qe-test-execution — Claude Code skill: what it does, how to install
qe-test-execution orchestrates Jest, Vitest, and Playwright suites using the aqe CLI with parallel workers, affected-test selection, and flaky test retries.
MIT 122 installs ★ 533 updated 2026-10-25
npx skills add proffesor-for-testing/agentic-qe --skill qe-test-execution -a claude-codeWhat qe-test-execution does
The skill orchestrates test suite runs across Jest, Vitest, and Playwright via the aqe CLI tool. It organizes parallel execution with worker processes, selects tests based on git diffs, and reruns flaky tests with configurable delays.
Work is divided across subagents. The qe-test-executor handles test execution alongside JUnit reporting, qe-test-selector finds impacted code from HEAD~1, and qe-flaky-detector quarantines tests that fail repeatedly. Outputs compile into a single result object with timing metrics and logs.
Parallel execution can hide flaky failures. For diagnosis, switch back to --workers=1. Full test runs inside containers also risk out-of-memory crashes, so intermediate outputs should be written directly to disk rather than stored in session memory.
What it helps with
- run test suites across multiple parallel workers or CI shards
- execute only tests affected by recent git changes
- quarantine and retry flaky tests automatically
- export aggregated execution results to JUnit and JSON reports
Example prompts for the agent
- Run only affected tests against HEAD~1 using 4 parallel workers
- Execute the full test suite with 3 retries for flaky failures and generate a JUnit report
- Configure test execution with sharding for our CI matrix pipeline
How to install qe-test-execution
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill qe-test-execution -a claude-code2Manually: put the files in place
~/.claude/skills/qe-test-execution/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/qe-test-execution/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill qe-test-execution -a codex2Manually: put the files in place
.agents/skills/qe-test-execution/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill qe-test-execution -a cursor2Manually: put the files in place
.cursor/skills/qe-test-execution/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install proffesor-for-testing/agentic-qe assets/skills/qe-test-execution2Manually: put the files in place
.github/skills/qe-test-execution/SKILL.md1Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill qe-test-execution -a gemini-cli2Platform CLI
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/qe-test-executionManually: put the files in place
.devin/skills/qe-test-execution/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add proffesor-for-testing/agentic-qe --skill qe-test-execution -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 qe-test-execution
How to install qe-test-execution in Claude Code?
Run npx skills add proffesor-for-testing/agentic-qe --skill qe-test-execution -a claude-code. The skill file will be placed at ~/.claude/skills/qe-test-execution/SKILL.md.
What does qe-test-execution do?
It directs test orchestration for Jest, Vitest, and Playwright via aqe test run. It manages parallel sharding, filters suites by git changes, and handles flaky retries.
How does it diagnose flaky tests?
Parallel execution can hide intermittent failures, so the author advises switching to --workers=1 when debugging flakiness. The system also supports quarantine thresholds and automated retry loops.
Source text
SKILL.md · MIT
---
name: "qe-test-execution"
description: "Orchestrates test suite execution with parallel sharding, intelligent retry, and real-time reporting across Jest, Vitest, and Playwright. Use when running test suites, optimizing execution time, handling flaky tests, configuring CI test pipelines, or analyzing test run results."
trust_tier: 3
validation:
schema_path: schemas/output.json
validator_path: scripts/validate-config.json
eval_path: evals/qe-test-execution.yaml
---
# QE Test Execution
## Purpose
Guide the use of v3's test execution capabilities including parallel orchestration, smart test selection, flaky test handling, and distributed execution across multiple environments.
## Activation
- When running test suites
- When optimizing test execution time
- When handling flaky tests
- When setting up CI/CD test pipelines
- When executing tests across environments
## Quick Start
```bash
# Run all tests with parallelization
aqe test run --parallel --workers 4
# Run affected tests only
aqe test run --affected --since HEAD~1
# Run with retry for flaky tests
aqe test run --retry 3 --retry-delay 1000
# Run specific test types
aqe test run --type unit,integration --exclude e2e
```
## Agent Workflow
```typescript
// Orchestrate test execution
Task("Execute test suite", `
Run the full test suite with:
- 4 parallel workers
- Retry flaky tests up to 3 times
- Generate JUnit report
- Fail fast on critical tests
Report results and any failures.
`, "qe-test-executor")
// Smart test selection
Task("Run affected tests", `
Analyze changes in PR #123 and:
- Identify affected test files
- Run only relevant tests
- Include integration tests for changed modules
- Report coverage delta
`, "qe-test-selector")
```
## Execution Strategies
### 1. Parallel Execution
```typescript
await testExecutor.runParallel({
suites: ['unit', 'integration'],
workers: 4,
distribution: 'by-file', // or 'by-test', 'by-duration'
isolation: 'process',
sharding: {
enabled: true,
total: 4,
index: process.env.SHARD_INDEX
}
});
```
### 2. Smart Test Selection
```typescript
await testExecutor.runAffected({
changes: gitChanges,
selection: {
direct: true, // Tests for changed files
transitive: true, // Tests for dependents
integration: true // Integration tests touching changed code
},
fallback: 'full-suite' // If analysis fails
});
```
### 3. Flaky Test Handling
```typescript
await testExecutor.handleFlaky({
detection: {
enabled: true,
threshold: 0.1, // 10% flake rate
window: 100 // Last 100 runs
},
strategy: {
retry: 3,
quarantine: true,
notify: ['#flaky-tests']
}
});
```
## Execution Configuration
```yaml
execution:
parallel:
workers: auto # CPU cores - 1
timeout: 30000
bail: false
retry:
count: 2
delay: 1000
only_failed: true
reporting:
formats: [junit, json, html]
include_timing: true
include_logs: true
environments:
- name: node-18
image: node:18-alpine
- name: node-20
image: node:20-alpine
```
## CI/CD Integration
```yaml
# GitHub Actions example
test:
runs-on: ubuntu-latest
strategy:
matrix:
shard: [1, 2, 3, 4]
steps:
- uses: actions/checkout@v4
- name: Run tests
run: |
aqe test run \
--shard ${{ matrix.shard }}/4 \
--parallel \
--report junit
- name: Upload results
uses: actions/upload-artifact@v4
with:
name: test-results-${{ matrix.shard }}
path: reports/
```
## Result Aggregation
```typescript
interface ExecutionResults {
summary: {
total: number;
passed: number;
failed: number;
skipped: number;
flaky: number;
duration: number;
};
shards: ShardResult[];
failures: TestFailure[];
flakyTests: FlakyTest[];
coverage: CoverageReport;
timing: TimingAnalysis;
}
```
## Gotchas
- Full test suites may OOM in containers — the rule "don't run full suite" was violated 20x despite being in CLAUDE.md. Fix: make suite lightweight, don't just add more rules
- Fewer focused agents (3-4) outperform many vague ones (6-8) — always include verification command in each agent prompt
- New model releases can shift agent behavior mid-sprint — rules followed yesterday may be ignored today after model update
- Running all tests in parallel can mask flaky tests — use `--workers=1` for initial diagnosis
- Session crashes lose all context — save intermediate results to disk, not just memory
## Coordination
**Primary Agents**: qe-test-executor, qe-test-selector, qe-flaky-detector
**Coordinator**: qe-test-execution-coordinator
**Related Skills**: qe-test-generation, qe-coverage-analysis
© proffesor-for-testing · MIT · proffesor-for-testing/agentic-qe