agentleFS
asospyasospy/asospy-agent-skills/skills/keyword-research/SKILL.md

keyword-research

Skill1 starsChanged 47 days agoMITView on GitHub

Build an App Store / Google Play keyword shortlist around a seed term, with ASOSpy's keyword metrics (Apple popularity, Google volume, CPC, competition) and the apps that rank for each keyword. Use when the user asks for keywords, search terms or ASO keyword ideas for an app or niche. Needs the ASOSpy MCP server.

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use link-prospecting, seo-project-setup and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JwuthriSkill

    link-prospecting

    Find link prospects, discover contact paths, and draft outreach from SERPs and backlink signals.

    Also in 11 projects that use this

  • JwuthriSkill

    seo-project-setup

    Set up a durable local SEO workspace with project context, notes, goals, positioning, preferences, MCP checks, and Search Console data intake.

    Also in 11 projects that use this

  • akii-technologies-ltdSkill

    keyword-clustering

    Cluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "group keywords", "organize keywords", "keyword mapping", "topic clusters", "keyword grouping", "build a content plan", "pillar pages", "topical authority", "semantic clustering", or pastes a list of keywords.

    Also in 12 projects that use this

  • opencueSkill

    serp-analysis

    Use when the user asks to "analyze SERPs"; reviews ranking factors, features, intent, AI Overviews, and snippets. SERP分析/搜索结果

    Also in 6 projects that use this

  • +5 more from Jwuthri

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 50 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. Distinctive:

    Before an ASO audit or a title/subtitle rewrite.

    line 11
  2. Very specific:

    If an app was given: get_app_detail, then mark each keyword as used in the title, used in the subtitle / short description, or missing.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 50 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

Keyword research

When to use

  • "Find keywords for my meditation app", "what do people search for around X", "which keywords should I target".
  • Before an ASO audit or a title/subtitle rewrite.
  • To size demand for a niche (pair with app-discovery).

Inputs

InputDefaultNotes
SeedrequiredOne short term or phrase. Run several seeds for broad topics.
StoreallPicks which store's top apps each keyword row shows.
AppnoneOptional: the user's app, to check which keywords it already uses.

Tools

  • search_keywords — related keywords with metrics and when they were last saved (updatedAt for Google, appleUpdatedAt for Apple); sort by apple_popularity, volume, cpc, competition or keyword; filters contains, min_/max_apple_popularity, min_/max_volume_score, min_/max_cpc, min_/max_competition.
  • search_niches — the seed's market size (apps, developers, installs) plus related keywords.
  • get_app_detail — the user's app title, subtitle / short description and description.
  • live_keyword_metrics — one keyword measured live: source: "apple" for Apple popularity in a storefront, source: "google" for Google volume, CPC and competition. It saves Google values and US Apple values in ASOSpy, so later search_keywords calls show them. Costs 3 quota units, or 1 when the answer comes from the cache (cached: true); at most 10 per minute per workspace.

How search_keywords matches the seed: a word of up to 4 letters (for example vpn) matches only exactly, with no typo matching. A 5-letter word also matches with 1 typo, and a longer word with up to 2.

Workflow

  1. search_keywords with query: <seed>, sort: "apple_popularity", limit: 50.
  2. search_keywords again with sort: "volume", limit: 50.
  3. For long-tail ideas, search_keywords with query: <seed>, contains: <seed> and sort: "apple_popularity".
  4. Merge, drop duplicates and off-topic terms. Keep 15–25 keywords.
  5. Classify: head terms (high popularity), long-tail terms (specific, lower popularity), brand terms (a competitor's name — usually not worth targeting).
  6. If an app was given: get_app_detail, then mark each keyword as used in the title, used in the subtitle / short description, or missing.
  7. Optional: search_niches with the seed for the market size.
  8. Optional: live_keyword_metrics for the 3–5 shortlisted keywords that matter most when a figure is missing or stale (no or an old updatedAt / appleUpdatedAt), or when the user targets a storefront other than the US (source: "apple", storefront). Do not call it for every row: each live call costs 3 units. measured: false means the value is unknown, not 0.

Output

  1. A table: keyword, applePopularity, volume, competition, cpc, top ranking apps, type (head / long-tail / brand), used by the app (if given). Mark values from live_keyword_metrics as live, with their measuredAt date.
  2. The 5 keywords to target first, each with one line on why (demand vs. how strong the top apps are).
  3. Keywords to avoid and why.

Limitations

  • applePopularity from search_keywords is Apple Search Ads popularity for the US App Store only; live_keyword_metrics can measure another storefront, one keyword at a time. volume, cpc and competition are Google Ads figures, not store search counts.
  • competitionLevel is null when Google has no data for the keyword; that means "unknown", not "low".
  • The keyword list has no per-country split, and the top apps shown are from the US store.
  • The backend works on the 10,000 highest-volume matches for a seed, so a very broad seed can hide rare long-tail terms. Use narrower seeds or contains.
  • Seed words of up to 4 letters get no typo matching, so check their spelling.
  • A live live_keyword_metrics call costs 3 quota units when Apple or Google answers, and 1 unit when the answer comes from the cache (Apple results are cached for 24 hours, Google results for 7 days). A failed lookup is free: Apple or Google refused or failed (details.reason rate_limited, session_rejected or upstream_error), or ASOSpy did not run it (no session, busy, switched off, or over the 10-per-minute limit).
  • Each new live measurement also uses one of the workspace's monthly live refreshes (50 on Individual, 500 on Start-up, 2,000 on Business), shared with the ASOSpy website. When they are used up, the tool returns INSUFFICIENT_QUOTA with details.reason: "allowance_used" and details.resetsAt; keep using search_keywords for the stored values.
  • Apple popularity measured live outside the US is not saved: search_keywords keeps showing the US figure. Report the storefront figure from the live call.

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.