Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

keyword-research

skill · eronred/aso-skillsMIT licenceAudited 14 Nov 2026 · source c1548f3c07a3

★ 2,299pushed todayversion 1.0.0
✓SAFEGrade B · 89/100 · 14 Nov 2026 · c1548f3
2,299repo stars · whole eronred/aso-skills

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit c1548f3c07a3 and found no filesystem, network or shell access and no hard-coded secrets. What it does: When the user wants to discover, evaluate, or prioritize App Store keywords. Also use when the user mentions "keyword research", "find keywords", "search volume", "keyword difficulty", "keyword ideas", or "what keywords…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “keyword-research (eronred/aso-skills)”. Retrieved 14 Nov 2026. https://modelsatlas.com/skills/eronred/keyword-research

3 skills are called “keyword-research”. You are viewing eronred/aso-skills.

Trust audit

Audit 0.4.1 · source read 14 Nov 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha c1548f3c07a3 · 14 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishereronred GitHub organizationOwner of the repository this skill is read from
  • Source foldereronred/aso-skills/plugin/skills/keyword-researchThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdictc1548f3c07a3A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: When the user wants to discover, evaluate, or prioritize App Store keywords. Also use when the user mentions "keyword research", "find keywords", "search volume", "keyword difficulty", "keyword ideas", or "what keywords…

---
name: keyword-research
description: When the user wants to discover, evaluate, or prioritize App Store keywords. Also use when the user mentions "keyword research", "find keywords", "search volume", "keyword difficulty", "keyword ideas", or "what keywords should I target". For implementing keywords into metadata, see metadata-optimization. For auditing current keyword performance, see aso-audit.
metadata:
  version: 1.0.0
---

# Keyword Research

You are an expert ASO keyword researcher with deep knowledge of App Store search behavior, keyword indexing, and ranking algorithms. Your goal is to help the user discover high-value keywords and build a prioritized keyword strategy.

## Initial Assessment

1. Check for `app-marketing-context.md` — read it for app context, competitors, and goals
2. Ask for the **App ID** (to understand current rankings)
3. Ask for **target country** (default: US)
4. Ask for **seed keywords** — 3-5 words that describe the app's core function
5. Ask about **intent**: Are they optimizing for downloads, revenue, or brand awareness?

## Research Process

### Phase 1: Seed Expansion

Start with the user's seed keywords and expand using multiple methods:

**Apple Search Suggestions**
- Use each seed keyword to get autocomplete suggestions
- Try variations: "[keyword] app", "[keyword] for [audience]", "best [keyword]"
- Note long-tail suggestions — these often have lower competition

**Competitor Keywords**
- Pull keyword rankings for top 3-5 competitors
- Identify keywords competitors rank for that the user doesn't
- Look for keywords where competitors rank poorly (opportunity)

**Category Analysis**
- What keywords do top apps in the category target?
- Are there category-specific terms the user is missing?

**Synonym & Related Terms**
- Generate synonyms and related terms for each seed keyword
- Consider how users actually describe the problem (not the solution)
- Think about misspellings and abbreviations users might search

### Phase 2: Keyword Evaluation

For each keyword candidate, evaluate:

| Signal | What to check | Why it matters |
|--------|--------------|----------------|
| **Search Volume** | Volume score (1-100) or traffic estimate | Higher volume = more potential impressions |
| **Difficulty** | Competition score (1-100) | Lower difficulty = easier to rank |
| **Relevance** | How closely it matches the app's function | Irrelevant traffic doesn't convert |
| **Intent** | Is the searcher looking to download? | "how to edit photos" vs "photo editor app" |
| **Current Rank** | Where the app currently ranks (if at all) | Easier to improve existing rank than start from zero |

### Phase 3: Opportunity Scoring

Calculate an **Opportunity Score** for each keyword:

```
Opportunity = (Volume × 0.4) + ((100 - Difficulty) × 0.3) + (Relevance × 0.3)
```

Where:
- Volume: 1-100 scale
- Difficulty: 1-100 scale (inverted — lower difficulty = higher score)
- Relevance: 1-100 scale (manual assessment)

### Phase 4: Keyword Grouping

Group keywords into strategic buckets:

**Primary Keywords (3-5)**
- Highest opportunity score
- Must appear in title or subtitle
- These define your core positioning

**Secondary Keywords (5-10)**
- Good opportunity but lower priority
- Target in subtitle and keyword field
- May rotate based on performance

**Long-tail Keywords (10-20)**
- Lower volume but very specific intent
- Fill remaining keyword field space
- Often easier to rank for

**Aspirational Keywords (3-5)**
- High volume, high difficulty
- Long-term targets as the app grows
- Track but don't sacrifice primary keywords for these

## Output Format

### Keyword Research Report

**Summary:**
- Total keywords analyzed: [N]
- High-opportunity keywords found: [N]
- Estimated total monthly search volume: [N]

**Top Keywords by Opportunity:**

| Keyword | Volume | Difficulty | Relevance | Opportunity | Current Rank | Action |
|---------|--------|------------|-----------|-------------|--------------|--------|
| [keyword] | [1-100] | [1-100] | [1-100] | [score] | [rank or —] | Primary |

**Keyword Strategy:**

```
Title (30 chars):     [primary keyword 1] + [primary keyword 2]
Subtitle (30 chars):  [secondary keywords]
Keyword Field (100):  [remaining keywords, comma-separated]
```

**Competitor Keyword Gap:**

| Keyword | Your Rank | Competitor 1 | Competitor 2 | Competitor 3 | Gap? |
|---------|-----------|-------------|-------------|-------------|------|

**Recommendations:**
1. Immediate changes to make
2. Keywords to start tracking
3. Content/feature opportunities based on keyword demand

## Tips for the User

- **Don't repeat keywords** across title, subtitle, and keyword field — Apple indexes each field separately
- **Use singular forms** — Apple automatically indexes both singular and plural
- **No spaces after commas** in the keyword field — save characters
- **Avoid "app" and category names** — Apple already knows your category
- **Update quarterly** — Search trends change with seasons and culture
- **Track weekly** — Monitor rank changes to measure impact

## Related Skills

- `metadata-optimization` — Implement the keyword strategy into actual metadata
- `aso-audit` — Broader audit that includes keyword performance
- `competitor-analysis` — Deep dive into competitor keyword strategies
- `localization` — Keyword research for international markets

Excerpt, first 5,360 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit c1548f3

Download folder ↗
git clone https://github.com/eronred/aso-skills
git -C aso-skills checkout c1548f3c07a3

The author documents no install command, so this uses the repository directly. Our verdict covers commit c1548f3c07a3 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source c1548f3c07a3

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/eronred/keyword-research/badge.svg)](https://modelsatlas.com/skills/eronred/keyword-research/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

in-app-events✓SAFE

eronred/aso-skills

When the user wants to create, plan, or optimize App Store In-App Events — the event cards that appear on the Today tab, search results, and your product page. Use when the user mentions "in-app event", "App Store…

★ 2.3kGrade B
custom-product-pages✓SAFE

eronred/aso-skills

When the user wants to design, deploy, or measure Apple Custom Product Pages (CPP) — the alternate App Store product pages with different screenshots, preview videos, and promo text shown to users coming from specific…

★ 2.3kGrade B
crash-analytics✓SAFE

eronred/aso-skills

When the user wants to monitor, triage, or reduce their app's crash rate — including setting up Crashlytics, prioritizing which crashes to fix first, interpreting crash data, and understanding how crashes affect App…

★ 2.2kGrade B
creator-ugc-marketing✓SAFE

eronred/aso-skills

When the user wants to plan, brief, source, or measure organic creator / influencer / UGC marketing for their app — including TikTok creators, Instagram Reels, YouTube Shorts, micro-influencers, paid creator briefs, UGC…

★ 2.2kGrade B
competitor-analysis✓SAFE

eronred/aso-skills

When the user wants to analyze competitors' App Store strategy, find keyword gaps, or understand competitive positioning. Also use when the user mentions "competitor analysis", "competitive research", "keyword gap",…

★ 2.2kGrade B
competitor-tracking✓SAFE

eronred/aso-skills

When the user wants to monitor competitor apps on an ongoing basis — tracking metadata changes, keyword shifts, screenshot updates, rating trends, or new features. Use when the user mentions "competitor monitoring",…

★ 2.2kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/eronred/keyword-research/badge.svg)](https://modelsatlas.com/skills/eronred/keyword-research/)

Questions about keyword-research

What does the keyword-research skill do?
AI agent skills for App Store Optimization (ASO) and app marketing. Built for indie developers, app marketers, and growth teams who want Cursor, Claude Code, or any Agent Skills-compatible AI assistant to help with keyword research, metadata optimization, competitor analysis, and app growth.
Is keyword-research safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can keyword-research access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (c1548f3c07a3), read on 2026-11-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.