web-qa-exploration — Claude Code skill
The web-qa-exploration skill explores web app flows with Playwright, records issues, and produces reports with screenshots and reproduction steps.
Apache-2.0 1 installs ★ 1 updated 2026-01-13
npx skills add bryonjacob/aug --skill web-qa-exploration -a claude-codeWhat web-qa-exploration does
The skill follows a defined scope through web pages and user flows. It checks forms, navigation, interface states, basic accessibility, and error handling, including empty submissions, boundary values, and direct links. Findings receive a category and severity.
Results go into report.md and report.json; screenshots are stored under /tmp/webqa/{session-id}/screenshots/. Each issue can include reproduction steps, expected and actual behavior, and a suggested Playwright test. Exploration stays within the specified waypoints and is time-boxed to 2–5 minutes per waypoint. It does not fix issues, so fixes need to be handled separately.
What it helps with
- check forms with empty and boundary-value submissions
- find failures after refreshes or back-button navigation
- inspect interface states and keyboard navigation
- record defects with screenshots and reproduction steps
- draft Playwright tests for discovered issues
Example prompts for the agent
- Explore the signup flow, check its form for issues, and save a report with screenshots.
- Test the specified pages, including back navigation and refresh, and document any failures.
- Check accessibility and invalid URL parameters, then suggest Playwright tests for the issues.
How to install web-qa-exploration
1Skills CLI (Vercel)
npx skills add bryonjacob/aug --skill web-qa-exploration -a claude-code2Manually: put the files in place
~/.claude/skills/web-qa-exploration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/web-qa-exploration/
1Skills CLI (Vercel)
npx skills add bryonjacob/aug --skill web-qa-exploration -a codex2Manually: put the files in place
.agents/skills/web-qa-exploration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add bryonjacob/aug --skill web-qa-exploration -a cursor2Manually: put the files in place
.cursor/skills/web-qa-exploration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install bryonjacob/aug aug-dev/skills/web-qa-exploration2Manually: put the files in place
.github/skills/web-qa-exploration/SKILL.md1Skills CLI (Vercel)
npx skills add bryonjacob/aug --skill web-qa-exploration -a gemini-cli2Platform CLI
gemini skills install https://github.com/bryonjacob/aug --path aug-dev/skills/web-qa-explorationManually: put the files in place
.devin/skills/web-qa-exploration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add bryonjacob/aug --skill web-qa-exploration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about web-qa-exploration
How do I install web-qa-exploration in Claude Code?
Run npx skills add bryonjacob/aug --skill web-qa-exploration -a claude-code. The skill file is at ~/.claude/skills/web-qa-exploration/SKILL.md.
What does web-qa-exploration do?
It explores web app flows with Playwright, checks the defined scope, and records findings in reports with screenshots and reproduction steps.
What output does the skill create?
It writes report.md with findings ordered by severity and report.json for automation. Screenshots go in the session directory.
Source text
SKILL.md · Apache-2.0
---
name: web-qa-exploration
description: Perform exploratory QA testing on web applications using Playwright. Navigate flows, analyze pages, find issues, and generate actionable reports with evidence.
---
# Web QA Exploration
Autonomous exploratory testing using Playwright to analyze web application flows, identify issues, and generate actionable reports.
## Core Principles
1. **Thoroughness over speed** - Analyze each page state fully
2. **Break things intentionally** - Try edge cases, unexpected inputs, unusual navigation
3. **Document everything** - When in doubt, capture it
4. **Stay focused** - Follow defined waypoints; don't wander
5. **Fail gracefully** - If stuck, document and move on
## Working Directory
```
/tmp/webqa/{session-id}/
session.md # Session context and scope
report.md # Human-readable findings
report.json # Machine-readable for automation
screenshots/ # Visual evidence
metadata.json # Session info, status
```
All ephemeral. Output feeds into `/plan-chat` or `/plan-breakdown`.
## Analysis Checklist
At each waypoint, systematically check:
### Visual & Layout
- Content fully visible (no overflow, cutoff)
- Proper spacing and alignment
- Images/icons load correctly
- No layout shifts after load
### Navigation & State
- **Back button** - Does it preserve state?
- **Refresh** - Does page recover?
- **Deep link** - Can URL be shared/bookmarked?
### Forms & Inputs
- **Empty submission** - Validation fires?
- **Boundary values** - Max length, min/max numbers
- **Special characters** - `<script>`, quotes, unicode
- **Whitespace** - Leading/trailing, only spaces
- **Tab order** - Keyboard navigation logical
- **Error messages** - Clear, positioned correctly
### Interactions
- **Double-click** - Rapid clicking on submit
- **Keyboard shortcuts** - Enter, Escape behavior
- **Focus states** - Visible indicators
- **Disabled states** - Buttons during submission
### Accessibility (basic)
- Heading structure (h1-h6 hierarchy)
- Form labels present
- Color contrast (visual check)
- Alt text on images
### Error Handling
- Network failure behavior
- Timeout handling
- Invalid URL parameters
## Issue Documentation
Each issue needs:
- **id**: ISSUE-001
- **severity**: critical | high | medium | low | note
- **category**: bug | ux | accessibility | edge-case | visual
- **page**: /path/to/page
- **title**: Short description
- **description**: Detailed explanation
- **steps_to_reproduce**: Ordered list
- **expected**: What should happen
- **actual**: What actually happens
- **screenshot**: Path to evidence
- **suggested_test**: Playwright test code
## Severity Guidelines
- **Critical**: Crashes, data loss, security issue, flow blocker
- **High**: Feature broken, significant UX problem
- **Medium**: Edge case failures, minor UX issues
- **Low**: Polish issues, minor visual glitches
- **Note**: Observations, suggestions, not bugs
## Scope Control
- Only explore pages/states within defined scope
- Time-box analysis (2-5 minutes per waypoint)
- Don't attempt to fix issues during exploration
### When Stuck
1. Document with maximum detail
2. Take screenshot
3. Attempt one workaround (refresh, re-navigate)
4. If still blocked, mark waypoint as "blocked" and skip
5. Continue from next accessible waypoint
## Output
### report.md
Summary table with severity counts, then issues ordered by severity. Each issue includes description, steps, expected/actual, screenshot, and suggested Playwright test.
### metadata.json
```json
{
"session_id": "{session-id}",
"scope": "{DESCRIPTION}",
"status": "complete",
"waypoints_total": 5,
"waypoints_completed": 5,
"issues": { "critical": 0, "high": 1, "medium": 3, "low": 2, "note": 2 }
}
```
## Integration
**Feeds into:**
- `/plan-chat` - When issues need architectural discussion
- `/plan-breakdown` - When ready to create fix tasks directly
## Quality Checklist
- [ ] All waypoints visited or documented as blocked
- [ ] Each issue has severity, category, description
- [ ] Screenshots captured for visual issues
- [ ] Steps to reproduce provided
- [ ] Suggested Playwright tests included
- [ ] Summary statistics accurate
© bryonjacob · Apache-2.0 · bryonjacob/aug