New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Krankie Audit

by n0an in n0an/VivaDicta

Run an ASO audit on canonical App Store metadata under ./metadata, then a krankie-based competitor keyword-gap analysis (no Astro subscription).

MITAuto-check passedMobile

Install Krankie Audit

skills CLI
$ npx skills add n0an/VivaDicta --skill krankie-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install n0an/VivaDicta krankie-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/n0an/VivaDicta.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/krankie-audit .claude/skills/krankie-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
krankie-audit
GitHub stars
130
Token cost
~1.3k tokens
SKILL.md length
518 words
Files
2
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Run an ASO audit on canonical App Store metadata under ./metadata, then a krankie-based competitor keyword-gap analysis (no Astro subscription).

  • Works in 2 steps: Offline Checks (unchanged) → krankie Competitor Rank-Gap Analysis
  • Tasks that involve App store release
  • SKILL.md covers Preconditions, Phase 1: Offline Checks…, Phase 2: krankie Competitor… and Output Format, plus 1 more section
  • Calls ssh and whisper

What it does

Krankie Audit is an agent skill from n0an/VivaDicta. Run an ASO audit on canonical App Store metadata under ./metadata, then a krankie-based competitor keyword-gap analysis (no Astro subscription). Krankie replacement for asc-aso-audit. Use after asc metadata pull.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Mobile, covering App store release, Static sites and blogs and Keyword research. It works with Astro. The repository describes itself as: iOS & watchOS speech-to-text app with AI voice keyboard, on-device RAG, and chat with your notes - powered by Apple Foundation Models, WhisperKit, NVIDIA Parakeet, and 20+ AI…. The licence is MIT.

When your agent uses it

  • Tasks that involve App store release
  • Tasks that involve Static sites and blogs
  • Tasks that involve Keyword research

Example prompts

  • “/krankie-audit”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Offline Checks (unchanged)
  2. krankie Competitor Rank-Gap Analysis

What it can do on your machine

Read from SKILL.md and the folder at commit db0b602. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • ssh
    • whisper

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use ssh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Krankie Audit loads about 1.3k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 518 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from n0an/VivaDicta at commit db0b602, republished under its MIT licence (© n0an). 518 words, ~1,282 tokens.

Download SKILL.mdSave it as .claude/skills/krankie-audit/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
krankie-audit
description
Run an ASO audit on canonical App Store metadata under `./metadata`, then a krankie-based competitor keyword-gap analysis (no Astro subscription). Krankie replacement for asc-aso-audit. Use after `asc metadata pull`.

ASO Audit (krankie)

Two-phase ASO audit. Phase 1 (offline metadata checks) is identical to asc-aso-audit and needs no network. Phase 2 replaces Astro's popularity/competitor analysis with krankie competitor rank-gap analysis.

What changes vs the Astro version: krankie gives rank position only - there is no popularity score, no difficulty score, and no keyword-suggestion engine. So Phase 2 finds gaps by competitor rank (keywords a competitor ranks well for that VivaDicta does not), not by popularity.

Preconditions

  • Metadata pulled into canonical files: asc metadata pull --app "6758147238" --version "X.Y.Z" --dir "./metadata".
  • For Phase 2: krankie tracking the app + competitors (the VPS at lobster@openclawtail is already set up; see krankie-rankings).

Phase 1: Offline Checks (unchanged)

Run the same offline checks as asc-aso-audit against ./metadata. Read .agents/skills/asc-aso-audit/references/aso_rules.md for the exact rules. Summary:

  1. Keyword waste - tokens in subtitle/name that also appear in keywords (already indexed, wasted budget).
  2. Underutilized fields - keywords < 90/100 chars, subtitle < 20/30 chars.
  3. Missing fields - empty subtitle/keywords/description/whatsNew.
  4. Bad separators - spaces after commas, semicolons, or pipes in keywords.
  5. Cross-locale gaps - non-primary locale keywords identical to en-US (not localized).
  6. Description keyword coverage - tracked keywords missing from the description (conversion, not indexing).

Metadata paths: app-info metadata/app-info/{locale}.json (subtitle); version metadata/version/{latest}/{locale}.json (keywords, description, whatsNew). Primary locale en-US.

Phase 2: krankie Competitor Rank-Gap Analysis

Pull current rankings for VivaDicta + the 3 tracked competitors from the VPS (canonical history):

bash
ssh lobster@openclawtail 'export PATH="$HOME/.bun/bin:$PATH"; krankie rankings --json'

Apps in the krankie DB:

  • VivaDicta 6758147238 (own)
  • Otter 1276437113, Wispr Flow 6497229487, Whisper Transcription 1668083311 (competitors, US)
Show full SKILL.md (275 more words)Show less
Steps
  1. Build a per-keyword rank table for US: VivaDicta rank vs each competitor's rank (current_rank, null = not in top 200).
  2. Surface gaps: keywords where a competitor ranks (especially top-50) and VivaDicta is unranked or much worse. These are the highest-value targets - a rival is capturing search traffic you are not.
  3. Rank gaps by competitor strength: sort by best competitor rank ascending (a keyword where Otter is #3 and we are unranked outranks one where a competitor is #150).
  4. Diff against metadata tokens: for each gap keyword, check whether its component tokens are present in subtitle + name + keywords of any locale. If the tokens are missing, that explains the gap and is an actionable add. If tokens are present but VivaDicta still doesn't rank, the issue is competition/authority, not coverage.
  5. Cross-field combo note: remember keywords combine within a locale across title + subtitle + keywords. Flag combos enabled by adding a single token (e.g. adding recorder when voice is already indexed enables "voice recorder").
Skip conditions
  • VPS unreachable - run krankie locally on the MacBook (krankie rankings --json), noting the local DB may be sparse; or skip Phase 2 with a note.
  • A keyword not tracked yet - add it: krankie keyword add 6758147238 "<kw>" --store us (and for competitors to compare).

Output Format

### ASO Audit Report (krankie)

**App:** VivaDicta - Speech to Text | **Primary Locale:** en-US
**Metadata source:** metadata/version/X.Y.Z

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

#### Offline Checks
| # | Check | Severity | Field | Locale | Detail |
...
**Summary:** X errors, Y warnings across Z locales

#### Competitor Rank-Gap (krankie, US)
| Keyword | VivaDicta | Otter | Wispr Flow | Whisper Trans. | In metadata? | Action |
|---------|-----------|-------|------------|----------------|--------------|--------|
| voice typing | - | #2 | #1 | - | tokens present | competition, not coverage |
| dictation keyboard | #164 | - | #1 | - | partial | reinforce combo |

#### Recommendations
1. [Errors first]
2. [Keyword waste]
3. [Utilization]
4. [Highest gap opportunities by competitor strength]

Notes

  • Phase 1 works with zero network access - the audit is useful even if the VPS/krankie is down.
  • No popularity data: prioritize by competitor rank, not popularity. If you later resubscribe to Astro, asc-aso-audit Phase 2 adds popularity + suggestions back.
  • After metadata changes, run krankie-rankings to measure impact (ranks settle over 1-2 weeks).
  • Related: krankie-rankings (dated rankings report), asc-aso-audit (Astro-based original).

© n0an, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/krankie-audit of n0an/VivaDicta.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit db0b602

Compare with similar skills

Krankie Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Krankie Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Krankie Audit this skilln0an/VivaDicta130—~1.3kAutomated safety check: PassMIT
Asc Aso AuditCamilleScholtz/swmpc2395 repos~2.6kAutomated safety check: PassEUPL-1.2
Content SEOjdevalk/skills105—~2.3kAutomated safety check: PassMIT
Metadata Optimizationappeeky/aso-skills2.2k—~1.5kAutomated safety check: PassMIT
Aso Routerappeeky/aso-skills2.2k—~2.7kAutomated safety check: PassMIT
Localizationappeeky/aso-skills2.2k—~1.5kAutomated safety check: PassMIT

Similar skills

  • Asc Aso Audit

    CamilleScholtz/swmpc

    Run an offline ASO audit on canonical App Store metadata under ./Store and surface keyword gaps using Astro MCP.

    239 GitHub starsUsed in 5 repos~2.6k tokens
    MobileAuto-check passed

  • Content SEO

    jdevalk/skills

    Audits a blog post draft or page copy for content-level SEO: search intent fit, focus keyphrase placement, E-E-A-T signals (experience, expertise, authoritativeness, trustworthiness), helpfulness…

    105 GitHub stars~2.3k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed

  • Metadata Optimization

    appeeky/aso-skills

    When the user wants to optimize App Store metadata — title, subtitle, keyword field, or description.

    2.2k GitHub stars~1.5k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed

  • Aso Router

    appeeky/aso-skills

    Single entry point that routes any ASO, App Store, Google Play, app marketing, paid UA, monetization, retention, reviews, ratings, market-intel, or app-analytics question to the correct specialist…

    2.2k GitHub stars~2.7k tokensUpdated 4 days ago
    MobileAuto-check passed

  • Localization

    appeeky/aso-skills

    When the user wants to localize their App Store listing for international markets.

    2.2k GitHub stars~1.5k tokensUpdated 4 days ago
    Marketing & SEOAuto-check passed

  • Astro SEO

    jdevalk/skills

    Audits and improves SEO for Astro sites. An agent skill from jdevalk/skills.

    105 GitHub stars~4.9k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed

More from n0an/VivaDicta

All 20 skills in this repo

  • Swiftdata Pro

    n0an/VivaDicta

    Writes, reviews, and improves SwiftData code using modern APIs and best practices.

    130 GitHub starsUsed in 1 repo~930 tokens
    Auto-check passed

  • iOS Simulator Skill

    n0an/VivaDicta

    21 production-ready scripts for iOS app testing, building, and automation.

    130 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

  • Asc Metadata Sync

    n0an/VivaDicta

    Sync and validate App Store metadata and localizations with asc, including legacy metadata format migration.

    130 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

  • Asc Aso Rankings

    n0an/VivaDicta

    Pull current keyword rankings from Astro MCP, compare against the previous rankings check, and save a new rankings file to the vault.

    130 GitHub stars~985 tokensUpdated yesterday
    Auto-check passed

  • Coverage Report

    n0an/VivaDicta

    Measure VivaDicta test code coverage from the terminal. An agent skill from n0an/VivaDicta.

    130 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Loc Report

    n0an/VivaDicta

    Count Swift lines of code across the VivaDicta codebase and refresh the production-vs-test history chart.

    130 GitHub stars~825 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Krankie Audit

What does Krankie Audit do?

Run an ASO audit on canonical App Store metadata under ./metadata, then a krankie-based competitor keyword-gap analysis (no Astro subscription). Krankie Audit is an agent skill from n0an/VivaDicta./metadata, then a krankie-based competitor keyword-gap analysis (no Astro subscription).

When should I use Krankie Audit?

Krankie Audit fits situations like: tasks that involve App store release; tasks that involve Static sites and blogs; tasks that involve Keyword research.

How do I install Krankie Audit in Claude Code?

Run `npx skills add n0an/VivaDicta --skill krankie-audit -a claude-code`. Or copy the skill folder (.agents/skills/krankie-audit in n0an/VivaDicta) into .claude/skills/krankie-audit in your project. Claude Code loads it when a task matches its description.

How do I install Krankie Audit in Codex?

Run `npx skills add n0an/VivaDicta --skill krankie-audit -a codex`. Or copy the skill folder (.agents/skills/krankie-audit in n0an/VivaDicta) into .agents/skills/krankie-audit in your project. Codex loads it when a task matches its description.

Can I use Krankie Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add n0an/VivaDicta --skill krankie-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/krankie-audit, .gemini/skills/krankie-audit, .github/skills/krankie-audit and .opencode/skills/krankie-audit in your project.

What does Krankie Audit need to run?

Going by SKILL.md and its folder, Krankie Audit needs the command-line tools its instructions call (ssh and whisper).

Does Krankie Audit access the network?

SKILL.md contains no URLs. Its commands use ssh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Krankie Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Krankie Audit use?

Krankie Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Krankie Audit use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Krankie Audit?

Skills that share tags, products or a category with Krankie Audit: Asc Aso Audit (CamilleScholtz/swmpc, 239 stars), Content SEO (jdevalk/skills, 105 stars), Metadata Optimization (appeeky/aso-skills, 2.2k stars) and Aso Router (appeeky/aso-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Krankie Audit?

n0an (a GitHub user) maintains it in n0an/VivaDicta, which has 130 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 9, 2026.

Source: n0an/VivaDicta on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.