Agent skill

Find Test Gaps

by antonio-orionus in antonio-orionus/Arroxy

Finds missing or weak tests across the full Electron codebase, focusing on stability, integrations, edge cases, and production-readiness rather than only current PR changes.

MITAuto-check passedTesting & QA

Install Find Test Gaps

skills CLI
$ npx skills add antonio-orionus/Arroxy --skill find-test-gaps -a claude-code

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

GitHub CLI
$ gh skill install antonio-orionus/Arroxy find-test-gaps --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/antonio-orionus/Arroxy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/find-test-gaps .claude/skills/find-test-gaps && 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
find-test-gaps
GitHub stars
393
Token cost
~713 tokens
SKILL.md length
362 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Finds missing or weak tests across the full Electron codebase, focusing on stability, integrations, edge cases, and production-readiness rather than only current PR changes.

  • Testing & QA work in your project
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Find Test Gaps is an agent skill from antonio-orionus/Arroxy. Finds missing or weak tests across the full Electron codebase, focusing on stability, integrations, edge cases, and production-readiness rather than only current PR changes.

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. It works with YouTube. The repository describes itself as: Free open-source YouTube and +2000 sites downloader GUI based on yt-dlp for Windows, macOS, and Linux. Download videos, Shorts, 4K, 1080p60, HDR, playlists, channels, and… The licence is MIT.

When your agent uses it

  • Testing & QA work in your project

Example prompts

  • “Use the find-test-gaps skill to find missing or weak tests across the full Electron codebase, focusing on stability, integrations, edge cases, and…”
  • “/find-test-gaps”

What it can do on your machine

Read from SKILL.md and the folder at commit eefe16f. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Find Test Gaps loads about 713 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 362 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~713

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 antonio-orionus/Arroxy at commit eefe16f, republished under its MIT licence (© antonio-orionus). 362 words, ~713 tokens.

Download SKILL.mdSave it as .claude/skills/find-test-gaps/SKILL.md (or your agent's skills folder).
name
find-test-gaps
description
Finds missing or weak tests across the full Electron codebase, focusing on stability, integrations, edge cases, and production-readiness rather than only current PR changes.

You are acting as a senior QA engineer, test architect, and Electron application reliability specialist.

Your task is to deeply inspect this Electron codebase and design, improve, and run a comprehensive testing strategy that helps ensure the app is stable, reliable, and production-ready.

Do not focus narrowly on the current PR, recent commits, or isolated diffs. Treat the whole application as the subject. Look for testing gaps across the full system.

Think broadly and creatively. Decide for yourself which areas deserve attention, which risks are most important, and which tests would provide the most confidence. Do not wait for exact instructions. Use your judgment.

Focus on questions like:

Does the app behave correctly across normal user flows? Does it remain stable under edge cases, bad inputs, slow systems, missing permissions, offline states, failed APIs, corrupted local data, and unexpected user behavior? Are the Electron main process, renderer process, preload scripts, IPC channels, filesystem access, native integrations, background services, windows, menus, auto-updates, notifications, permissions, and storage layers properly tested? Do all integrated systems work together correctly, not just in isolation? Are there hidden assumptions, race conditions, lifecycle issues, startup/shutdown problems, memory leaks, platform differences, or packaging/build issues? Are there meaningful tests around error handling, recovery, security boundaries, user data safety, and app resilience?

Review the existing test coverage and identify what is missing. Add or propose tests where valuable. Improve weak tests if they do not actually prove the app works. Prefer tests that increase confidence in real behavior over tests that only check implementation details.

Show full SKILL.md (107 more words)Show less

Use any suitable testing level: unit tests, integration tests, end-to-end tests, smoke tests, regression tests, manual test plans, mocks, fixtures, automated workflows, or scenario-based testing. Choose what fits best.

Be especially attentive to Electron-specific risks: main/renderer communication, IPC validation, preload isolation, window lifecycle, file permissions, local persistence, app updates, OS-level behavior, deep links, tray/menu behavior, multi-window behavior, crashes and recovery, packaged versus development behavior, and cross-platform differences.

The goal is to discover gaps, strengthen confidence, and make the application feel trustworthy and stable.

Be thoughtful, autonomous, and thorough. Prioritize stability, coverage of real user behavior, and confidence that all parts of the Electron app work together correctly.

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

Files

Just SKILL.md in .agents/skills/find-test-gaps of antonio-orionus/Arroxy.

Open the folder on GitHubat commit eefe16f

Compare with similar skills

Find Test Gaps 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.

Find Test Gaps compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Find Test Gaps this skillantonio-orionus/Arroxy393—~713Automated safety check: PassMIT
Agency Docs Updaterglebis/claude-skills391—~5.1kAutomated safety check: NotesMIT
Claude Design Cardgeekjourneyx/claude-design-card463—~3.5kAutomated safety check: PassNone
Abx DlArchiveBox/abx-dl145—~557Automated safety check: PassMIT
Lets Go RssALBEDO-TABAI/lets-go-rss102—~1.2kAutomated safety check: NotesNone
Playwright Publishszhshp/panda-video-generator291—~1.1kAutomated safety check: PassNone

Similar skills

  • Agency Docs Updater

    glebis/claude-skills

    End-to-end pipeline for publishing Claude Code lab meetings.

    391 GitHub stars~5.1k tokensUpdated 2 days ago
    Testing & QAAuto-check: notes
  • Claude Design Card

    geekjourneyx/claude-design-card

    将任意文本、网页或 URL 生成符合 Claude/Anthropic 设计语言的 HTML 信息卡片,通过 Playwright 截图为 PNG。

    463 GitHub stars~3.5k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed
  • Abx Dl

    ArchiveBox/abx-dl

    Use this when working on the standalone ArchiveBox downloader CLI, extractor orchestration, plugin execution, config, and output verification.

    145 GitHub stars~557 tokensUpdated today
    Testing & QAAuto-check passed
  • Lets Go Rss

    ALBEDO-TABAI/lets-go-rss

    轻量级全平台 RSS 订阅管理器。一键聚合 YouTube、Vimeo、Behance、Twitter/X、知识星球、B站、微博、抖音、小红书的内容更新,支持增量去重和 AI 智能分类。

    102 GitHub stars~1.2k tokensUpdated 5 mo ago
    Testing & QAAuto-check: notes
  • Playwright Publish

    szhshp/panda-video-generator

    Multi-platform browser login and video upload via Playwright Test only (headed Chromium).

    291 GitHub stars~1.1k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • Bun Test

    involvex/youtube-music-cli

    Configure Bun's built-in test runner with Jest-compatible APIs.

    456 GitHub stars~2.3k tokensUpdated 2 days ago
    Testing & QAAuto-check: notes

More from antonio-orionus/Arroxy

  • Remember

    antonio-orionus/Arroxy

    Persists a durable Arroxy lesson — a gotcha, user preference, workflow rule, or design decision — to the right tracked file (project memory, AGENTS.md, CONTEXT.md, dev-docs, or an ADR) so any coding…

    393 GitHub stars~571 tokensUpdated yesterday
    Auto-check passed
  • Translate Arroxy I18n

    antonio-orionus/Arroxy

    Arroxy app i18n workflow. An agent skill from antonio-orionus/Arroxy.

    393 GitHub stars~684 tokensUpdated yesterday
    Auto-check passed
  • Clarify

    antonio-orionus/Arroxy

    Identify underspecified areas in a document (spec, requirements, PRD, brief, etc.) by asking targeted clarification questions and encoding answers back into the document.

    393 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Find Test Gaps

What does Find Test Gaps do?

Finds missing or weak tests across the full Electron codebase, focusing on stability, integrations, edge cases, and production-readiness rather than only current PR changes. Find Test Gaps is an agent skill from antonio-orionus/Arroxy. Finds missing or weak tests across the full Electron codebase, focusing on stability, integrations, edge cases, and production-readiness rather than only current PR changes.

When should I use Find Test Gaps?

Find Test Gaps fits situations like: testing & QA work in your project.

How do I install Find Test Gaps in Claude Code?

Run `npx skills add antonio-orionus/Arroxy --skill find-test-gaps -a claude-code`. Or copy the skill folder (.agents/skills/find-test-gaps in antonio-orionus/Arroxy) into .claude/skills/find-test-gaps in your project. Claude Code loads it when a task matches its description.

How do I install Find Test Gaps in Codex?

Run `npx skills add antonio-orionus/Arroxy --skill find-test-gaps -a codex`. Or copy the skill folder (.agents/skills/find-test-gaps in antonio-orionus/Arroxy) into .agents/skills/find-test-gaps in your project. Codex loads it when a task matches its description.

Can I use Find Test Gaps 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 antonio-orionus/Arroxy --skill find-test-gaps -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/find-test-gaps, .gemini/skills/find-test-gaps, .github/skills/find-test-gaps and .opencode/skills/find-test-gaps in your project.

What does Find Test Gaps need to run?

SKILL.md names no scripts, command-line tools or credentials: Find Test Gaps is instructions for the agent only.

Does Find Test Gaps access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Find Test Gaps 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 Find Test Gaps use?

Find Test Gaps 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 Find Test Gaps use?

About 713 tokens (SKILL.md is roughly 2.9k 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 Find Test Gaps?

Skills that share tags, products or a category with Find Test Gaps: Agency Docs Updater (glebis/claude-skills, 391 stars), Claude Design Card (geekjourneyx/claude-design-card, 463 stars), Abx Dl (ArchiveBox/abx-dl, 145 stars) and Lets Go Rss (ALBEDO-TABAI/lets-go-rss, 102 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Find Test Gaps?

antonio-orionus (a GitHub user) maintains it in antonio-orionus/Arroxy, which has 393 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 9, 2026.

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