agentic-qe 3.8.1 → 3.8.3

package/assets/skills/performance-testing/SKILL.md

@@ -313,3 +313,24 @@ const perfFleet = await FleetManager.coordinate({
 **Trend over time:** Catch degradation early
 
 **With Agents:** Agents automate load testing, analyze bottlenecks, and compare with production. Use agents to maintain performance at scale.
+
+## Run History
+
+After each performance test run, append results to `run-history.json` in this skill directory:
+```bash
+node -e "
+const fs = require('fs');
+const h = JSON.parse(fs.readFileSync('.claude/skills/performance-testing/run-history.json'));
+h.runs.push({date: new Date().toISOString().split('T')[0], scenario: 'load', p95_ms: P95, throughput_rps: RPS, error_rate_pct: ERR});
+fs.writeFileSync('.claude/skills/performance-testing/run-history.json', JSON.stringify(h, null, 2));
+"
+```
+Read `run-history.json` before each run — compare with baselines. Alert if p95 increases >20% from baseline.
+
+## Gotchas
+
+- k6 scripts generated by agent often hardcode base URLs — use environment variables for portability
+- Load tests in containers hit resource limits before app limits — ensure container has 2x the resources of target
+- Agent forgets to include think time between requests — without it, load is unrealistically bursty
+- P95 vs P99 matters — agent defaults to averages which hide tail latency problems
+- Baseline comparison requires consistent environment — CI runner variance can cause 20%+ noise

package/assets/skills/performance-testing/config.json

@@ -0,0 +1,18 @@
+{
+  "$schema": "./config-schema.json",
+  "_description": "Performance Testing configuration. Auto-created on first run. Edit to customize.",
+  "tool": null,
+  "baseline_file": null,
+  "thresholds": {
+    "p95_response_ms": 500,
+    "error_rate_percent": 1,
+    "throughput_rps": 100
+  },
+  "options": {
+    "duration": "30s",
+    "vus": 10,
+    "rampUp": "10s",
+    "thinkTime": "1s"
+  },
+  "_setupPrompt": "If tool is null, ask: 'Which load testing tool do you use? (k6/artillery/jmeter)'. If baseline_file is null, ask: 'Do you have an existing performance baseline file? (path or \"none\")'."
+}

package/assets/skills/performance-testing/references/k6-patterns.md

@@ -0,0 +1,72 @@
+# k6 Load Testing Patterns
+
+## Basic Load Test
+```javascript
+import http from 'k6/http';
+import { check, sleep } from 'k6';
+
+export const options = {
+  stages: [
+    { duration: '30s', target: 20 },  // ramp up
+    { duration: '1m', target: 20 },   // steady state
+    { duration: '10s', target: 0 },   // ramp down
+  ],
+  thresholds: {
+    http_req_duration: ['p(95)<500'],
+    http_req_failed: ['rate<0.01'],
+  },
+};
+
+export default function () {
+  const res = http.get(`${__ENV.BASE_URL}/api/endpoint`);
+  check(res, {
+    'status is 200': (r) => r.status === 200,
+    'response time < 500ms': (r) => r.timings.duration < 500,
+  });
+  sleep(1); // Think time — don't forget!
+}
+```
+
+## Stress Test Pattern
+```javascript
+export const options = {
+  stages: [
+    { duration: '2m', target: 100 },
+    { duration: '5m', target: 100 },
+    { duration: '2m', target: 200 },
+    { duration: '5m', target: 200 },
+    { duration: '2m', target: 0 },
+  ],
+};
+```
+
+## Spike Test Pattern
+```javascript
+export const options = {
+  stages: [
+    { duration: '10s', target: 10 },
+    { duration: '1m', target: 10 },
+    { duration: '10s', target: 1000 },  // spike!
+    { duration: '3m', target: 1000 },
+    { duration: '10s', target: 10 },
+  ],
+};
+```
+
+## Soak Test Pattern
+```javascript
+export const options = {
+  stages: [
+    { duration: '5m', target: 50 },
+    { duration: '4h', target: 50 },  // long duration
+    { duration: '5m', target: 0 },
+  ],
+};
+```
+
+## Tips
+- Always include `sleep()` for think time
+- Use `__ENV.BASE_URL` not hardcoded URLs
+- Set `--out json=results.json` for CI comparison
+- Use `scenarios` for complex user journeys
+- Watch for connection reuse vs real-world patterns

package/assets/skills/performance-testing/run-history.json

@@ -0,0 +1,6 @@
+{
+  "_description": "Performance testing run history. Append after each test run. Claude reads this to detect performance regressions.",
+  "_format": "Each entry: {date, scenario, p50_ms, p95_ms, p99_ms, throughput_rps, error_rate_pct, baseline_comparison}",
+  "_instructions": "After running performance tests, append results here. Compare with baselines. Alert if p95 increases >20% from baseline.",
+  "runs": []
+}

package/assets/skills/pr-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pr-review
-description: Scope-aware GitHub PR review with user-friendly tone and trust tier validation
+description: "Use when reviewing a GitHub PR for quality, scope correctness, trust tier compliance, or generating user-friendly review feedback."
 trust_tier: 0
 domain: code-review
 ---
@@ -24,8 +24,8 @@ Read the complete diff and PR description. Do not skim — read every changed fi
 
 ### 2. Scope Check
 - Only analyze AQE/QE skills (NOT Claude Flow platform skills)
-- Platform skills to EXCLUDE: v3-*, flow-nexus-*, agentdb-*, reasoningbank-*, swarm-*, github-*, hive-mind-advanced, hooks-automation, iterative-loop, stream-chain, skill-builder, sparc-methodology, pair-programming, release, debug-loop, aqe-v2-v3-migration
-- If the PR touches skills, verify the count/scope matches expectations (~78 AQE skills)
+- Platform skills to EXCLUDE: v3-*, flow-nexus-*, agentdb-*, reasoningbank-*, swarm-*, github-*, hive-mind-advanced, hooks-automation, iterative-loop, stream-chain, skill-builder, sparc-methodology, pair-programming, release, debug-loop
+- If the PR touches skills, verify the count/scope matches expectations (~82 AQE skills)
 - Flag any platform skill changes that may have leaked into an AQE-focused PR
 
 ### 3. Summarize Changes

package/assets/skills/qcsd-cicd-swarm/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: qcsd-cicd-swarm
-description: "QCSD Verification phase swarm for CI/CD pipeline quality gates using regression analysis, flaky test detection, quality gate enforcement, and deployment readiness assessment. Consumes Development outputs (SHIP/CONDITIONAL/HOLD decisions, quality metrics) and produces signals for Production monitoring."
+description: "Use when enforcing CI/CD quality gates before release, running regression analysis, detecting flaky tests, or assessing deployment readiness in the QCSD Verification phase."
 category: qcsd-phases
 priority: critical
 version: 1.0.0
@@ -48,7 +48,6 @@ validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qcsd-cicd-swarm.yaml
-
 ---
 
 # QCSD CI/CD Swarm v1.0

package/assets/skills/qcsd-development-swarm/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: qcsd-development-swarm
-description: "QCSD Development phase swarm for in-sprint code quality assurance using TDD adherence, code complexity analysis, coverage gap detection, and defect prediction. Consumes Refinement outputs (BDD scenarios, SFDIPOT priorities) and produces signals for Verification."
+description: "Use when monitoring in-sprint code quality with TDD adherence checks, complexity analysis, coverage gap detection, or defect prediction in the QCSD Development phase."
 category: qcsd-phases
 priority: critical
 version: 1.0.0
@@ -48,7 +48,6 @@ validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qcsd-development-swarm.yaml
-
 ---
 
 # QCSD Development Swarm v1.0

package/assets/skills/qcsd-ideation-swarm/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: qcsd-ideation-swarm
-description: "QCSD Ideation phase swarm for Quality Criteria sessions using HTSM v6.3, Risk Storming, and Testability analysis before development begins. Uses 5-tier browser cascade: Vibium -> agent-browser -> Playwright+Stealth -> WebFetch -> WebSearch-fallback."
+description: "Use when running Quality Criteria sessions during PI/Sprint planning with HTSM v6.3, Risk Storming, or Testability analysis in the QCSD Ideation phase."
 category: qcsd-phases
 priority: critical
 version: 7.5.1
@@ -47,7 +47,6 @@ validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qcsd-ideation-swarm.yaml
-
 ---
 
 # QCSD Ideation Swarm v7.0

package/assets/skills/qcsd-production-swarm/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: qcsd-production-swarm
-description: "QCSD Production Telemetry phase swarm for post-release production health assessment using DORA metrics, root cause analysis, defect prediction, and cross-phase feedback loops. Consumes CI/CD outputs (RELEASE/REMEDIATE/BLOCK decisions, release readiness metrics) and produces feedback signals to Ideation and Refinement."
+description: "Use when assessing post-release production health with DORA metrics, root cause analysis, defect prediction, or cross-phase feedback loops in the QCSD Production phase."
 category: qcsd-phases
 priority: critical
 version: 1.0.0
@@ -44,7 +44,6 @@ validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qcsd-production-swarm.yaml
-
 ---
 
 # QCSD Production Swarm v1.0

package/assets/skills/qcsd-production-swarm/steps/01-flag-detection.md

@@ -26,7 +26,7 @@ mcp__agentic-qe__memory_query({
 **CLI Fallback:**
 
 ```bash
-npx @claude-flow/cli@latest memory search --query "qcsd-cicd" --namespace qcsd-cicd --limit 1
+npx --no-install ruflo memory search --query "qcsd-cicd" --namespace qcsd-cicd --limit 1
 ```
 
 **Extract and record CI/CD baseline (if available):**

package/assets/skills/qcsd-production-swarm/steps/07-learning-persistence.md

@@ -131,12 +131,12 @@ Save a JSON record to `${OUTPUT_FOLDER}/09-learning-persistence.json`:
 If MCP memory_store tool is unavailable, use CLI instead (STILL MANDATORY):
 
 ```bash
-npx @claude-flow/cli@latest memory store \
+npx --no-install ruflo memory store \
   --key "qcsd-production-${RELEASE_ID}-$(date +%s)" \
   --value '{"recommendation":"[VALUE]","doraScore":[N],"slaCompliance":[N],"incidentSeverity":"[P_]","defectTrend":"[VALUE]"}' \
   --namespace qcsd-production
 
-npx @claude-flow/cli@latest hooks post-task \
+npx --no-install ruflo hooks post-task \
   --task-id "qcsd-production-${RELEASE_ID}" \
   --success true
 ```

package/assets/skills/qcsd-refinement-swarm/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: qcsd-refinement-swarm
-description: "QCSD Refinement phase swarm for Sprint Refinement sessions using SFDIPOT product factors, BDD scenario generation, and requirements validation."
+description: "Use when running Sprint Refinement sessions with SFDIPOT product factors, generating BDD scenarios, or validating requirements in the QCSD Refinement phase."
 category: qcsd-phases
 priority: critical
 version: 1.0.0
@@ -42,7 +42,6 @@ validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qcsd-refinement-swarm.yaml
-
 ---
 
 # QCSD Refinement Swarm v1.0

package/assets/skills/qcsd-refinement-swarm/steps/01-flag-detection.md

@@ -26,7 +26,7 @@ mcp__agentic-qe__memory_query({
 **CLI Fallback:**
 
 ```bash
-npx @claude-flow/cli@latest memory search --query "qcsd-ideation" --namespace qcsd-ideation --limit 1
+npx --no-install ruflo memory search --query "qcsd-ideation" --namespace qcsd-ideation --limit 1
 ```
 
 ### Step 1: Scan Story Content and Detect Flags

package/assets/skills/qe-chaos-resilience/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Chaos Resilience"
-description: "Chaos engineering and resilience testing including fault injection, load testing, and system recovery validation."
+description: "Use when injecting faults into distributed systems, validating system recovery, running load/stress tests, or building confidence in resilience through chaos engineering."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-chaos-resilience.yaml
-
 ---
 
 # QE Chaos Resilience
@@ -241,4 +240,4 @@ await resilienceTester.validateSLA({
 
 **Primary Agents**: qe-chaos-engineer, qe-load-tester, qe-resilience-tester
 **Coordinator**: qe-chaos-coordinator
-**Related Skills**: qe-performance, qe-security-compliance
+**Related Skills**: qe-performance, security-testing

package/assets/skills/qe-code-intelligence/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Code Intelligence"
-description: "Knowledge graph-based code understanding with semantic search and 80% token reduction through intelligent context retrieval."
+description: "Use when understanding unfamiliar code, searching semantically across a codebase, mapping dependencies, or reducing context window usage through intelligent retrieval."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-code-intelligence.yaml
-
 ---
 
 # QE Code Intelligence
@@ -208,6 +207,14 @@ aqe kg export --format dot --output codebase.dot
 aqe kg stats
 ```
 
+## Gotchas
+
+- WARNING: code-intelligence domain has 18% success rate — prefer direct grep/glob over agent-based code search for simple queries
+- Knowledge graph construction fails on repos >50K LOC — scope to specific modules
+- Semantic search returns irrelevant results without domain-specific embeddings — always verify search results manually
+- Agent claims "80% token reduction" but may skip critical context — verify key files are included in results
+- Fleet must be initialized before using: run `npx ruflo doctor --fix` if you get initialization errors
+
 ## Coordination
 
 **Primary Agents**: qe-knowledge-graph, qe-semantic-searcher, qe-dependency-mapper

package/assets/skills/qe-coverage-analysis/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Coverage Analysis"
-description: "O(log n) sublinear coverage gap detection with risk-weighted analysis and intelligent test prioritization."
+description: "Use when analyzing test coverage, identifying coverage gaps, prioritizing testing effort, or comparing coverage between branches."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-coverage-analysis.yaml
-
 ---
 
 # QE Coverage Analysis
@@ -186,6 +185,33 @@ quality_gates:
       - alert_on_decline: 3  # consecutive PRs
 ```
 
+## Run History
+
+After each coverage analysis, append results to `run-history.json` in this skill directory:
+```bash
+# Read current history, append new entry, write back
+node -e "
+const fs = require('fs');
+const h = JSON.parse(fs.readFileSync('.claude/skills/qe-coverage-analysis/run-history.json'));
+h.runs.push({date: new Date().toISOString().split('T')[0], statements_pct: STATEMENTS, branches_pct: BRANCHES, gaps_found: GAPS});
+fs.writeFileSync('.claude/skills/qe-coverage-analysis/run-history.json', JSON.stringify(h, null, 2));
+"
+```
+Read `run-history.json` before each run to detect trends (e.g., "coverage dropped 3 consecutive times").
+
+## Skill Composition
+
+- **Coverage dropped?** → Use `/coverage-drop-investigator` to trace the cause
+- **Need more tests** → Use `/qe-test-generation` to fill gaps
+- **Validate quality** → Use `/mutation-testing` to ensure coverage means quality
+- **Ship decision** → Feed into `/qe-quality-assessment` for deployment readiness
+
+## Gotchas
+
+- High line coverage does NOT mean good tests — 100% coverage with 0% assertions is common agent output. Use mutation testing to verify
+- coverage-analysis domain has 86% success rate — 14% of runs fail on initialization. Always verify results and have fallback plan (e.g. manual coverage tools)
+- Self-learning pipeline may silently stop learning (statusline frozen for days) — only human inspection catches this
+
 ## Coordination
 
 **Primary Agents**: qe-coverage-specialist, qe-coverage-analyzer, qe-gap-detector

package/assets/skills/qe-coverage-analysis/run-history.json

@@ -0,0 +1,6 @@
+{
+  "_description": "Coverage analysis run history. Append after each run. Claude reads this to detect trends.",
+  "_format": "Each entry: {date, scope, statements_pct, branches_pct, functions_pct, gaps_found, recommendation}",
+  "_instructions": "After running coverage analysis, append results here. Compare with previous entries to detect trends. Alert if coverage declines 3 consecutive times.",
+  "runs": []
+}

package/assets/skills/qe-defect-intelligence/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Defect Intelligence"
-description: "AI-powered defect prediction, pattern learning, and root cause analysis for proactive quality management."
+description: "Use when predicting defects before they escape, analyzing root causes of failures, learning defect patterns, or implementing proactive quality management with AI."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-defect-intelligence.yaml
-
 ---
 
 # QE Defect Intelligence

package/assets/skills/qe-iterative-loop/SKILL.md

@@ -5,7 +5,6 @@ trust_tier: 2
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
-
 ---
 
 # QE Iterative Loop

package/assets/skills/qe-learning-optimization/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Learning Optimization"
-description: "Transfer learning, metrics optimization, and continuous improvement for AI-powered QE agents."
+description: "Use when optimizing QE agent performance, applying transfer learning across test domains, tuning quality metrics, or implementing continuous improvement loops for AI-powered testing."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-learning-optimization.yaml
-
 ---
 
 # QE Learning Optimization

package/assets/skills/qe-quality-assessment/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Quality Assessment"
-description: "Comprehensive quality gates, metrics analysis, and deployment readiness assessment for continuous quality assurance."
+description: "Use when evaluating code quality, setting up quality gates, assessing deployment readiness, or generating quality reports."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-quality-assessment.yaml
-
 ---
 
 # QE Quality Assessment
@@ -212,8 +211,35 @@ quality_check:
       - 1  # Warnings only
 ```
 
+## Run History
+
+After each quality assessment, append results to `run-history.json` in this skill directory:
+```bash
+node -e "
+const fs = require('fs');
+const h = JSON.parse(fs.readFileSync('.claude/skills/qe-quality-assessment/run-history.json'));
+h.runs.push({date: new Date().toISOString().split('T')[0], gate_result: 'PASS_OR_FAIL', failed_checks: []});
+fs.writeFileSync('.claude/skills/qe-quality-assessment/run-history.json', JSON.stringify(h, null, 2));
+"
+```
+Read `run-history.json` before each run — alert if quality gate failed 3 of last 5 runs.
+
+## Skill Composition
+
+- **Before assessment** → Run `/qe-coverage-analysis` and `/mutation-testing` first
+- **If issues found** → Use `/test-failure-investigator` to diagnose failures
+- **For PR review** → Combine with `/code-review-quality` for comprehensive review
+
+## Gotchas
+
+- NEVER trust agent-reported pass/fail status — 12 test failures were caught that agents claimed were passing (Nagual pattern, reward 0.92)
+- Completion theater: agent hardcoded version '3.0.0' instead of reading from package.json — verify actual values in output
+- Fix issues in priority waves (P0 → P1 → P2) with verification between each wave — don't fix everything in parallel
+- quality-assessment domain has 53.7% success rate — expect failures and have fallback
+- If HybridMemoryBackend initialization fails, run `npx ruflo doctor --fix` first
+
 ## Coordination
 
 **Primary Agents**: qe-quality-analyzer, qe-deployment-advisor, qe-metrics-collector
 **Coordinator**: qe-quality-coordinator
-**Related Skills**: qe-coverage-analysis, qe-security-compliance
+**Related Skills**: qe-coverage-analysis, security-testing

package/assets/skills/qe-quality-assessment/run-history.json

@@ -0,0 +1,6 @@
+{
+  "_description": "Quality assessment run history. Append after each run. Claude reads this to track quality gate pass/fail trends.",
+  "_format": "Each entry: {date, scope, gate_result, scores, failed_checks, recommendation}",
+  "_instructions": "After running quality assessment, append results here. Alert if quality gate fails 3 of last 5 runs. Track which checks fail most often.",
+  "runs": []
+}

package/assets/skills/qe-requirements-validation/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Requirements Validation"
-description: "Requirements traceability, acceptance criteria validation, and BDD scenario management for complete requirements coverage."
+description: "Use when validating acceptance criteria, tracing requirements to tests, managing BDD scenarios, or ensuring complete requirements coverage before development."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-requirements-validation.yaml
-
 ---
 
 # QE Requirements Validation

package/assets/skills/qe-test-execution/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Test Execution"
-description: "Parallel test execution orchestration with intelligent scheduling, retry logic, and comprehensive result aggregation."
+description: "Use when running test suites, optimizing test execution time, handling flaky tests, or setting up CI/CD test pipelines."
 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
@@ -181,6 +180,14 @@ interface ExecutionResults {
 }
 ```
 
+## 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

package/assets/skills/qe-test-generation/SKILL.md

@@ -1,12 +1,11 @@
 ---
 name: "QE Test Generation"
-description: "AI-powered test generation using pattern recognition, code analysis, and intelligent test synthesis for comprehensive test coverage."
+description: "Use when generating tests for new/changed code, improving test coverage, or migrating between Jest/Vitest/Playwright frameworks."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/qe-test-generation.yaml
-
 ---
 
 # QE Test Generation
@@ -140,6 +139,20 @@ quality_checks:
     statements: 85
 ```
 
+## Skill Composition
+
+- **After generating tests** → Run `/mutation-testing` to verify test quality
+- **Before generating** → Use `/test-automation-strategy` to choose framework and patterns
+- **Related** → `/qe-coverage-analysis` to find where tests are needed most
+
+## Gotchas
+
+- Agent truncates output on files >3000 lines — scope generation to individual modules, not entire directories
+- Components that pass unit tests individually may have zero integration wiring — always generate at least one integration test per module boundary
+- When generating tests for a new codebase, check which framework is installed (jest vs vitest vs mocha) — they have different mock APIs and Claude will use the wrong one
+- Completion theater: agent may claim "comprehensive tests generated" but leave stubs or hardcoded values — always run the generated tests before accepting
+- Fleet must be initialized before using QE agents: run `npx ruflo doctor --fix` if you get "Fleet not initialized"
+
 ## Coordination
 
 **Primary Agents**: qe-test-generator, qe-pattern-matcher, qe-test-architect

package/assets/skills/qe-test-generation/config.json

@@ -0,0 +1,14 @@
+{
+  "$schema": "./config-schema.json",
+  "_description": "QE Test Generation configuration. Auto-created on first run. Edit to customize.",
+  "framework": null,
+  "style": null,
+  "coverageTarget": 80,
+  "outputDir": "tests/",
+  "options": {
+    "generateIntegrationTests": true,
+    "generateEdgeCases": true,
+    "maxTestsPerFile": 20
+  },
+  "_setupPrompt": "If framework is null, ask the user: 'Which test framework does this project use? (jest/vitest/mocha/playwright)'. If style is null, ask: 'Do you prefer London (mock-based) or Chicago (state-based) TDD style?'"
+}

package/assets/skills/qe-test-generation/templates/test-scaffold-jest.md

@@ -0,0 +1,72 @@
+# Jest Unit Test Scaffold
+
+## Class Under Test Pattern
+```typescript
+import { {{ClassName}} } from '../src/{{path}}';
+
+describe('{{ClassName}}', () => {
+  let sut: {{ClassName}};
+
+  beforeEach(() => {
+    sut = new {{ClassName}}(/* dependencies */);
+  });
+
+  describe('{{methodName}}', () => {
+    it('should return expected result for valid input', () => {
+      // Arrange
+      const input = /* valid input */;
+
+      // Act
+      const result = sut.{{methodName}}(input);
+
+      // Assert
+      expect(result).toBe(/* expected */);
+    });
+
+    it('should throw for invalid input', () => {
+      expect(() => sut.{{methodName}}(null)).toThrow();
+    });
+
+    it('should handle edge case: empty input', () => {
+      const result = sut.{{methodName}}(/* empty */);
+      expect(result).toBe(/* expected for empty */);
+    });
+
+    it('should handle edge case: boundary value', () => {
+      const result = sut.{{methodName}}(/* boundary */);
+      expect(result).toBe(/* expected at boundary */);
+    });
+  });
+});
+```
+
+## Integration Test Pattern
+```typescript
+describe('{{Feature}} Integration', () => {
+  beforeAll(async () => {
+    await setupTestDatabase();
+  });
+
+  afterAll(async () => {
+    await teardownTestDatabase();
+  });
+
+  it('should complete the full workflow', async () => {
+    // Step 1: Create
+    const created = await service.create(validPayload);
+    expect(created.id).toBeDefined();
+
+    // Step 2: Read
+    const fetched = await service.getById(created.id);
+    expect(fetched).toMatchObject(validPayload);
+
+    // Step 3: Update
+    const updated = await service.update(created.id, changes);
+    expect(updated.field).toBe(changes.field);
+
+    // Step 4: Delete
+    await service.delete(created.id);
+    await expect(service.getById(created.id)).rejects.toThrow('Not found');
+  });
+});
+```