QA

Test an application at its browser, API, CLI, job or webhook surface and fix reproducible bugs within the requested scope, with evidence and appropriate regression checks. Honors report-only and no-commit requests.

9 starsTesting & QA Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add borkweb/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add borkweb/skills --skill qa
Manual install
git clone --depth 1 https://github.com/borkweb/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/gstack/qa ~/.claude/skills/qa

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# QA: Test, Fix, Verify

Test the requested application at the selected surface and correct reproducible bugs within scope. Use [exploration.md](exploration.md) for shared browser testing and reporting. A requested report-only run follows qa-only's no-source-edit boundary.

## Fix loop

Record the starting checkout and preserve unrelated dirt. Use an isolated checkout when required; do not stash or commit the user's entire tree to begin QA. Honor no-commit instructions. A QA invocation does not itself authorize commit, push, merge or publication.

For each confirmed issue, trace the cause and make a scoped correction. Reproduce the original scenario against the fix, collect appropriate before/after evidence and check adjacent behavior. Write a meaningful regression test for logic or contract bugs where the project supports it: demonstrate failure without the fix and success with it. Do not delete a failing test to finish; fix the bug or report the unresolved failure.

Run appropriate checks once against the final changed files. Commit only verified, owned changes when authorized, following the repository's commit conventions. An unverified fix stays explicitly unverified; a regression requires correction or reversal of only your own edit, not an indiscriminate `git revert HEAD`.
Read the full skill on GitHub

Details

Skill name
qa
Repository
borkweb/skills
Path
skills/gstack/qa/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the QA skill do?

Test an application at its browser, API, CLI, job or webhook surface and fix reproducible bugs within the requested scope, with evidence and appropriate regression checks. Honors report-only and no-commit requests.

How do I install the QA skill?

Claude Code plugin: /plugin marketplace add borkweb/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is QA popular?

It lives in borkweb/skills, which has 9 GitHub stars and 0 forks.

Related skills

Prototype

9

borkweb/skills

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

Frontend & DesignIn 1 list

Agents Md Lint

9

borkweb/skills

Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code alone. Use when asked to lint, audit, optimize, prune, or trim any agent instruction file in a repository. Removes redundant documentation that wastes context tokens. Supports a dry-run mode that reports findings without modifying files.

AI, LLMs & Agents

Auto Scope

9

borkweb/skills

Scopes a coding task before implementation — names the handful of files actually relevant (read/edit these), the areas to leave alone, and any open scope questions, so work doesn't start by reading the whole repo. Fires proactively at the start of substantive, multi-file, or unfamiliar-area work; stays silent on single-file edits, one-line fixes, questions, and continued work in an area already scoped this session. Use when beginning a feature, bug fix, or refactor that could plausibly touch several files or an area not yet seen this session.

Software Development

QA Only

9

borkweb/skills

Test an application at its browser, API, CLI, job or webhook surface and report reproducible bugs with evidence, without fixing them. Use for 'QA this and report', 'test the app', 'find bugs but don't fix', 'verify this flow works' or when do needs a runtime check of a change.

Testing & QA

Cmd PR Test Plan

9

Olshansk/agent-skills

Generate manual test plans for PR changes — focused on hands-on verification a developer would do, not unit-test edge cases

Testing & QA

Acceptance Orchestrator

9

huytran1120/vietnam-agentic-skills

Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.