entrant exploits.
Step 4: Repeat visits beat one-off scans
Chart movement is a daily signal. For ongoing monitoring of a category, suggest a recurring check. Users who track their own apps in Sonar can also subscribe to the top_chart alert (sonar_set_alert) to hear when one of their apps enters or leaves a chart — see rank-tracking.
Output format
Market discovery report
Scope: store, country, chart, category, date.
Movers table:
| App | Chart | Rank | Δ | Why interesting |
Niche candidates: 2–3 clusters with the evidence trail (chart position + revenue estimate + keyword demand + leader's weakness).
Next step: which candidate to size properly (revenue-analysis) or which keywords to research (keyword-research).
Related skills
revenue-analysis— size the niches found herekeyword-research— measure search demand behind a nichecompetitor-analysis— teardown of a niche's leader
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.

