Skip to main content
skill CX Codex

exploratory-testing-advanced — Claude Code skill: testing

exploratory-testing-advanced is a Claude Code skill for planning exploratory sessions, investigating bugs, and recording defects. It supports checks of new features and issues automated tests miss.

MIT 1 installs ★ 533 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add proffesor-for-testing/agentic-qe --skill exploratory-testing-advanced -a claude-code
Open on GitHub

What exploratory-testing-advanced does

The skill structures an exploratory session around SBTM: set a mission and scope, investigate the software, capture observations, then debrief. SFDIPOT and FEW HICCUPPS offer ways to choose what to examine and recognize problems. Test tours guide navigation, from critical business flows to failure scenarios.

Session notes can track bugs, open questions, explored areas, and follow-up work. The skill also describes agent-supported exploration: agents can generate test variations, spot visual anomalies, and assess risks. This is not a collection of ready-made test cases. The tester still needs to judge system behavior and record discoveries during the session.

What it helps with

  • plan an exploratory session with a clear mission and time-box
  • check a new feature using quality heuristics
  • look for bugs that automated tests miss
  • record findings and choose follow-up checks

Example prompts for the agent

  • Explore the new payment form with SFDIPOT and record any bugs you find.
  • Plan a session to investigate the changed checkout flow.
  • Use a test tour to examine failure scenarios and note questions for the debrief.

How to install exploratory-testing-advanced

1Skills CLI (Vercel)

npx skills add proffesor-for-testing/agentic-qe --skill exploratory-testing-advanced -a claude-code

2Manually: put the files in place

~/.claude/skills/exploratory-testing-advanced/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/exploratory-testing-advanced/

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

Questions about exploratory-testing-advanced

How do I install exploratory-testing-advanced in Claude Code?

Run npx skills add proffesor-for-testing/agentic-qe --skill exploratory-testing-advanced -a claude-code. The skill file is available at ~/.claude/skills/exploratory-testing-advanced/SKILL.md.

What does exploratory-testing-advanced do?

It helps structure exploratory testing by selecting heuristics or a test tour, recording observations, and reviewing findings at the end of a session.

How does an SBTM session work?

Set a mission, scope, and focus, then investigate the software and take notes. Debrief by summarizing findings, setting priorities, and sharing results.

Source text

SKILL.md · MIT
---
name: exploratory-testing-advanced
description: "Advanced exploratory testing techniques with Session-Based Test Management (SBTM), RST heuristics, and test tours. Use when planning exploration sessions, investigating bugs, or discovering unknown quality risks."
category: testing-methodologies
priority: high
tokenEstimate: 1000
agents: [qe-flaky-test-hunter, qe-visual-tester, qe-quality-analyzer]
implementation_status: optimized
optimization_version: 1.0
last_optimized: 2025-12-02
dependencies: []
quick_reference_card: true
tags: [exploratory, sbtm, rst, heuristics, test-tours, session-based]
trust_tier: 0
validation:
---

# Advanced Exploratory Testing

<default_to_action>
When exploring software or investigating quality risks:
1. CREATE charter with mission, scope, and time-box (45-90 min)
2. APPLY heuristics: SFDIPOT (quality criteria), FEW HICCUPPS (consistency oracles)
3. EXPLORE systematically using test tours (Business District, Bad Neighborhood, Historical)
4. DOCUMENT findings in real-time with notes, screenshots, evidence
5. DEBRIEF: What learned? What's next? Share via agent memory

**Quick Heuristic Selection:**
- What to test → SFDIPOT (Structure, Function, Data, Interfaces, Platform, Operations, Time)
- Recognize problems → FEW HICCUPPS (Familiar, Explainable, World, History, Image, Comparable, Claims, Users, Product, Purpose, Standards)
- Navigate app → Test Tours (12 types for different exploration strategies)

**Critical Success Factors:**
- Exploration is skilled, structured thinking - not random clicking
- Document discoveries, not pre-planned test cases
- Pair testing reveals more than solo exploration
</default_to_action>

## Quick Reference Card

### When to Use
- Investigating new or changed features
- Finding bugs automation misses
- Learning unfamiliar systems
- Risk discovery before test planning

### Session Structure (SBTM)
| Phase | Duration | Activity |
|-------|----------|----------|
| Charter | 5 min | Define mission, scope, focus |
| Explore | 45-75 min | Systematic investigation |
| Note | Continuous | Document findings real-time |
| Debrief | 10-15 min | Summarize, prioritize, share |

### SFDIPOT Heuristic (What to Test)
| Letter | Focus | Example Questions |
|--------|-------|------------------|
| **S**tructure | Is it properly composed? | Code structure, UI layout, data schema |
| **F**unction | Does it do what it should? | Core features work correctly |
| **D**ata | Handles data correctly? | CRUD, validation, persistence |
| **I**nterfaces | Interacts well? | APIs, UI, integrations |
| **P**latform | Works in environment? | Browsers, OS, devices |
| **O**perations | Can be used/managed? | Install, config, monitor |
| **T**ime | Handles timing? | Concurrency, timeouts, scheduling |

### FEW HICCUPPS Oracle (Recognize Problems)
| Consistency With | Check |
|-----------------|-------|
| **F**amiliar problems | Does this look like a known bug pattern? |
| **E**xplainable | Can behavior be explained rationally? |
| **W**orld | Matches real-world expectations? |
| **H**istory | Consistent with prior versions? |
| **I**mage | Matches brand/product image? |
| **C**omparable | Similar to competing products? |
| **C**laims | Matches specs/docs/marketing? |
| **U**sers | Meets user expectations? |
| **P**urpose | Fulfills intended purpose? |
| **S**tatements | Matches what devs said? |

### Test Tours (12 Types)
| Tour | Strategy |
|------|----------|
| Business District | Critical business flows |
| Historical | Where bugs clustered before |
| Bad Neighborhood | Known problem areas |
| Money | Revenue-impacting features |
| Landmark | Navigate by key features |
| Intellectual | Complex, thinking-intensive features |
| FedEx | Follow data through system |
| Garbage Collector | Cleanup and edge cases |
| Museum | Help docs and examples |
| Rained-Out | What happens when things fail? |
| Couch Potato | Minimal effort paths |
| Obsessive-Compulsive | Repetitive actions |

---

## Session Note Template

```markdown
**Charter:** Explore [area] to discover [what] focusing on [heuristic]
**Time-box:** 60 min | **Tester:** [name] | **Date:** [date]

## Session Notes
- [timestamp] Observation/finding
- [timestamp] Bug: [description] - [severity]
- [timestamp] Question: [unclear behavior]

## Findings Summary
- Bugs: X (Critical: Y, Major: Z)
- Questions: X
- Ideas: X

## Coverage
- Areas explored: [list]
- Heuristics used: [SFDIPOT areas]
- % Time on: Bug investigation 30%, Exploration 50%, Setup 20%

## Next Steps
- [ ] Deep dive on [area]
- [ ] Follow up on question about [topic]
```

---

## Agent-Assisted Exploration

```typescript
// Collaborative exploration session
await Task("Exploratory Session", {
  charter: 'Explore checkout flow for payment edge cases',
  duration: '60min',
  heuristics: ['SFDIPOT', 'FEW_HICCUPPS'],
  tour: 'money',
  collaboration: 'human-navigator-agent-driver'
}, "qe-flaky-test-hunter");

// Agent generates test variations while human observes
await Task("Edge Case Generation", {
  area: 'payment-form',
  variations: ['boundary-values', 'invalid-inputs', 'concurrent-submits']
}, "qe-test-generator");

// Visual exploration
await Task("Visual Exploration", {
  tour: 'landmark',
  focus: 'responsive-breakpoints',
  compare: 'baseline-screenshots'
}, "qe-visual-tester");
```

---

## Agent Coordination Hints

### Memory Namespace
```
aqe/exploratory/
├── sessions/*           - Session notes and findings
├── charters/*           - Reusable charter templates
├── bug-clusters/*       - Historical bug patterns
└── heuristic-results/*  - What heuristics revealed
```

### Fleet Coordination
```typescript
const exploratoryFleet = await FleetManager.coordinate({
  strategy: 'exploratory-testing',
  agents: [
    'qe-flaky-test-hunter',   // Pattern recognition
    'qe-visual-tester',       // Visual anomalies
    'qe-quality-analyzer'     // Risk assessment
  ],
  topology: 'mesh'
});
```

---

## Pairing Patterns

| Pattern | Human Role | Agent Role |
|---------|------------|------------|
| Driver-Navigator | Navigate strategy | Execute variations |
| Strong-Style | Dictate actions | Record findings |
| Ping-Pong | Observe one area | Explore another |

---

## Related Skills
- [context-driven-testing](../context-driven-testing/) - RST foundations
- [risk-based-testing](../risk-based-testing/) - Focus exploration on risk
- [agentic-quality-engineering](../agentic-quality-engineering/) - Agent coordination

---

## Remember

**Exploratory testing = simultaneous learning, test design, and test execution.**

Not random clicking. Structured, skilled investigation guided by heuristics and oracles. Document discoveries in real-time. Pair testing amplifies findings.

**With Agents:** Agents generate variations, recognize patterns, and maintain session notes while humans apply judgment and intuition. Combine agent thoroughness with human insight.

## Gotchas

- Agent treats exploratory testing as scripted test execution — remind it: exploration means learning + adapting in real-time
- Session notes from agents lack the "why I tried this" reasoning — explicitly ask for decision rationale
- 90-minute sessions cause context overflow — cap at 45 minutes with explicit debrief
- Agent defaults to happy-path exploration — explicitly assign "Bad Neighborhood" or "Saboteur" tours for negative testing
- SFDIPOT heuristics are misapplied when agent doesn't understand the domain — provide domain context upfront

© proffesor-for-testing · MIT · proffesor-for-testing/agentic-qe

Similar skills

All skills for Testing and QA →

From the same set73

The whole set →
qcsd-cicd-swarm The qcsd-cicd-swarm Claude Code skill checks CI/CD pipelines before release and assesses deployment readiness. It reviews regression risk and flaky tests, then returns a RELEASE, REMEDIATE, or BLOCK decision. CX Codex +1 104installs test-idea-rewriting test-idea-rewriting is a Claude Code skill that turns passive test descriptions into active actions with observable results. It runs when test ideas are vague or fail quality validation. CX Codex +1 104installs cicd-pipeline-qe-orchestrator The cicd-pipeline-qe-orchestrator skill assigns quality checks and QE agents to CI/CD stages, from commit through production. Use it to plan pipeline testing and define release gates. CX Codex +1 1installs accessibility-testing accessibility-testing — a skill with checklists and test snippets for checking keyboard navigation, color contrast and screen reader support against WCAG 2.2. CX Codex +1 1installs qe-visual-accessibility qe-visual-accessibility runs WCAG 2.2 accessibility audits and catches UI regressions through pixel-diff screenshot comparisons. It validates responsive layouts after CSS or component changes. CX Codex +1 1installs compliance-testing compliance-testing is a skill that checks an app against GDPR, CCPA, HIPAA, SOC2, and PCI-DSS, and tests user rights, encryption, and access logs before audits or during work with personal data. CX Codex +1 1installs quality-metrics Tracks software quality metrics like defect density, DORA indicators, MTTD, and bug escape rates for CI quality gates. CX Codex +1 1installs bug-reporting-excellence The bug-reporting-excellence skill guides an agent through clear bug reports with reproduction steps, environment details, and impact. Use it when documenting defects or setting reporting standards for a team. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open