Skip to main content
skill CX Codex

qa-execution — Claude Code skill: QA through public interfaces

qa-execution — a skill that walks personas through a product's public interfaces, records friction and findings, and writes everything into a living QA docs tree.

no license 568 installs ★ 655 updated 2026-10-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add pedronauck/skills --skill qa-execution -a claude-code
Open on GitHub

What qa-execution does

The skill tests a product the way a person meets it. Each persona enters through a real entry point with its own device, network and locale, then walks a journey to its true end state. No dev-tools shortcuts, no reading code to decide what should happen. A Pass means the expected observable was seen, confirmed through an independent read path, and survived a refresh.

The QA docs tree is the skill's memory and its only output location. Before running, it reads README.md, scenario files, open bugs and the cycle's charters. The report is created on disk before the first session, with every matrix row set to Pending. After each session and each fix, the report updates. The rule is blunt: write back or it didn't happen.

Seven steps hold the process together: resolve tree and scope, build the matrix and report, walk each journey in persona, run tours and edge probes, apply experience lenses, file findings into the bug registry, then run the governed fix loop. Each auto-fix passes the governor's bounds and gets a regression test. Anything else goes to Decisions for a Human with options and a recommendation.

The skill does not bootstrap the tree. If docs/qa/ does not exist, run qa-report first — it owns the tree and its setup. Legs that only a human can complete, like real payment or external OAuth, get marked Blocked (needs human verify) with exact instructions, never faked.

What it helps with

  • walk a product through its public interfaces the way a real user would
  • catch paper cuts that functional checks never flag
  • maintain a QA docs tree with reports, bugs and scenarios
  • decide which fixes are auto-applied and which need a human decision
  • reuse existing evidence for behavior that has not changed

Example prompts for the agent

  • Run the QA pass for the branch I just pushed and update the report under docs/qa/
  • Walk the checkout-smoke charter as a persona on a slow mobile network
  • Build the release-run matrix and mark every row Pending before the first session

How to install qa-execution

1Skills CLI (Vercel)

npx skills add pedronauck/skills --skill qa-execution -a claude-code

2Manually: put the files in place

~/.claude/skills/qa-execution/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/qa-execution/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about qa-execution

How do I install qa-execution in Claude Code?

Run npx skills add pedronauck/skills --skill qa-execution -a claude-code and the skill lands at ~/.claude/skills/qa-execution/SKILL.md.

What does qa-execution do?

It runs personas through public product interfaces, records friction and findings in the QA docs tree, and pushes each fix through a governor so only fixes that pass all bounds get applied automatically.

How does qa-execution relate to qa-report?

qa-report owns the docs/qa/ tree and its bootstrap. qa-execution uses that tree for sessions and writes reports and bugs into it. If the tree is missing, run qa-report first.

Similar skills

All skills for Testing and QA →

From the same set52

The whole set →
no-workarounds The no-workarounds skill examines fixes that conceal an error or its symptoms. Use it when a change looks like a workaround or the defect comes from outside your codebase. CX Codex +1 593installs typescript-advanced typescript-advanced guides agents through advanced TypeScript types and compile-time contracts. Use it when generic inference or reusable type utilities are the hard part. CX Codex +1 587installs architectural-analysis architectural-analysis audits a codebase for design problems: dead exports, duplicated duties, tangled types, dependency cycles. Read-only unless you've already allowed fixes. CX Codex +1 555installs qa-report The qa-report skill maintains project QA docs, maps user journeys, and plans persona-led sessions. Use it to keep planning and bug records connected across QA cycles. CX Codex +1 551installs tailwindcss Guides coding agents through Tailwind CSS v4 component styling using project tokens, explicit utility classes, and accessible layouts. CX Codex +1 484installs react Guidance for building and reviewing React 19 components and hooks with React Compiler in mind. Use it for compiler setup, state and Effects decisions, or component tests. CX Codex +1 483installs electron-builder electron-builder guides the agent through configuring Electron app packaging, platform targets, code signing, and auto-updates. Useful for release workflows. CX Codex +1 459installs refactoring-analysis refactoring-analysis audits architectural health and Fowler code smells, writing prioritized refactoring plans to docs/_refacs/. Built for planning refactoring while preserving existing behavior. CX Codex +1 434installs

Project sponsors

Companies that keep this analytics open