sonar
Skill0 starsChanged 42 days agoMITView on GitHub
Use when the user wants App Store Optimization or app market research for iOS (App Store) or Android (Google Play) with Sonar — keyword research, keyword difficulty, metadata optimization, ASO audits, competitor analysis, review mining, revenue estimates, top charts, rank tracking, or App Store screenshot generation. Use the Sonar MCP tools for live data; several tools work with no account at all.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- avantmedialtd/skillstheir own version, first seen Oct 9, 2026
- ffroliva/gflow-clitheir own version, first seen Sep 14, 2026
- koderover/devops-skillstheir own version, first seen Mar 4, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ffroliva/gflow-cli★ 367same name
- koderover/devops-skills★ 7same name
- avantmedialtd/skills★ 1same 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- app-marketing-contextSkill
- aso-auditSkill
- competitor-analysisSkill
- keyword-researchSkill
- market-discoverySkill
- 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
8 rules. About 0 are common, 3 are distinctive, and 5 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill as the Sonar entry point for App Store and Google Play research.
- Distinctive: line 12
Read only the focused workflow that matches the user's intent:
- Very specific: line 32
Prefer live Sonar data through the MCP tools (all prefixed sonar_).
- Very specific: line 45
Ask only for the missing inputs that block the request: store (ios/android), app id, country, seed keywords, competitors.
- Very specific: line 49
Use difficulty_breakdown.beatable to shortlist keywords worth targeting, and explain *why* using the breakdown fields — don't just report a …
- Very specific: line 51
Prefer bulk calls: sonar_keyword_metrics takes up to 25 keywords per call, sonar_track_keywords up to 200.
- Distinctive: line 52
When a tool reports a missing plan, sign-in, or credits, tell the user plainly what it needs.
- Distinctive: line 53
When one workflow naturally leads to another, say so and load the next focused workflow only if needed.
≈ “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
Sonar
Use this skill as the Sonar entry point for App Store and Google Play research. It routes to the focused workflows in skills/, so agents that need a root SKILL.md can import the repository directly.
Route the request
Read only the focused workflow that matches the user's intent:
| User intent | Load |
| Find, evaluate, or prioritize keywords | skills/keyword-research/SKILL.md |
| Write or improve title, subtitle, keyword field, description | skills/metadata-optimization/SKILL.md |
| Compare apps, find keyword gaps, analyze the competitive landscape | skills/competitor-analysis/SKILL.md |
| Audit an app listing and score its ASO health | skills/aso-audit/SKILL.md |
| Mine reviews for complaints, praise, and feature requests | skills/review-analysis/SKILL.md |
| Estimate or benchmark app revenue, or read App Store Connect sales | skills/revenue-analysis/SKILL.md |
| Scan top charts, find movers and rising apps or niches | skills/market-discovery/SKILL.md |
| Track ranks, read how a tracked app is doing, competitors, alerts, portfolio | skills/rank-tracking/SKILL.md |
| Generate or translate App Store screenshots | skills/screenshot-studio/SKILL.md |
| Capture reusable app, audience, competitor, and goal context | skills/app-marketing-context/SKILL.md |
| Exact tool names, parameters, costs, and access tiers | skills/sonar-aso/SKILL.md |
For the full skill-to-tool matrix, read tools/REGISTRY.md only when you need exact coverage details.
Data access
Prefer live Sonar data through the MCP tools (all prefixed sonar_). In Claude, the Sonar plugin bundles the hosted server at https://trysonar.app/mcp:
- No account (free tier, per-IP daily limits):
sonar_app_search,sonar_app_lookup,sonar_app_aso_score,sonar_app_extract_keywords,sonar_keyword_suggestions,sonar_top_charts(shared 30 calls/day),sonar_keyword_metrics(5 keywords/day), andsonar_screenshot_layout_guide - Signed-in account (credits or plan quota):
sonar_keyword_search(10 credits),sonar_keyword_metrics(1 credit per keyword, no daily cap),sonar_app_reviews,sonar_app_revenue - Workspace reads (Indie or Agency plan; trial counts):
sonar_list_products,sonar_list_apps,sonar_get_app,sonar_app_overview,sonar_app_keywords,sonar_app_rankings,sonar_app_changes,sonar_keyword_rankings,sonar_competitor_keywords,sonar_competitor_landscape,sonar_discovered_keywords,sonar_review_insights,sonar_list_alerts,sonar_alert_events - Agency plan only:
sonar_portfolio, plussonar_app_salesandsonar_app_engagement(iOS, needs an App Store Connect connection) - Workspace writes (Indie or Agency plan):
sonar_create_product,sonar_track_app,sonar_track_competitor,sonar_track_keywords,sonar_scan_competitor,sonar_analyze_competitors,sonar_generate_review_insights,sonar_set_alert,sonar_star_keyword,sonar_update_keyword_note, plus the untrack/delete counterparts - Screenshot Studio:
sonar_screenshot_layout_guide,sonar_screenshot_devices,sonar_list_screenshot_sets,sonar_get_screenshot_set,sonar_create_screenshot_set,sonar_update_screenshot_set,sonar_delete_screenshot_set,sonar_add_screenshot,sonar_update_screenshot,sonar_delete_screenshot,sonar_set_screenshot_translations, andsonar_export_screenshots(local stdio server only)
If a tool asks the user to connect their Sonar account, that is the OAuth sign-in on the Sonar connector — tell the user, then retry. If no live data access is available, say what needs to be connected before making data-backed claims. Do not invent Sonar metrics.
Operating rules
- Ask only for the missing inputs that block the request: store (
ios/android), app id, country, seed keywords, competitors. - Store ids: iOS uses the numeric App Store id (e.g.
389801252), Android the package name (e.g.com.spotify.music). Workspace tools take Sonar UUIDs (app_id,product_id) fromsonar_list_apps/sonar_list_products— never pass a store id where a UUID is expected. - State the store, country, and filters used for every live data pull. Country defaults to
us. - Revenue and popularity are estimates — present them as such. iOS popularity is real Apple Search Popularity where available (
popularity_source: "apple"). App Store Connect numbers fromsonar_app_salesare the app's own reported data; proceeds are converted to USD approximately. - Use
difficulty_breakdown.beatableto shortlist keywords worth targeting, and explain why using the breakdown fields — don't just report a difficulty number. - Synthesize into decisions, tables, and next actions instead of dumping raw JSON.
- Prefer bulk calls:
sonar_keyword_metricstakes up to 25 keywords per call,sonar_track_keywordsup to 200. - When a tool reports a missing plan, sign-in, or credits, tell the user plainly what it needs. Don't pitch plans or purchases.
- When one workflow naturally leads to another, say so and load the next focused workflow only if needed.
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.

