shift-left-testing · proffesor-for-testing — Claude Code skill: testing and installation
The shift-left-testing skill moves checks earlier in development: validate requirements, write tests before implementation, and run them in CI. Use it when introducing TDD or other early quality practices.
MIT 117 installs ★ 533 updated 2026-10-25
npx skills add proffesor-for-testing/agentic-qe --skill shift-left-testing -a claude-codeWhat shift-left-testing does
The skill lays out a workflow that checks whether requirements are testable before coding, puts tests ahead of implementation, and automates checks in CI. Its four levels cover unit tests in pull requests, TDD, BDD scenarios during refinement, and risk analysis during design.
It can coordinate agents for requirement checks, unit, integration, and end-to-end test generation, plus regression selection based on changed files. The CI example runs npm run test:unit and npm run test:integration, then checks coverage. Generating tests before understanding the requirements can encode the wrong behavior.
The skill is listed for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. On Claude Code, install it with npx skills; its file is at ~/.claude/skills/shift-left-testing/SKILL.md.
What it helps with
- check requirements for ambiguity before coding
- write tests before implementing a feature
- run unit and integration tests in CI
- select regression tests from changed files
- add a coverage check to a CI pipeline
Example prompts for the agent
- Check these requirements for testability and ambiguity before coding.
- Generate unit, integration, and end-to-end tests from these requirements.
- Choose regression tests for the files changed in this pull request.
How to install shift-left-testing
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill shift-left-testing -a claude-code2Manually: put the files in place
~/.claude/skills/shift-left-testing/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/shift-left-testing/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill shift-left-testing -a codex2Manually: put the files in place
.agents/skills/shift-left-testing/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill shift-left-testing -a cursor2Manually: put the files in place
.cursor/skills/shift-left-testing/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install proffesor-for-testing/agentic-qe assets/skills/shift-left-testing2Manually: put the files in place
.github/skills/shift-left-testing/SKILL.md1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill shift-left-testing -a gemini-cli2Platform CLI
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/shift-left-testingManually: put the files in place
.devin/skills/shift-left-testing/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill shift-left-testing -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 shift-left-testing
How do I install shift-left-testing in Claude Code?
Run npx skills add proffesor-for-testing/agentic-qe --skill shift-left-testing -a claude-code. The skill file is at ~/.claude/skills/shift-left-testing/SKILL.md.
What does shift-left-testing do?
It guides requirement checks before coding, test creation before implementation, and automated checks in CI. It also describes selecting regression tests based on changed files.
Which agents does shift-left-testing use?
It names qe-requirements-validator for requirement checks, qe-test-generator for test creation, and qe-regression-risk-analyzer for regression analysis.
Source text
SKILL.md · MIT
---
name: shift-left-testing
description: "Move testing activities earlier in the development lifecycle to catch defects when they're cheapest to fix. Use when implementing TDD, CI/CD, or early quality practices."
category: testing-methodologies
priority: high
tokenEstimate: 900
agents: [qe-test-generator, qe-requirements-validator, qe-regression-risk-analyzer]
implementation_status: optimized
optimization_version: 1.0
last_optimized: 2025-12-02
dependencies: []
quick_reference_card: true
tags: [shift-left, early-testing, tdd, bdd, ci-cd, prevention]
trust_tier: 3
validation:
schema_path: schemas/output.json
validator_path: scripts/validate-config.json
eval_path: evals/shift-left-testing.yaml
---
# Shift-Left Testing
<default_to_action>
When implementing early testing practices:
1. VALIDATE requirements before coding (testability, BDD scenarios)
2. WRITE tests before implementation (TDD)
3. AUTOMATE in CI pipeline (every commit triggers tests)
4. FIX defects immediately - never let them accumulate
**Quick Shift-Left Levels:**
- Level 1: Unit tests with each PR (developer responsibility)
- Level 2: TDD practice (tests before code)
- Level 3: BDD/Example mapping in refinement (requirements testing)
- Level 4: Risk analysis in design (architecture testing)
</default_to_action>
## Quick Reference Card
### When to Use
- Reducing cost of defects
- Implementing CI/CD pipelines
- Starting TDD practice
- Improving requirements quality
### Shift-Left Levels
| Level | Practice | When |
|-------|----------|------|
| 1 | Unit tests in PR | Before merge |
| 2 | TDD | Before implementation |
| 3 | BDD/Example Mapping | During refinement |
| 4 | Risk Analysis | During design |
---
## Level 1: Tests in Every PR
```yaml
# CI pipeline - tests run on every commit
name: CI
on: [push, pull_request]
jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- run: npm ci
- run: npm run test:unit
- run: npm run test:integration
- run: npm run lint
quality-gate:
needs: test
steps:
- name: Coverage Check
run: npx coverage-check --min 80
- name: No New Warnings
run: npm run lint -- --max-warnings 0
```
---
## Agent-Assisted Shift-Left
```typescript
// Validate requirements testability
await Task("Requirements Validation", {
requirements: userStories,
check: ['INVEST-criteria', 'testability', 'ambiguity'],
generateBDD: true
}, "qe-requirements-validator");
// Generate tests from requirements
await Task("Generate Tests", {
source: 'requirements',
types: ['unit', 'integration', 'e2e'],
coverage: 'comprehensive'
}, "qe-test-generator");
// Smart test selection for changes
await Task("Select Regression Tests", {
changedFiles: prFiles,
algorithm: 'risk-based',
targetReduction: 0.7 // 70% time savings
}, "qe-regression-risk-analyzer");
```
---
## Agent Coordination Hints
### Memory Namespace
```
aqe/shift-left/
├── requirements/* - Validated requirements
├── generated-tests/* - Auto-generated tests
├── coverage-targets/* - Coverage goals by component
└── pipeline-results/* - CI/CD test history
```
### Fleet Coordination
```typescript
const shiftLeftFleet = await FleetManager.coordinate({
strategy: 'shift-left',
agents: [
'qe-requirements-validator', // Level 3-4
'qe-test-generator', // Level 2
'qe-regression-risk-analyzer' // Smart selection
],
topology: 'sequential'
});
```
---
## Related Skills
- [tdd-london-chicago](../tdd-london-chicago/) - TDD practices
- [holistic-testing-pact](../holistic-testing-pact/) - Proactive testing
- [cicd-pipeline-qe-orchestrator](../cicd-pipeline-qe-orchestrator/) - Pipeline integration
- [shift-right-testing](../shift-right-testing/) - Production feedback
---
## Remember
**With Agents:** Agents validate requirements testability, generate tests from specs, and select optimal regression suites. Use agents to implement shift-left practices consistently.
## Skill Composition
- **TDD practice** → Use `/tdd-london-chicago` for specific TDD guidance
- **Generate tests** → Use `/qe-test-generation` for AI-powered test generation
- **CI/CD quality** → Use `/cicd-pipeline-qe-orchestrator` for pipeline setup
## Gotchas
- "Shift left" doesn't mean "only test left" — production monitoring (shift right) is still needed
- Agent generates tests before understanding requirements — tests for wrong behavior are worse than no tests
- CI pipeline tests that take >10 minutes kill the feedback loop — keep commit-stage tests under 5 minutes
- TDD discipline degrades when agent writes test+code simultaneously — enforce Red phase separation
- Shifting left without lightweight environments just shifts the bottleneck — fix environments first
© proffesor-for-testing · MIT · proffesor-for-testing/agentic-qe
Similar skills
All skills for Testing and QA →shift-left-testing by other authors comes first.