Agent skill

Next QA Loop

by breaking-brake in breaking-brake/cc-wf-studio

Runs one unattended iteration of a QA loop: tend any open QA pull request, then build one queued qa issue as tests or test tooling only and open a PR.

Custom licenceAuto-check passedTesting & QA

Install Next QA Loop

skills CLI
$ npx skills add breaking-brake/cc-wf-studio --skill next-qa -a claude-code

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

GitHub CLI
$ gh skill install breaking-brake/cc-wf-studio next-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/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/next-qa .claude/skills/next-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
next-qa
GitHub stars
5.4k
Token cost
~2.5k tokens
SKILL.md length
1,431 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Custom licence

At a glance

Runs one unattended iteration of a QA loop: tend any open QA pull request, then build one queued qa issue as tests or test tooling only and open a PR.

  • Works in 4 steps: Serialization guard — one in-flight task… → Interrupts — red CI on auto-qa → Pick ONE qa issue from the queue → …
  • Making unattended progress on a repository's queued QA issues
  • SKILL.md covers The scope boundary — tests and…, 0. Serialization guard — one…, 1. Interrupts — red CI on… and 2. Pick ONE qa issue from the…, plus 2 more sections
  • Calls pnpm, gh and git

What it does

One invocation is one iteration: guard, pick a single queued `qa` issue, then build and record it. The loop exists because the feature loop's merge gate only proves the code compiles through `pnpm build` and `pnpm check`, not that it behaves, so this loop adds an automated test suite that turns regressions into red CI builds. It works on an `auto-qa` integration branch, a sibling of `auto-dev`; both branch from main, a human promotes each to main, and neither merges into the other.

The scope is strict: it never edits product source under `packages/*/src`. It may create test files and fixtures under each package's `src/__tests__/` tree, test configuration such as the vitest config, `.github/workflows/ci.yml` only to run and gate on tests, and `docs/qa-log.md`. If a test exposes a real product bug, it files a bug issue and lands the test skipped. Only the repository owner's own issue text and what the agent verified in code count as the spec; other authors' text is a report to check, not instructions.

When your agent uses it

  • Making unattended progress on a repository's queued QA issues
  • Adding regression tests for known bugs without touching product code
  • Stewarding an in-flight QA pull request through CI

Example prompts

  • “Run next qa and take the next queued qa issue.”
  • “QAタスクを進めて: build the next test infrastructure issue and open a PR.”
  • “Add a regression test for the known workflow validation bug, skipped until it is fixed.”

Requirements

  • A repository with an auto-qa branch, qa-labeled issues and docs/task-automation.md
  • pnpm and a CI workflow that runs the test suite

Workflow steps

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

  1. Serialization guard — one in-flight task at a time
  2. Interrupts — red CI on auto-qa
  3. Pick ONE qa issue from the queue
  4. Build & Record

What it can do on your machine

Read from SKILL.md and the folder at commit a7bf24a. 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:

    • pnpm
    • gh
    • git

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

  • Network

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

Next QA Loop loads about 2.5k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 1,431 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,431 words (~2,459 tokens).

“One invocation = one iteration: guard → pick ONE queued qa issue → build & record.”

— opening of SKILL.md by breaking-brake, Custom licence
name
next-qa

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/next-qa of breaking-brake/cc-wf-studio.

Open the folder on GitHubat commit a7bf24a

Compare with similar skills

Next QA Loop 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.

Next QA Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Next QA Loop this skillbreaking-brake/cc-wf-studio5.4k—~2.5kAutomated safety check: PassCustom licence
Ya Runkzahel/yepanywhere534—~957Automated safety check: PassMIT
Ckeditor5 TestingTriliumNext/Trilium38k—~3.3kAutomated safety check: PassAGPL-3.0
Issue WriterNVIDIA/container-canary308—~1.1kAutomated safety check: PassApache-2.0
Ha Frontend Testinghome-assistant/frontend5.7k—~1.7kAutomated safety check: PassApache-2.0
Openclaw Test Heap Leaksopenclaw/openclaw392k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Ya Run

    kzahel/yepanywhere

    Launch and drive Yep Anywhere — an isolated dev server plus real browser interaction — and run the repository's check suite.

    534 GitHub stars~957 tokensUpdated today
    Testing & QAAuto-check passed
  • Ckeditor5 Testing

    TriliumNext/Trilium

    Testing CKEditor 5 plugins in the Trilium monorepo. An agent skill from TriliumNext/Trilium.

    38k GitHub stars~3.3k tokensUpdated today
    Testing & QAAuto-check passed
  • Issue Writer

    NVIDIA/container-canary

    Official

    Draft and revise concise, human-focused GitHub issues for pytest-kind-ng.

    308 GitHub stars~1.1k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Ha Frontend Testing

    home-assistant/frontend

    Home Assistant frontend testing and validation workflow. An agent skill from home-assistant/frontend.

    5.7k GitHub stars~1.7k tokensUpdated today
    Testing & QAAuto-check passed
  • Openclaw Test Heap Leaks

    openclaw/openclaw

    Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

    392k GitHub stars~1.9k tokensUpdated today
    Testing & QAAuto-check passed
  • Neru File Issue

    y3owk1n/neru

    File a Neru bug report or feature request that matches the repo's issue forms: duplicate check first, every required field filled with real diagnostics, correct labels.

    793 GitHub stars~890 tokensUpdated yesterday
    Testing & QAAuto-check passed

More from breaking-brake/cc-wf-studio

All 11 skills in this repo
  • CC Workflow Studio AI Editor

    breaking-brake/cc-wf-studio

    Creates and edits visual agent workflows in CC Workflow Studio through conversation, with the agent reading and writing the canvas over MCP.

    5.4k GitHub stars~561 tokensUpdated 2 days ago
    Auto-check passed
  • PR Review Analysis

    breaking-brake/cc-wf-studio

    Fetches review comments from a GitHub pull request, checks each one against the real code, rates it valid, invalid or partial, and can reply on GitHub.

    5.4k GitHub stars~626 tokensUpdated 2 days ago
    Auto-check passed
  • Workflow Schema Tuning

    breaking-brake/cc-wf-studio

    Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.

    5.4k GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed
  • Changesets Pull Request to Main

    breaking-brake/cc-wf-studio

    Opens a pull request to main in a pnpm and Changesets monorepo, after working out which packages changed and making sure a changeset file exists.

    5.4k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • PR Merge Branch Cleanup

    breaking-brake/cc-wf-studio

    Clean up merged feature branches after PR to main is merged. Use when the user says "ブランチ削除", "cleanup", "マージ後の片付け", or wants to delete a merged branch.

    5.4k GitHub stars~232 tokensUpdated 2 days ago
    Auto-check passed
  • ccwf Workflow CLI

    breaking-brake/cc-wf-studio

    Teaches the agent to use the ccwf command line tool to validate, preview, render, export and run cc-wf-studio workflow JSON files without opening VS Code.

    5.4k GitHub stars~3.3k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Next QA Loop

What does Next QA Loop do?

Runs one unattended iteration of a QA loop: tend any open QA pull request, then build one queued qa issue as tests or test tooling only and open a PR. One invocation is one iteration: guard, pick a single queued `qa` issue, then build and record it. The loop exists because the feature loop's merge gate only proves the code compiles through `pnpm build` and `pnpm check`, not that it behaves, so this loop adds an automated test suite that turns regressions into red CI builds.

When should I use Next QA Loop?

Next QA Loop fits situations like: making unattended progress on a repository's queued QA issues; adding regression tests for known bugs without touching product code; stewarding an in-flight QA pull request through CI.

How do I install Next QA Loop in Claude Code?

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

How do I install Next QA Loop in Codex?

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

Can I use Next QA Loop 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 breaking-brake/cc-wf-studio --skill next-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/next-qa, .gemini/skills/next-qa, .github/skills/next-qa and .opencode/skills/next-qa in your project.

What does Next QA Loop need to run?

Going by SKILL.md and its folder, Next QA Loop needs the command-line tools its instructions call (pnpm, gh and git). Our summary lists: A repository with an auto-qa branch, qa-labeled issues and docs/task-automation.md; pnpm and a CI workflow that runs the test suite.

Does Next QA Loop access the network?

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

Is Next QA Loop 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 Next QA Loop use?

Next QA Loop 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 Next QA Loop use?

About 2.5k tokens (SKILL.md is roughly 9.8k 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 Next QA Loop?

Skills that share tags, products or a category with Next QA Loop: Ya Run (kzahel/yepanywhere, 534 stars), Ckeditor5 Testing (TriliumNext/Trilium, 38k stars), Issue Writer (NVIDIA/container-canary, 308 stars) and Ha Frontend Testing (home-assistant/frontend, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Next QA Loop?

breaking-brake (a GitHub user) maintains it in breaking-brake/cc-wf-studio, which has 5,394 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

Source: breaking-brake/cc-wf-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.