holistic-testing-pact — Claude Code skill: setup and guide
holistic-testing-pact builds testing strategies around PACTS principles and holistic quadrants. It structures quality planning for classical, AI-assisted, and autonomous agent setups.
MIT 111 installs ★ 533 updated 2026-11-04
npx skills add proffesor-for-testing/agentic-qe --skill holistic-testing-pact -a claude-codeWhat holistic-testing-pact does
The skill applies the Holistic Testing Model combined with PACTS principles: Proactive, Autonomous, Collaborative, Targeted, and Structured. It divides test suites into four distinct quadrants, keeping developer-facing fast feedback loops separate from business acceptance testing. Specific tasks get routed to dedicated agents from the repository, including qe-test-architect and qe-requirements-validator.
The Structured principle reflects DORA research on AI delivery mechanisms. When autonomous agents handle quality engineering, the framework demands auditable decision traces and explicit guardrails. Running autonomous agents without established boundaries is treated as an anti-pattern, because adding agents to chaotic workflows merely automates the chaos.
What it helps with
- map test suites across technical and business quadrants
- run proactive risk analysis during refinement
- audit autonomous agent decisions through confidence scores and traces
- prune valueless checks to focus on high-risk workflows
Example prompts for the agent
- Design a PACTS testing strategy for the checkout service
- Run risk analysis on user story requirements using qe-requirements-validator
- Establish governance guardrails and decision traces for test agents
How to install holistic-testing-pact
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill holistic-testing-pact -a claude-code2Manually: put the files in place
~/.claude/skills/holistic-testing-pact/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/holistic-testing-pact/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill holistic-testing-pact -a codex2Manually: put the files in place
.agents/skills/holistic-testing-pact/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill holistic-testing-pact -a cursor2Manually: put the files in place
.cursor/skills/holistic-testing-pact/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install proffesor-for-testing/agentic-qe assets/skills/holistic-testing-pact2Manually: put the files in place
.github/skills/holistic-testing-pact/SKILL.md1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill holistic-testing-pact -a gemini-cli2Platform CLI
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/holistic-testing-pactManually: put the files in place
.devin/skills/holistic-testing-pact/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill holistic-testing-pact -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 holistic-testing-pact
How to install holistic-testing-pact in Claude Code?
Run npx skills add proffesor-for-testing/agentic-qe --skill holistic-testing-pact -a claude-code in your terminal. This writes the skill to ~/.claude/skills/holistic-testing-pact/SKILL.md.
What does holistic-testing-pact do?
It establishes a structured test strategy across holistic quadrants and PACTS principles. It coordinates testing tasks among agents like qe-fleet-commander and qe-test-architect.
Why does PACTS add the Structured principle?
Structured was introduced based on DORA research for agentic systems. It requires observability and guardrails so teams rely on verifiable confidence rather than unmeasured trust.
Source text
SKILL.md · MIT
---
name: holistic-testing-pact
description: "Apply the Holistic Testing Model evolved with PACTS (Proactive, Autonomous, Collaborative, Targeted, Structured) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices."
category: testing-methodologies
priority: critical
tokenEstimate: 1100
agents: [qe-fleet-commander, qe-test-architect, qe-quality-gate, qe-requirements-validator]
implementation_status: optimized
optimization_version: 1.0
last_optimized: 2025-12-02
dependencies: []
quick_reference_card: true
tags: [holistic, pacts, quality, whole-team, proactive, autonomous, collaborative, targeted, structured]
trust_tier: 0
validation:
---
# Holistic Testing Model with PACTS Principles
<default_to_action>
When designing test strategies or building quality into teams:
1. APPLY PACTS principles: Proactive (test before bugs), Autonomous (teams own quality), Collaborative (whole-team responsibility), Targeted (risk-focused), Structured (governance, observability, and explainability of agent behavior)
2. IDENTIFY quadrant focus: Technology-facing (unit, integration, performance) or Business-facing (acceptance, exploratory, usability)
3. SELECT agents based on PACTS dimension and testing quadrant
4. IMPLEMENT feedback loops that catch issues in minutes, not days
5. MEASURE outcomes (bug escape rate, release confidence, agent confidence) not activities (test count)
**Quick PACTS Application:**
- Proactive → Design testability into architecture, risk analysis during refinement
- Autonomous → Devs run tests locally, CI gates automated wherever risk and regulation allow
- Collaborative → Three Amigos, QE pairs with dev, shared test ownership
- Targeted → Risk-based planning, focus on critical flows, kill valueless tests
- Structured → Governance, observability, and explainability of agent behavior; measure confidence, not trust
**Critical Success Factors:**
- Quality is a whole-team responsibility, not a QA phase
- QA as enablers (build infrastructure, coach), not gatekeepers
- Fast feedback during development, not after
</default_to_action>
## Quick Reference Card
### When to Use
- Designing comprehensive test strategies
- Building quality culture in teams
- Choosing testing approach for new projects
- Evolving from sequential QA to concurrent quality
### PACTS Principles
| Principle | Focus | Anti-Pattern |
|-----------|-------|--------------|
| **Proactive** | Test before code, design testability | Waiting for bugs to find you |
| **Autonomous** | Teams deploy when ready | QA as manual gatekeepers |
| **Collaborative** | Whole-team quality thinking | QA works in isolation |
| **Targeted** | Risk-based, high-value tests | Exhaustive checkbox testing |
| **Structured** | Governance, observability, explainability of agent behavior | Bolting agentic AI onto chaos |
### Holistic Testing Quadrants
| Quadrant | Purpose | Examples |
|----------|---------|----------|
| Tech + Support | Fast feedback | Unit, component, integration tests |
| Tech + Critique | Find limits | Performance, security, chaos |
| Business + Support | Shared understanding | BDD, acceptance tests |
| Business + Critique | Discover unknowns | Exploratory, usability, A/B |
### Agent Selection by PACTS + Quadrant
| PACTS Dimension | Agents |
|----------------|--------|
| Proactive + Tech | qe-test-architect, qe-requirements-validator |
| Autonomous + Tech | qe-parallel-executor, qe-coverage-specialist |
| Collaborative | qe-fleet-commander (orchestration) |
| Targeted | qe-regression-analyzer, qe-quality-gate |
| Structured | qe-fleet-commander, qe-quality-gate (governance, observability, explainability) |
---
## PACTS in Practice
### Proactive: Test Before Bugs
```javascript
// During API design, ask: "How will we know if this times out under load?"
// Build observability from start
await Task("Risk Analysis", {
phase: 'refinement',
question: 'What could go wrong and how will we know?'
}, "qe-requirements-validator");
```
### Autonomous: Teams Own Quality
- Developers run full test suite locally
- CI fails fast with clear diagnostics
- Deployment approvals automated where the risk allows; where regulation or risk requires a human sign-off, make it fast and evidence-based rather than a queue
- Self-service test environments
### Collaborative: Whole-Team Thinking
- QE attends planning and refinement
- Three Amigos for every user story
- Shared ownership of test code
- Ensemble testing for complex scenarios
### Targeted: Test What Matters
```javascript
// E-commerce checkout? Test thoroughly.
// Admin panel used twice a month? Lighter touch.
await Task("Risk-Based Planning", {
critical: ['checkout', 'payment'],
light: ['admin-panel', 'settings']
}, "qe-regression-analyzer");
```
### Structured: Governance, Observability, Explainability
The 5th principle for agentic systems. As agents take on quality work, you need
governance (boundaries and guardrails), observability (what agents did and why),
and explainability (decisions you can audit). Especially important in regulated
industries.
- We measure **CONFIDENCE, not trust** — trust is a human feeling; confidence can
be mathematically explained.
- Ships with a playbook + readiness-assessment guide.
- Anti-pattern: bolting agentic AI onto chaos. Structure first, then automate.
```javascript
// Make agent behavior auditable and explainable, not a black box
await Task("Agent Governance Review", {
guardrails: ['scope-boundaries', 'approval-gates'],
observability: ['decision-traces', 'confidence-scores'],
explainability: 'every-decision-auditable'
}, "qe-fleet-commander");
```
---
## From PACT to PACTS
PACT originated with Reuven Cohen (Agentics Foundation) and was adapted to quality
engineering by Dragan Spiridonov. PACTS adds a fifth principle — **Structured** —
inspired by DORA's research on AI-assisted delivery and platform-engineering
quality measurement. The addition reflects that autonomous, agentic quality work
needs governance, observability, and explainability to earn confidence at scale.
---
## Evolution from Traditional
| Old Way (Sequential) | Holistic + PACTS (Concurrent) |
|---------------------|------------------------------|
| Dev writes → QA tests → bugs found → fixes | Team discusses what to build and how to test |
| Slow feedback, finger-pointing | Fast feedback, shared ownership |
| Quality as gatekeeping | Quality as enabler |
| QA on critical path | QA builds infrastructure, coaches |
---
## Success Signals
- Deployments happen as often as the business and its risk profile need, without fear (a medical device and a consumer web app have different right answers)
- Bug escape rate trending down
- Team discusses quality naturally
- Developers write tests without being told
- Releases are boring (in a good way)
---
## Agent Coordination Hints
### Memory Namespace
```
aqe/holistic-testing/
├── pacts-assessment/* - PACTS maturity analysis
├── quadrant-coverage/* - Coverage per quadrant
├── team-metrics/* - Quality ownership metrics
└── feedback-loops/* - Cycle time data
```
### Fleet Coordination
```typescript
const holisticFleet = await FleetManager.coordinate({
strategy: 'holistic-testing',
pacts: { proactive: true, autonomous: true, collaborative: true, targeted: true, structured: true },
agents: [
'qe-fleet-commander', // Orchestration
'qe-test-architect', // Tech quadrant
'qe-requirements-validator', // Business quadrant
'qe-quality-gate' // Quality decisions
],
topology: 'mesh'
});
```
---
## Related Skills
- [agentic-quality-engineering](../agentic-quality-engineering/) - Agent coordination
- [context-driven-testing](../context-driven-testing/) - Adapt to context
- [shift-left-testing](../shift-left-testing/) - Proactive testing
- [risk-based-testing](../risk-based-testing/) - Targeted testing
---
## Remember
**PACTS = Proactive + Autonomous + Collaborative + Targeted + Structured**
Quality is built in, not tested in. Teams own quality. QA enables, doesn't gate. Test what matters, skip what doesn't. Govern agent behavior with observability and explainability — measure confidence, not trust. Measure outcomes, not activities.
**With Agents:** Agents analyze PACTS maturity, recommend quadrant coverage, and coordinate whole-team quality. Use agents to scale holistic thinking while maintaining human judgment.
© proffesor-for-testing · MIT · proffesor-for-testing/agentic-qe