agentsclimarketplace
Sign in

Appstore aso auditor

Skill Xopoko/plug-n-skills/plugins/build-swift-apps/skills/appstore-aso-auditor

Run an offline ASO audit on canonical App Store metadata under `./metadata` and, when available, add Astro MCP keyword-gap analysis and Apple app-tag context. Use after `asc metadata pull`.From its SKILL.md

Install
npx -y skills add Xopoko/plug-n-skills --skill appstore-aso-auditor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 3 commands, including `asc app-tags list --app "APP_ID" --output json` and 2 more.
  • fetches URLsInstructs the agent to fetch 5 URLs, including get_app_keywords and 4 more.

SKILL.md

3.3 KB, 688 tokens by cl100k_base, as published. Nobody here has run it

App Store ASO Auditor

Audit the latest local metadata version first; Astro keyword gaps and Apple-generated tags are additive signals.

Preconditions

  • Canonical metadata from asc metadata pull --app "APP_ID" --version "1.2.3" --dir "./metadata".
  • Normalize asc migrate export or asc localizations download output before auditing.
  • Read references/aso_rules.md for rule details.
  • Use highest semantic version under metadata/version/.
  • Primary locale is en-US unless the user specifies another.

Paths:

  • App-info fields: metadata/app-info/{locale}.json
  • Version fields: metadata/version/{latest-version}/{locale}.json
  • App name may be absent; fetch with asc apps info list or ask before flagging it.

Offline Checks

  1. Keyword waste: tokens in subtitle or name also present in keywords. For Arabic also compare variants without ال; for CJK split by punctuation/character groups.
  2. Underused fields: keywords below 90/100 or subtitle below 20/30 chars.
  3. Missing fields: empty subtitle, keywords, description, whatsNew; only flag name if present and empty.
  4. Bad keyword separators: spaces after commas, semicolons, or pipes.
  5. Cross-locale gaps: non-primary locale keywords identical to the primary locale.
  6. Description coverage: keywords absent from description as conversion evidence, not Apple indexing evidence. Ignore Latin keywords in non-Latin descriptions when they target separate search paths.

Optional app tags:

asc app-tags list --app "APP_ID" --output json
asc app-tags view --app "APP_ID" --id "TAG_ID" --output json

Use tags only as classification evidence. Do not promise metadata changes will immediately alter Apple-generated tags.

Astro Keyword Gaps

If Astro MCP is connected and the app is tracked:

  • call get_app_keywords;
  • add per-store tracking with add_keywords for locales/territories before querying non-US stores;
  • run extract_competitors_keywords for 3-5 competitor app IDs;
  • call get_keyword_suggestions and search_rankings;
  • diff suggestions against title, subtitle, and keywords;
  • rank gaps by popularity and note source.

Skip with an explicit note when Astro is unavailable, the app is not tracked, or a store is not tracked.

Recommendations

Prioritize errors, keyword waste, utilization gaps, exact cross-locale duplicates, then Astro opportunities. Consider cross-field combos such as title/subtitle + keyword terms (for example adding a missing word that combines with an existing subtitle word).

Output

Produce one report for the latest version directory:

### ASO Audit Report
**App:** ... | **Primary Locale:** ...
**Metadata source:** metadata/version/<version>

#### Field Utilization
| Field | Value | Length | Limit | Usage |

#### Offline Checks
| # | Check | Severity | Field | Locale | Detail |

#### Keyword Gap Analysis
| Keyword | Popularity | Source | In Metadata? | Suggested Action |

#### Recommendations
1. ...

After edits, re-run the audit. For keyword-only follow-up prefer asc metadata keywords diff/apply/sync.

What ships with it: 1 file

3.9 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most audit compliance skills give in 688 tokens

Counted across 960 of the 1,589 authors here whose files we hold, read 2026-09-06

  • Read product marketing context before asking questionsin 29 of 960, across 11 files
  • Rank findings by severityin 29 of 960, across 22 files
  • Generate audit reportin 22 of 960
  • Run the audit scriptin 20 of 960, across 19 files
  • Generate a prioritized action plan reportin 19 of 960, across 11 files
  • Ensure one H1 per pagein 15 of 960, across 5 files
  • Ensure sitemap exists and is accessiblein 14 of 960, across 4 files
  • Verify alt text on all imagesin 12 of 960, across 3 files
  • Determine the audit scope before startingin 12 of 960, across 4 files
  • Verify important pages allowed in robots.txtin 11 of 960, across 2 files
  • Detect business type from homepage signalsin 11 of 960, across 7 files
  • Delegate specialized tasks to subagentsin 11 of 960, across 7 files

Said here and by no other author read

  • Audit the latest local metadata version first
  • Use highest semantic version under metadata version
  • Treat primary locale as en-US unless specified
  • Check for keyword waste in subtitle or name
  • Check for underused metadata fields
  • Check for bad keyword separators

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.