Agent skill

QA

Run quokka's real-device E2E layer (QA strategy layer 5): drive the real qk binary against connected iPhone/Android devices through tmux, apply deterministic verifiers, and write a report.

MITAuto-check passedTesting & QA

Install QA

skills CLI

$ npx skills add dutradotdev/quokka --skill qa -a claude-code

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

GitHub CLI

$ gh skill install dutradotdev/quokka 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/dutradotdev/quokka.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/qa .claude/skills/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/

Paste into Claude Code

Install the "qa" agent skill from https://github.com/dutradotdev/quokka/tree/main/.claude/skills/qa into .claude/skills/qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa", 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/dutradotdev/quokka/tree/main/.claude/skills/qa

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 dutradotdev/quokka --skill qa -a codex

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

GitHub CLI

$ gh skill install dutradotdev/quokka qa --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/dutradotdev/quokka.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/qa .agents/skills/qa && 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 "qa" agent skill from https://github.com/dutradotdev/quokka/tree/main/.claude/skills/qa into .agents/skills/qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa", 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 dutradotdev/quokka --skill qa -a cursor

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

GitHub CLI

$ gh skill install dutradotdev/quokka qa --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/dutradotdev/quokka.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/qa .cursor/skills/qa && 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 "qa" agent skill from https://github.com/dutradotdev/quokka/tree/main/.claude/skills/qa into .cursor/skills/qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa", 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/dutradotdev/quokka.git --path .claude/skills/qa

--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 dutradotdev/quokka --skill qa -a gemini-cli

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

GitHub CLI

$ gh skill install dutradotdev/quokka qa --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/dutradotdev/quokka.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/qa .gemini/skills/qa && 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 "qa" agent skill from https://github.com/dutradotdev/quokka/tree/main/.claude/skills/qa into .gemini/skills/qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa", 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 dutradotdev/quokka qa

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 dutradotdev/quokka --skill qa -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/dutradotdev/quokka.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/qa .github/skills/qa && 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 "qa" agent skill from https://github.com/dutradotdev/quokka/tree/main/.claude/skills/qa into .github/skills/qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa", 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 dutradotdev/quokka --skill qa -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 dutradotdev/quokka qa --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/dutradotdev/quokka.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/qa .opencode/skills/qa && 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 "qa" agent skill from https://github.com/dutradotdev/quokka/tree/main/.claude/skills/qa into .opencode/skills/qa/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa", 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: qa
GitHub stars: 108
Token cost: ~1k tokens
SKILL.md length: 515 words
Files: 1
Skills in repo: 1
Repo updated: Jul 27, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Run quokka's real-device E2E layer (QA strategy layer 5): drive the real qk binary against connected iPhone/Android devices through tmux, apply deterministic verifiers, and write a report.

Works in 3 steps: tmux and jq installed. If tmux is… → A current build: run cargo build (debug… → At least one device attached. Detect…
The user asks to run /qa
SKILL.md covers Hard rule, Preconditions, Procedure and Report, plus 1 more section
Calls brew, cargo and jq

What it does

QA is an agent skill from dutradotdev/quokka. Run quokka's real-device E2E layer (QA strategy layer 5): drive the real qk binary against connected iPhone/Android devices through tmux, apply deterministic verifiers, and write a report. Use when the user asks to "run /qa", "run the device QA suite", "test against the real device", or before a release. Optionally finishes with an advisory exploratory UX pass (layer 6).

Its SKILL.md is about 1k 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, covering Test strategy, End-to-end testing and Report writing. It works with tmux and Android. The repository describes itself as: Inspect and clean a USB-connected device from your terminal: storage, apps, media, and a live log viewer. No jailbreak, no root. The licence is MIT.

When your agent uses it

The user asks to run /qa
Run the device QA suite
Test against the real device
Before a release

Example prompts

“run /qa”
“run the device QA suite”
“test against the real device”
“/qa”

Workflow steps

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

tmux and jq installed. If tmux is missing, stop and tell the user
A current build: run cargo build (debug qk at target/debug/qk).
At least one device attached. Detect platforms

What it can do on your machine

Read from SKILL.md and the folder at commit 685254d. 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:
- brew
- cargo
- jq
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

QA loads about 1k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 515 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~94
When it runs · the whole SKILL.md, loaded when a task matches: ~1k

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 dutradotdev/quokka at commit 685254d, republished under its MIT licence (© dutradotdev). 515 words, ~1,042 tokens.

Download SKILL.mdSave it as .claude/skills/qa/SKILL.md (or your agent's skills folder).

name: qa
description: Run quokka's real-device E2E layer (QA strategy layer 5): drive the real qk binary against connected iPhone/Android devices through tmux, apply deterministic verifiers, and write a report. Use when the user asks to "run /qa", "run the device QA suite", "test against the real device", or before a release. Optionally finishes with an advisory exploratory UX pass (layer 6).

/qa — real-device E2E runner

You are the driver for layer 5 of the QA strategy (docs/superpowers/specs/2026-06-01-qa-strategy-design.md). You run the real binary against attached hardware and decide pass/fail deterministically.

Hard rule

Pass/fail is decided ONLY by the deterministic predicates below (exit code, regex over captured text, golden-frame compare, JSON validity). You do not use your own judgment to pass or fail a case. Subjective UX judgment belongs to the optional exploratory pass at the end, which is advisory and never a gate.

Preconditions

tmux and jq installed. If tmux is missing, stop and tell the user brew install tmux.
A current build: run cargo build (debug qk at target/debug/qk).
At least one device attached. Detect platforms: tests/llm/lib/drive.sh platforms → prints ios and/or android. If empty, stop and tell the user to connect a device.

All mechanics go through tests/llm/lib/drive.sh (see its header for the subcommands). Never reimplement the tmux dance inline.

Procedure

Read every tests/llm/*.yaml (not lib/, not golden/, not reports/). For each case, in file order:

Check requires against the detected platforms.
- any → at least one device present.
- ios / android → that platform present.
- Not met → record SKIP with the reason. Never fail on absence.
Run it.
- No interact block (non-interactive): drive.sh run <command>. The output ends with __QA_EXIT__=<code>. The captured text above that line is the output.
- Has interact (interactive TUI):
  - drive.sh start <session> <command> (use a unique session like qa_<id>).
  - For each step: wait_for: X → drive.sh wait <session> "X" <timeout>; keys: [..] → drive.sh keys <session> <k1> <k2> ....
  - After the steps, capture the frame: drive.sh capture <session>.
  - Send quit_keys (default q) and drive.sh stop <session>.
  - If wait times out, that is a FAIL (the TUI never reached the expected state).

Apply every verify predicate against the captured output/frame:

Predicate	Check
`exit_code: N`	the `__QA_EXIT__` value equals N
`output_matches: R`	regex R matches the captured output
`frame_matches: R`	regex R matches the captured frame
`frame_excludes: R`	regex R does not match the frame
`json_valid: true`	the captured output parses as JSON (`jq . <<<output`)
`golden_frame: name`	the frame equals `tests/llm/golden/<name>.txt` exactly
A case PASSES only if every predicate holds. A case with no predicates and a
clean run is a PASS but flag it as "smoke-only".

Always tear the session down even on failure (drive.sh stop).

Show full SKILL.md (136 more words)Show less

Report

Write tests/llm/reports/<YYYY-MM-DD-HHMM>.md containing:

a summary line: N passed, M failed, K skipped and the detected platforms;
per case: id, status (PASS/FAIL/SKIP), which predicate failed (if any), and the captured frame in a fenced block (the trajectory, for debugging).

Then print the summary to the user. If anything failed, lead with the failures.

Optional: exploratory UX pass (layer 6, advisory)

Only if the user asks for it, or it is pre-release. After the deterministic suite, drive a connected device freely beyond the scripted cases — open each TUI, trigger an error path (e.g. unplug mid-command if the user is present), resize, navigate. Report UX smells ("this error doesn't say what to do", "the dashboard wraps awkwardly at 80 cols") as observations, NOT pass/fail. The user decides what becomes a ticket. Never gate a release on this pass.

Files

Just SKILL.md in .claude/skills/qa of dutradotdev/quokka.

Open the folder on GitHubat commit 685254d

Compare with similar skills

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.

QA compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
QA this skilldutradotdev/quokka	108	—	~1k	Automated safety check: Pass	MIT	2 mo ago
Feature Development WorkflowQwenLM/qwen-code	28k	—	~1.2k	Automated safety check: Pass	Apache-2.0	today
CodexBar Live QAsteipete/CodexBar	22k	—	~1.2k	Automated safety check: Pass	MIT	today
E2Egronxb/hot-updater	1.8k	—	~1.6k	Automated safety check: Pass	Custom licence	today
Senior QAnicepkg/auto-company	192	3 repos	~1.1k	Automated safety check: Notes	None	7 mo ago
Drive MiMo CodeXiaomiMiMo/MiMo-Code	14k	—	~3.9k	Automated safety check: Pass	MIT	4 days ago

Similar skills

Feature Development Workflow
QwenLM/qwen-code
Phased workflow for non-trivial qwen-code features: investigate, design doc, E2E test plan, baseline dry-run, implement, verify, self-audit, review and iterate.
28k GitHub stars~1.2k tokensUpdated today
DevelopmentAuto-check passed
CodexBar Live QA
steipete/CodexBar
Runs live QA for the CodexBar app: provider usage matrix checks through its packaged CLI, config validation and menu checks, with 1Password-backed credentials handled safely.
22k GitHub stars~1.2k tokensUpdated today
Testing & QAAuto-check passed
E2E
gronxb/hot-updater
Run end-to-end OTA verification for examples/v0.85.0 with agent-device.
1.8k GitHub stars~1.6k tokensUpdated today
Testing & QAAuto-check passed
Senior QA
nicepkg/auto-company
Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications.
192 GitHub starsUsed in 3 repos~1.1k tokens
Testing & QAAuto-check: notes
Drive MiMo Code
XiaomiMiMo/MiMo-Code
Lets one MiMoCode process drive another, headless with JSON events or interactively through tmux, to test behavior and visual regressions with parseable evidence.
14k GitHub stars~3.9k tokensUpdated 4 days ago
Testing & QAAuto-check passed
E2E Current PR
gronxb/hot-updater
Generate and execute PR-aware OTA E2E scenarios for examples/v0.85.0 by diffing the checked-out branch against its PR base branch or default branch, inferring the affected runtime, rollout, and…
1.8k GitHub stars~1k tokensUpdated today
Testing & QAAuto-check passed

Works with

Questions about QA

What does QA do?

Run quokka's real-device E2E layer (QA strategy layer 5): drive the real qk binary against connected iPhone/Android devices through tmux, apply deterministic verifiers, and write a report. QA is an agent skill from dutradotdev/quokka. Run quokka's real-device E2E layer (QA strategy layer 5): drive the real qk binary against connected iPhone/Android devices through tmux, apply deterministic verifiers, and write a report.

When should I use QA?

QA fits situations like: the user asks to run /qa; run the device QA suite; test against the real device; before a release.

How do I install QA in Claude Code?

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

How do I install QA in Codex?

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

Can I use 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 dutradotdev/quokka --skill 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/qa, .gemini/skills/qa, .github/skills/qa and .opencode/skills/qa in your project.

What does QA need to run?

Going by SKILL.md and its folder, QA needs the command-line tools its instructions call (brew, cargo and jq).

Does QA 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 QA 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 QA use?

QA 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 QA use?

About 1k tokens (SKILL.md is roughly 4.2k 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 QA?

Skills that share tags, products or a category with QA: Feature Development Workflow (QwenLM/qwen-code, 28k stars), CodexBar Live QA (steipete/CodexBar, 22k stars), E2E (gronxb/hot-updater, 1.8k stars) and Senior QA (nicepkg/auto-company, 192 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains QA?

dutradotdev (a GitHub user) maintains it in dutradotdev/quokka, which has 108 GitHub stars. The repository was last updated on July 27, 2026.

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

Install QA

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

/qa — real-device E2E runner

Hard rule

Preconditions

Procedure

Report

Optional: exploratory UX pass (layer 6, advisory)

Files

Compare with similar skills

Similar skills

Feature Development Workflow

CodexBar Live QA

E2E

Senior QA

Drive MiMo Code

E2E Current PR

Related

Questions about QA