rodrigobranas/aidev_axon_7/execute-qa

Claude Code and agent skill by rodrigobranas/aidev_axon_7

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Execute QA validation for a completed feature against its PRD, Tech Spec, and tasks using Playwright MCP, accessibility checks, visual review, bug documentation, and a final QA report. Use when Codex is asked to test, QA, validate, approve, reject, or verify a feature implementation in tasks/prd-[feature-name]/.

Install

npx vskill@latest install rodrigobranas/aidev_axon_7/execute-qa

SKILL.md

Execute QA

Use this skill to validate that an implementation satisfies all PRD, Tech Spec, and task requirements before approval.

Required Workflow

  1. Analyze documentation.
  • Identify the feature folder under tasks/prd-[feature-name]/.
  • Read prd.md, techspec.md, and tasks.md.
  • Extract all numbered PRD functional requirements.
  • Verify technical decisions from the Tech Spec.
  • Check task completion status.
  • Build a requirement verification checklist before testing.
  1. Prepare the localhost environment.
  • Confirm the application is running on localhost.
  • If it is not running and project scripts are available, start the required frontend/backend servers.
  • Use Playwright MCP browser_navigate to access the app.
  • Use browser_snapshot to confirm the page loaded and understand current state before interacting.
  1. Run E2E tests with Playwright MCP.
  • Use Playwright MCP for all browser interactions.
  • For each PRD functional requirement, navigate to the relevant functionality, execute the expected flow, verify the result, capture evidence, and mark PASSED or FAILED.
  • Use browser_snapshot before interactions.
  • Use browser_click, browser_type, browser_fill_form, browser_select_option, and browser_press_key as needed.
  • Use browser_console_messages to check JavaScript errors.
  • Use browser_network_requests to inspect API calls when relevant.
  1. Check accessibility against WCAG 2.2.
  • Verify keyboard navigation with Tab, Enter, and Escape.
  • Confirm interactive elements have descriptive labels.
  • Confirm images have appropriate alt text.
  • Check color contrast.
  • Confirm forms have associated labels.
  • Confirm error messages are clear and accessible.
  • Use browser_snapshot for labels and semantic structure.
  1. Perform visual checks.
  • Capture screenshots of main screens with browser_take_screenshot.
  • Check empty, populated, loading, and error states where applicable.
  • Check responsiveness when relevant to the feature.
  • Document visual inconsistencies with screenshots.
  1. Document bugs.
  • Write bugs to tasks/prd-[feature-name]/bugs.md when any issue is found.
  • Include description, severity, reproduction steps, expected result, actual result, and screenshot evidence.
  • Report blocking bugs immediately.
  1. Generate the final QA report.
  • Use references/qa-report-template.md.
  • Save the report as tasks/prd-[feature-name]/qa.md.
  • Set status to APPROVED only when all PRD requirements pass.
  • Set status to REJECTED when any required check fails.

Hard Rules

  • Use Playwright MCP for all E2E browser interactions.
  • Do not approve QA until all PRD requirements, Tech Spec expectations, and task outcomes are verified and passing.
  • Do not skip documentation analysis.
  • Do not skip accessibility checks.
  • Do not skip visual checks.
  • Document all bugs with screenshot evidence.
  • Follow WCAG 2.2 for accessibility evaluation.

Quality Checklist

  • PRD analyzed and requirements extracted.
  • Tech Spec analyzed.
  • Tasks verified and completion status checked.
  • Localhost environment accessible.
  • E2E tests run via Playwright MCP.
  • All main flows tested.
  • Accessibility verified against WCAG 2.2.
  • Evidence screenshots captured.
  • Browser console checked.
  • Network requests checked when relevant.
  • Bugs documented in bugs.md if found.
  • Final report saved to qa.md.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/rodrigobranas/aidev_axon_7/execute-qa/badge)](https://verified-skill.com/skills/rodrigobranas/aidev_axon_7/execute-qa)

Something wrong with this skill or its page? Tell us.