Agent skill

Krankie Rankings

Pull VivaDicta App Store keyword rankings via krankie (free, self-hosted), compare against the previous check, and write a dated rankings report to the Obsidian vault.

MITAuto-check passedMobile

Install Krankie Rankings

skills CLI

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

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

GitHub CLI

$ gh skill install n0an/VivaDicta krankie-rankings --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-rankings .claude/skills/krankie-rankings && 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/

Paste into Claude Code

Install the "krankie-rankings" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/krankie-rankings into .claude/skills/krankie-rankings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "krankie-rankings", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/n0an/VivaDicta/tree/main/.agents/skills/krankie-rankings

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add n0an/VivaDicta --skill krankie-rankings -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta krankie-rankings --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

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

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "krankie-rankings" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/krankie-rankings into .agents/skills/krankie-rankings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "krankie-rankings", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add n0an/VivaDicta --skill krankie-rankings -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta krankie-rankings --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

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

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "krankie-rankings" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/krankie-rankings into .cursor/skills/krankie-rankings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "krankie-rankings", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/n0an/VivaDicta.git --path .agents/skills/krankie-rankings

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add n0an/VivaDicta --skill krankie-rankings -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta krankie-rankings --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

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

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "krankie-rankings" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/krankie-rankings into .gemini/skills/krankie-rankings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "krankie-rankings", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install n0an/VivaDicta krankie-rankings

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add n0an/VivaDicta --skill krankie-rankings -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

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

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "krankie-rankings" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/krankie-rankings into .github/skills/krankie-rankings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "krankie-rankings", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add n0an/VivaDicta --skill krankie-rankings -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta krankie-rankings --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

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

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "krankie-rankings" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/krankie-rankings into .opencode/skills/krankie-rankings/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "krankie-rankings", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: krankie-rankings
GitHub stars: 130
Token cost: ~1.4k tokens
SKILL.md length: 568 words
Files: 2
Skills in repo: 20
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Pull VivaDicta App Store keyword rankings via krankie (free, self-hosted), compare against the previous check, and write a dated rankings report to the Obsidian vault.

Works in 4 steps: Run a fresh check + generate the report… → Read the produced report → Compare against the previous check → …
Tasks that involve App store release
SKILL.md covers Architecture: VPS is the…, Tracked set (the documented…, Steps and Report format, plus 2 more sections
Calls whisper, ssh and bun

What it does

Krankie Rankings is an agent skill from n0an/VivaDicta. Pull VivaDicta App Store keyword rankings via krankie (free, self-hosted), compare against the previous check, and write a dated rankings report to the Obsidian vault. Krankie-based replacement for asc-aso-rankings (no Astro subscription required).

Its SKILL.md is about 1.4k 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 and Static sites and blogs. It works with Astro and Obsidian. 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

Example prompts

“/krankie-rankings”

Workflow steps

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

Run a fresh check + generate the report (VPS)
Read the produced report
Compare against the previous check
Present the comparison report

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:
- whisper
- ssh
- bun
- scp
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use ssh and scp, 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 Rankings loads about 1.4k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 568 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~66
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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). 568 words, ~1,352 tokens.

Download SKILL.mdSave it as .claude/skills/krankie-rankings/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: krankie-rankings
description: Pull VivaDicta App Store keyword rankings via krankie (free, self-hosted), compare against the previous check, and write a dated rankings report to the Obsidian vault. Krankie-based replacement for asc-aso-rankings (no Astro subscription required).
argument-hint: optional notes, e.g. "2 week check"

ASO Rankings Check (krankie)

Pull keyword rankings with krankie instead of Astro MCP, compare against the previous check, and save a dated rankings file to the Obsidian vault.

This is the no-subscription replacement for asc-aso-rankings. krankie is MIT-licensed, stores history in local SQLite, and reads ranks from the public App Store search API. The trade-off vs Astro: krankie reports rank position only - no popularity or difficulty scores, and tracks the top 200 (Astro tracked top 250).

Architecture: VPS is the source of truth

VPS (lobster@openclawtail) runs krankie under a daily cron (krankie cron), so the SQLite DB there holds the continuous day-over-day history. This is canonical.
MacBook also has krankie installed for ad-hoc local peeks, but its DB only has data from whenever it was last run - do not use it for the historical comparison.
The vault is bidirectionally synced between the VPS (/home/lobster/vault) and the MacBook (/Users/antonnovoselov/Documents/Vault), so a report written on either side appears on both.

Because the VPS holds the history and the previous_rank/rank_change columns krankie computes between checks, run the check + report on the VPS.

Tracked set (the documented strategy)

Track the 41 canonical keywords from the ASO strategy (see app-store-keywords.md change log) plus the brand term vivadicta, for the app 6758147238, on stores us, gb, ca, au. The same 41 keywords are tracked for 3 competitors on us only:

Otter 1276437113
Wispr Flow 6497229487
Whisper Transcription 1668083311

The keyword list and competitor set live in ~/.krankie/ setup on the VPS; the report generator is ~/.krankie/kr_report.mjs.

Steps

1. Run a fresh check + generate the report (VPS)

bash

ssh lobster@openclawtail 'export PATH="$HOME/.bun/bin:$PATH"; \
  krankie check run --force >/dev/null 2>&1; \
  REPORT_VERSION="<live-version>" bun ~/.krankie/kr_report.mjs'

krankie check run --force re-checks every tracked keyword now (ignores the 24h throttle).
kr_report.mjs reads krankie rankings --json, writes rankings/rankings-YYYY-MM-DD.md to the vault, and appends a row to the app-store-keywords.md index. Pass REPORT_VERSION to stamp the live metadata version (default 3.7.0).
The generator prints the output path and a one-line summary.

2. Read the produced report

The file syncs to the MacBook at:

/Users/antonnovoselov/Documents/Vault/Projects/VivaDicta/ASO/rankings/rankings-YYYY-MM-DD.md

If sync lag is a problem, scp it back: scp lobster@openclawtail:/home/lobster/vault/Projects/VivaDicta/ASO/rankings/rankings-YYYY-MM-DD.md /tmp/.

Show full SKILL.md (233 more words)Show less

3. Compare against the previous check

The report's Change column already reflects krankie's previous_rank (the prior check, i.e. yesterday under cron). For a longer-horizon comparison, read the previous dated rankings-*.md and diff:

Improved: rank moved closer to #1 (or entered top 200 = NEW)
Declined: rank moved away from #1 (or fell out of top 200 = DROPPED)
Stable: unchanged or +/- a few positions

4. Present the comparison report

### Rankings Check: YYYY-MM-DD (krankie) (vs previous: YYYY-MM-DD)

**Overall:** X/41 ranked (was A/41)
**Improved:** keywords that moved up
**Declined:** keywords that moved down
**New rankings:** keywords that entered top 200
**Best performer:** "{keyword}" at #{rank}
**Biggest gain:** "{keyword}" +{positions}

### vs Competitors (US)
| Keyword | VivaDicta | Otter | Wispr Flow | Whisper Trans. |
...

### Gap opportunities (competitors rank, we don't)
- keywords where a competitor is top-50 and VivaDicta is unranked

Report format

kr_report.mjs emits three sections:

VivaDicta Rankings (US store) - | Keyword | Rank | Prev | Change |, sorted ranked-first then unranked by best-competitor-rank (gap priority).
Competitors (US store) - | Keyword | VivaDicta | Otter | Wispr Flow | Whisper Trans. |.
International reach - VivaDicta US/GB/CA/AU for any keyword ranked in any store.

No frontmatter (raw reference file), matching the existing rankings-*.md convention.

Fallback: MacBook-local (VPS unreachable / Tailscale down)

krankie is also installed on the MacBook (~/.bun/bin/krankie). You can run an ad-hoc check locally, but it lacks the VPS's day-over-day history, so Change will be empty/NEW:

bash

krankie check run --force
krankie rankings --json

Then hand-build the report in the April format.

Notes

Rankings take 1-2 weeks to settle after a metadata change.
krankie ranks 1-200; blank = not in top 200. Lower is better.
Recommended cadence: the VPS cron checks daily; generate a vault report weekly, or on demand right after a metadata change.
No popularity/difficulty - prioritize gaps by competitor rank (a keyword Otter/Wispr win and we don't) instead of by Astro popularity.
Related: krankie-audit (offline metadata checks + competitor rank-gap analysis).

Files

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

SKILL.md
agents/openai.yaml

Open the folder on GitHubat commit db0b602

Compare with similar skills

Krankie Rankings 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 Rankings compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Krankie Rankings this skilln0an/VivaDicta	130	—	~1.4k	Automated safety check: Pass	MIT	yesterday
Asc Aso AuditCamilleScholtz/swmpc	239	5 repos	~2.6k	Automated safety check: Pass	EUPL-1.2	4 days ago
Tabler Astro Dev Servertabler/tabler	42k	—	~1.2k	Automated safety check: Pass	MIT	yesterday
Tabler Astro Component Scriptstabler/tabler	42k	—	~2.1k	Automated safety check: Pass	MIT	yesterday
Kill AI Slopyetone/kill-ai-slop	1.3k	—	~1.4k	Automated safety check: Pass	Apache-2.0	26 days ago
Motion Dev Animations199-biotechnologies/motion-dev-animations-skill	133	1 repos	~2.8k	Automated safety check: Notes	MIT	6 mo ago

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
Tabler Astro Dev Server
tabler/tabler
Starts the right Tabler dev server, keeps it from clashing with builds and verifies changes in the browser before a page or component is handed back.
42k GitHub stars~1.2k tokensUpdated yesterday
Frontend & DesignAuto-check passed
Tabler Astro Component Scripts
tabler/tabler
Rules for adding or fixing client-side scripts in Tabler's Astro components so the copied preview HTML stays readable, self-contained and runs in the right order.
42k GitHub stars~2.1k tokensUpdated yesterday
Frontend & DesignAuto-check passed
Kill AI Slop
yetone/kill-ai-slop
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project.
1.3k GitHub stars~1.4k tokensUpdated 26 days ago
Frontend & DesignAuto-check passed
Motion Dev Animations
199-biotechnologies/motion-dev-animations-skill
Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects.
133 GitHub starsUsed in 1 repo~2.8k tokens
Frontend & DesignAuto-check: notes
Astro
devantler-tech/ksail
Skill for building with the Astro web framework. An agent skill from devantler-tech/ksail.
165 GitHub starsUsed in 3 repos~1.1k tokens
Frontend & DesignAuto-check passed

Questions about Krankie Rankings

What does Krankie Rankings do?

Pull VivaDicta App Store keyword rankings via krankie (free, self-hosted), compare against the previous check, and write a dated rankings report to the Obsidian vault. Krankie Rankings is an agent skill from n0an/VivaDicta. Pull VivaDicta App Store keyword rankings via krankie (free, self-hosted), compare against the previous check, and write a dated rankings report to the Obsidian vault.

When should I use Krankie Rankings?

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

How do I install Krankie Rankings in Claude Code?

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

How do I install Krankie Rankings in Codex?

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

Can I use Krankie Rankings 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-rankings -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-rankings, .gemini/skills/krankie-rankings, .github/skills/krankie-rankings and .opencode/skills/krankie-rankings in your project.

What does Krankie Rankings need to run?

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

Does Krankie Rankings 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 Rankings 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 Rankings use?

Krankie Rankings 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 Rankings use?

About 1.4k tokens (SKILL.md is roughly 5.4k 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 Rankings?

Skills that share tags, products or a category with Krankie Rankings: Asc Aso Audit (CamilleScholtz/swmpc, 239 stars), Tabler Astro Dev Server (tabler/tabler, 42k stars), Tabler Astro Component Scripts (tabler/tabler, 42k stars) and Kill AI Slop (yetone/kill-ai-slop, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Krankie Rankings?

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.

Install Krankie Rankings

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

ASO Rankings Check (krankie)

Architecture: VPS is the source of truth

Tracked set (the documented strategy)

Steps

1. Run a fresh check + generate the report (VPS)

2. Read the produced report

3. Compare against the previous check

4. Present the comparison report

Report format

Fallback: MacBook-local (VPS unreachable / Tailscale down)

Notes

Files

Compare with similar skills

Similar skills

More from n0an/VivaDicta

Related

Questions about Krankie Rankings