.cursor/skills/qa-exploratory/SKILL.md
Exploratory QA to find edge cases and unexpected bugs. Tests boundary conditions, error states, and unusual user flows.
npx skillsauth add astro44/Autonom8-Agents qa-exploratoryInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Performs exploratory testing to discover edge cases, boundary conditions, and unexpected bugs that structured tests miss.
{
"project_dir": "/path/to/project",
"ticket_id": "TICKET-XXX",
"url": "http://localhost:8080",
"focus_areas": ["forms", "navigation", "data_display", "error_states"],
"time_budget": 60
}
From ticket acceptance_criteria, identify:
// Test input boundaries
const boundaryTests = {
// Empty inputs
emptyString: '',
// Max length
longString: 'a'.repeat(10000),
// Special characters
specialChars: '<script>alert(1)</script>',
unicode: '日本語テスト🎉',
// Numbers
zero: 0,
negative: -1,
maxInt: Number.MAX_SAFE_INTEGER,
// Dates
farPast: '1900-01-01',
farFuture: '2100-12-31'
};
// Force error conditions
const errorTests = [
'Network offline',
'API returns 500',
'Empty data response',
'Malformed JSON',
'Timeout after 30s'
];
// Test unexpected user behaviors
const flowTests = [
'Double-click submit',
'Back button during form submission',
'Rapid navigation between pages',
'Open in multiple tabs',
'Refresh during async operation'
];
// Test visual boundaries
const visualTests = [
'Very long text content',
'Missing images (404)',
'Slow image loading',
'Extreme viewport sizes (320px, 4K)',
'High contrast mode',
'Zoom at 200%'
];
{
"skill": "qa-exploratory",
"status": "pass|issues_found",
"time_spent": 45,
"tests_performed": 23,
"findings": [
{
"id": "EXP-001",
"severity": "MEDIUM",
"category": "boundary",
"title": "Form accepts 10000+ character input without validation",
"description": "Email field accepts extremely long strings, may cause DB issues",
"steps_to_reproduce": [
"Navigate to contact form",
"Paste 10000 characters into email field",
"Submit form",
"Observe: form submits successfully"
],
"expected": "Validation error for max length",
"actual": "Form submitted, possible truncation",
"screenshot": "screenshots/exp-001-long-email.png"
}
],
"areas_tested": {
"forms": {"tests": 8, "issues": 1},
"navigation": {"tests": 5, "issues": 0},
"data_display": {"tests": 6, "issues": 2},
"error_states": {"tests": 4, "issues": 0}
},
"suggestions": [
"Add client-side max length validation",
"Test with network throttling enabled"
],
"next_action": "proceed|fix|review"
}
| Area | What to Test |
|------|--------------|
| forms | Validation, submission, reset |
| navigation | Links, routes, back/forward |
| data_display | Empty states, overflow, formatting |
| error_states | 404, 500, network errors |
| accessibility | Keyboard, screen reader, contrast |
| performance | Large datasets, slow connections |
| concurrency | Multiple tabs, rapid actions |
Any HIGH severity findings?
YES → status: "issues_found", next_action: "fix"
Any MEDIUM severity findings?
YES → status: "issues_found", next_action: "review"
Only LOW or no findings?
YES → status: "pass", next_action: "proceed"
Full exploratory session:
{
"project_dir": "/projects/oxygen_site",
"ticket_id": "TICKET-OXY-003",
"url": "http://localhost:8080",
"focus_areas": ["forms", "navigation", "data_display", "error_states"],
"time_budget": 120
}
Quick boundary check:
{
"project_dir": "/projects/oxygen_site",
"ticket_id": "TICKET-OXY-003",
"url": "http://localhost:8080",
"focus_areas": ["forms"],
"time_budget": 30
}
development
Scores proposal complexity against codebase surface. Uses proposal text analysis and readiness stats to determine decomposition tier and agent count.
testing
Fast filesystem readiness scan — counts docs, source files, manifests, platform signals. Produces initial ReadinessReport for agent spawning decisions.
testing
Merges bookend agent reports into revised readiness, complexity, and decomposition plan. Produces the final evidence-backed assessment consumed by sprint-architect-agent.
development
Rigorously reasons about definitions, proofs, and computations in algebra, analysis, discrete math, probability, linear algebra, and applied math. Verifies derivations, spots invalid steps, and states assumptions clearly. Use when solving or proving math problems, reviewing mathematical arguments, modeling with equations, interpreting statistics, or when the user mentions proofs, lemmas, theorems, integrals, series, matrices, optimization, or numerical methods.