Agent skill

Manual QA

by gronxb in gronxb/hot-updater

Execute a caller's natural-language HotUpdater QA scenario on examples/v0.85.0 with profile-scoped infrastructure prepared by hot-updater-agent and app interactions driven through agent-device.

Custom licenceAuto-check: notesTesting & QA

Install Manual QA

skills CLI
$ npx skills add gronxb/hot-updater --skill manual-qa -a claude-code

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

GitHub CLI
$ gh skill install gronxb/hot-updater manual-qa --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/gronxb/hot-updater.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/manual-qa .claude/skills/manual-qa && 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
manual-qa
GitHub stars
1.8k
Token cost
~1.6k tokens
SKILL.md length
802 words
Files
5 (incl. scripts, references)
Skills in repo
6
Repo updated
First seen
Licence
Custom licence

At a glance

Execute a caller's natural-language HotUpdater QA scenario on examples/v0.85.0 with profile-scoped infrastructure prepared by hot-updater-agent and app interactions driven through agent-device.

  • Works in 3 steps: Run the returned closeCommand if the… → Run hot-updater-agent manual stop . → Confirm hot-updater-agent manual status…
  • AI-led manual OTA QA rather than the full E2E runner
  • SKILL.md covers Defaults, Start The Prepared Environment, Turn Natural Language Into A… and Execute With Control APIs And…, plus 3 more sections
  • Runs Shell scripts from its folder; calls git, curl and pnpm

What it does

Manual QA is an agent skill from gronxb/hot-updater. Execute a caller's natural-language HotUpdater QA scenario on examples/v0.85.0 with profile-scoped infrastructure prepared by hot-updater-agent and app interactions driven through agent-device. Use for AI-led manual OTA QA rather than the full E2E runner.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/runtime-targets.md` and `scripts/inspect_android_state.sh`).

It sits in Testing & QA, covering End-to-end testing and Cross-platform mobile apps. It works with React Native. The repository describes itself as: A self-hostable OTA update solution for React Native (Alternative to CodePush).

When your agent uses it

  • AI-led manual OTA QA rather than the full E2E runner
  • Tasks that involve End-to-end testing
  • Tasks that involve Cross-platform mobile apps

Example prompts

  • “/manual-qa”

Requirements

  • A Bash shell

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Run the returned closeCommand if the app/session was opened.
  2. Run hot-updater-agent manual stop .
  3. Confirm hot-updater-agent manual status is stopped (or

What it can do on your machine

Read from SKILL.md and the folder at commit b3cc4bb. 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

    Ships 2 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • curl
    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use git, curl and pnpm, 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

Manual QA loads about 1.6k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 802 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:21
    - Environment target: `examples/v0.85.0/.env.hotupdater`.
  • NoteMentions a .env fileSKILL.md:36
    -env-target examples/v0.85.0/.env.hotupdater \

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 802 words (~1,643 tokens).

“The only required caller input is a natural-language scenario. Accept the user's intent directly; never require or reinterpret it as a file name from e2e/shared/scenarios.”

— opening of SKILL.md by gronxb, Custom licence
name
manual-qa

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (scripts, references) in .agents/skills/manual-qa of gronxb/hot-updater.

  • SKILL.md
  • agents/openai.yaml
  • references/runtime-targets.md
  • scripts/inspect_android_state.sh
  • scripts/inspect_ios_state.sh

Open the folder on GitHubat commit b3cc4bb

Compare with similar skills

Manual QA 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.

Manual QA compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Manual QA this skillgronxb/hot-updater1.8k—~1.6kAutomated safety check: NotesCustom licence
Engine E2Ewix/react-native-navigation13k—~1.1kAutomated safety check: PassMIT
Android Audio E2Ehyochan/react-native-nitro-sound961—~814Automated safety check: PassMIT
iOS Audio E2Ehyochan/react-native-nitro-sound961—~907Automated safety check: PassMIT
Nitro Sound Workflowshyochan/react-native-nitro-sound961—~1.2kAutomated safety check: PassMIT
Iapkit E2E Martiehyodotdev/openiap155—~5.4kAutomated safety check: NotesMIT

Similar skills

  • Engine E2E

    wix/react-native-navigation

    Official

    Run Wix Engine (mobile-apps-engine) iOS E2E tests locally to validate RNN changes.

    13k GitHub stars~1.1k tokensUpdated 5 days ago
    Testing & QAAuto-check passed
  • Android Audio E2E

    hyochan/react-native-nitro-sound

    Build and run device-backed Android end-to-end checks for react-native-nitro-sound permissions, recording, playback, listeners, pause/resume, seek, speed, audio focus, lifecycle behavior, and rapid…

    961 GitHub stars~814 tokensUpdated 11 days ago
    MobileAuto-check passed
  • iOS Audio E2E

    hyochan/react-native-nitro-sound

    Build and run device-backed iOS end-to-end checks for react-native-nitro-sound recording, playback, listeners, pause/resume, seek, speed, interruption, audio-session behavior, and rapid switching.

    961 GitHub stars~907 tokensUpdated 11 days ago
    MobileAuto-check passed
  • Nitro Sound Workflows

    hyochan/react-native-nitro-sound

    A skill your agent uses for react-native-nitro-sound repository work that should follow the project workflows for PR review, code audit, knowledge compilation, full verification, iOS or Android…

    961 GitHub stars~1.2k tokensUpdated 11 days ago
    MobileAuto-check passed
  • Iapkit E2E Martie

    hyodotdev/openiap

    Run IAPKit local receipt-validation E2E with the dev.hyo.martie React Native or Expo examples, the compiled packages/kit server, real Convex, and Apple or Google sandbox purchases.

    155 GitHub stars~5.4k tokensUpdated yesterday
    MobileAuto-check: notes
  • Iapkit E2E Petgu

    hyodotdev/openiap

    A skill your agent uses for IAPKit product sync E2E testing in packages/kit with the Petgu React Native app, localhost dashboard, App Store Connect, and Google Play Console.

    155 GitHub stars~1.1k tokensUpdated yesterday
    MobileAuto-check passed

More from gronxb/hot-updater

  • Agent Device

    gronxb/hot-updater

    Automates interactions for iOS simulators/devices and Android emulators/devices.

    1.8k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Hot Updater

    gronxb/hot-updater

    Set up, upgrade, operate, and diagnose Hot Updater projects.

    1.8k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Fix CI

    gronxb/hot-updater

    Run a local pnpm monorepo CI loop, fix failures, and stop only when the full sequence is green.

    1.8k GitHub stars~572 tokensUpdated today
    Auto-check passed
  • Hot Updater Agent

    gronxb/hot-updater

    A skill your agent uses when an AI agent needs to run or inspect full HotUpdater E2E jobs, or prepare and lease a profile-scoped manual QA environment through the local hot-updater-agent CLI.

    1.8k GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

Works with

Questions about Manual QA

What does Manual QA do?

Execute a caller's natural-language HotUpdater QA scenario on examples/v0.85.0 with profile-scoped infrastructure prepared by hot-updater-agent and app interactions driven through agent-device. Manual QA is an agent skill from gronxb/hot-updater.0 with profile-scoped infrastructure prepared by hot-updater-agent and app interactions driven through agent-device.

When should I use Manual QA?

Manual QA fits situations like: AI-led manual OTA QA rather than the full E2E runner; tasks that involve End-to-end testing; tasks that involve Cross-platform mobile apps.

How do I install Manual QA in Claude Code?

Run `npx skills add gronxb/hot-updater --skill manual-qa -a claude-code`. Or copy the skill folder (.agents/skills/manual-qa in gronxb/hot-updater) into .claude/skills/manual-qa in your project. Claude Code loads it when a task matches its description.

How do I install Manual QA in Codex?

Run `npx skills add gronxb/hot-updater --skill manual-qa -a codex`. Or copy the skill folder (.agents/skills/manual-qa in gronxb/hot-updater) into .agents/skills/manual-qa in your project. Codex loads it when a task matches its description.

Can I use Manual QA 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 gronxb/hot-updater --skill manual-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manual-qa, .gemini/skills/manual-qa, .github/skills/manual-qa and .opencode/skills/manual-qa in your project.

What does Manual QA need to run?

Going by SKILL.md and its folder, Manual QA needs a shell for the scripts in its folder and the command-line tools its instructions call (git, curl and pnpm). Our summary lists: A Bash shell.

Does Manual QA access the network?

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

Is Manual QA safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Manual QA use?

Manual QA has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Manual QA use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 677 tokens, read only when the agent opens those files.

What are the alternatives to Manual QA?

Skills that share tags, products or a category with Manual QA: Engine E2E (wix/react-native-navigation, 13k stars), Android Audio E2E (hyochan/react-native-nitro-sound, 961 stars), iOS Audio E2E (hyochan/react-native-nitro-sound, 961 stars) and Nitro Sound Workflows (hyochan/react-native-nitro-sound, 961 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Manual QA?

gronxb (a GitHub user) maintains it in gronxb/hot-updater, which has 1,762 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 11, 2026.

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