agentic-qe 3.8.2 → 3.8.3

package/.claude/skills/mobile-testing/SKILL.md

@@ -65,51 +65,6 @@ When testing mobile applications:
 | **Tier 2** | 30% users | iPhone 14/13, Pixel 8 |
 | **Tier 3** | 10% users | Older devices, other manufacturers |
 
-### Mobile Performance Goals
-| Metric | Target |
-|--------|--------|
-| App launch | < 2 seconds |
-| Screen transition | < 300ms |
-| Frame rate | 60 FPS |
-| Battery drain | < 5%/hour background |
-
----
-
-## Touch Gesture Testing
-
-```javascript
-// Appium gesture examples
-// Tap
-await driver.touchAction({ action: 'tap', x: 100, y: 200 });
-
-// Swipe (scroll down)
-await driver.touchAction([
-  { action: 'press', x: 200, y: 400 },
-  { action: 'moveTo', x: 200, y: 100 },
-  { action: 'release' }
-]);
-
-// Pinch to zoom
-const finger1 = [
-  { action: 'press', x: 100, y: 200 },
-  { action: 'moveTo', x: 50, y: 150 },
-  { action: 'release' }
-];
-const finger2 = [
-  { action: 'press', x: 200, y: 200 },
-  { action: 'moveTo', x: 250, y: 250 },
-  { action: 'release' }
-];
-await driver.multiTouchAction([finger1, finger2]);
-
-// Long press
-await driver.touchAction({
-  action: 'longPress',
-  x: 100, y: 200,
-  duration: 2000
-});
-```
-
 ---
 
 ## Mobile-Specific Scenarios
@@ -217,8 +172,6 @@ const mobileFleet = await FleetManager.coordinate({
 
 ## Remember
 
-**Mobile is not a smaller desktop - it's a different platform.** 60%+ of web traffic is mobile. Device fragmentation (1000+ Android devices), touch gestures, sensors, permissions, offline scenarios - all require specific testing.
-
-**Test on real devices for critical flows.** Emulators catch 80% of bugs but real devices needed for actual performance, sensor behavior, and platform quirks.
+**Test on real devices for critical flows.** Emulators catch 80% of bugs but real devices are needed for actual performance, sensor behavior, and platform quirks.
 
-**With Agents:** `qe-test-executor` orchestrates testing across device farms, manages platform differences, and tests 10+ devices in parallel. Reduces mobile testing from days to hours.
+**With Agents:** `qe-test-executor` orchestrates testing across device farms, manages platform differences, and tests 10+ devices in parallel.

package/.claude/skills/mutation-testing/SKILL.md

@@ -233,3 +233,29 @@ const mutationFleet = await FleetManager.coordinate({
 **Focus on critical paths first.** Don't mutation test everything - prioritize payment, authentication, data integrity code.
 
 **With Agents:** Agents run mutation analysis, identify surviving mutants, and generate missing test cases to kill them. Automated improvement of test quality.
+
+## Run History
+
+After each mutation 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/mutation-testing/run-history.json'));
+h.runs.push({date: new Date().toISOString().split('T')[0], mutation_score_pct: SCORE, killed: KILLED, survived: SURVIVED});
+fs.writeFileSync('.claude/skills/mutation-testing/run-history.json', JSON.stringify(h, null, 2));
+"
+```
+Read `run-history.json` before each run to track score improvements over time.
+
+## Skill Composition
+
+- **Before mutation testing** → Run `/qe-test-generation` to ensure tests exist
+- **After mutation results** → Use `/qe-coverage-analysis` to prioritize improvement areas
+- **Quality gate** → Feed results into `/qe-quality-assessment` for ship/no-ship decision
+
+## Gotchas
+
+- Stryker requires `--testRunner jest` explicitly if both jest and vitest are installed
+- Mutating `>=` to `>` in date comparisons rarely gets killed — add boundary tests
+- Running on files >500 LOC will timeout; use `--mutate` to target specific functions
+- `--concurrency` defaults to CPU count which OOMs in containers — set to 2

package/.claude/skills/mutation-testing/config.json

@@ -0,0 +1,14 @@
+{
+  "$schema": "./config-schema.json",
+  "_description": "Mutation Testing configuration. Auto-created on first run. Edit to customize.",
+  "mutator": "stryker",
+  "concurrency": 2,
+  "score_threshold": 80,
+  "options": {
+    "testRunner": null,
+    "mutateGlob": "src/**/*.{ts,js}",
+    "excludeGlob": "src/**/*.test.{ts,js}",
+    "timeoutMs": 60000
+  },
+  "_setupPrompt": "If testRunner is null, ask: 'Which test runner does this project use? (jest/vitest/mocha)'. Warn: concurrency defaults to 2 to avoid OOM in containers."
+}

package/.claude/skills/mutation-testing/references/mutation-operators.md

@@ -0,0 +1,38 @@
+# Mutation Operators Reference
+
+## Arithmetic Operators
+| Original | Mutant | What It Tests |
+|----------|--------|--------------|
+| `a + b` | `a - b` | Addition logic |
+| `a * b` | `a / b` | Multiplication logic |
+| `a % b` | `a * b` | Modulo logic |
+
+## Conditional Operators
+| Original | Mutant | What It Tests |
+|----------|--------|--------------|
+| `a > b` | `a >= b` | Off-by-one in boundaries |
+| `a >= b` | `a > b` | Boundary inclusion |
+| `a === b` | `a !== b` | Equality checks |
+| `a && b` | `a \|\| b` | Logical conjunction |
+
+## Statement Mutations
+| Original | Mutant | What It Tests |
+|----------|--------|--------------|
+| `return x` | `return !x` | Return value negation |
+| `if (cond)` | `if (true)` | Condition relevance |
+| `if (cond)` | `if (false)` | Dead code detection |
+| `statement` | _(removed)_ | Statement necessity |
+
+## Common Surviving Mutants and Fixes
+
+**`>=` to `>` survives**: Add boundary test with exact boundary value
+**`&&` to `||` survives**: Add test where only one condition is true
+**Removed `return` survives**: Function's return value isn't being checked
+**`+1` to `-1` survives**: Increment/decrement logic untested
+
+## Stryker Configuration Tips
+- `--testRunner jest` — explicit when multiple runners installed
+- `--concurrency 2` — prevents OOM in containers
+- `--mutate 'src/**/*.ts,!src/**/*.d.ts'` — skip type definitions
+- `--timeoutMS 60000` — increase for slow test suites
+- `--thresholds.high 80 --thresholds.low 60` — score quality bands

package/.claude/skills/mutation-testing/run-history.json

@@ -0,0 +1,6 @@
+{
+  "_description": "Mutation testing run history. Append after each run. Claude reads this to track mutation score trends.",
+  "_format": "Each entry: {date, scope, mutation_score_pct, killed, survived, timeout, no_coverage, improvement_areas}",
+  "_instructions": "After running mutation testing, append results here. Track score improvements over time. Flag if score drops below threshold.",
+  "runs": []
+}

package/.claude/skills/no-skip/SKILL.md

@@ -0,0 +1,74 @@
+---
+name: no-skip
+description: "Use when you want to prevent .skip(), .only(), xit(), and xdescribe() from being committed to test files. Activate with /no-skip for session-scoped test skip prevention."
+user-invocable: true
+---
+
+# No-Skip Mode
+
+When activated, blocks any write that adds test-skipping patterns to test files.
+
+## What It Does
+
+Prevents these patterns from being written to test files:
+- `.skip()` — skips individual tests
+- `.only()` — runs only one test (excludes all others)
+- `xit(` / `xdescribe(` — Jasmine skip syntax
+- `test.todo(` — unimplemented test placeholders
+- `@Skip` / `@Disabled` — JUnit skip annotations
+
+## Activation
+
+```
+/no-skip
+```
+
+## Hook Configuration
+
+```json
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hook": ".claude/skills/no-skip/scripts/check-skips.sh",
+        "condition": "file matches **/*.test.{ts,js,tsx,jsx} OR **/*.spec.{ts,js}"
+      }
+    ]
+  }
+}
+```
+
+## Enforcement Logic
+
+```bash
+#!/bin/bash
+# check-skips.sh
+CONTENT="$1"
+
+SKIP_PATTERNS=(
+  '\.skip\s*\('
+  '\.only\s*\('
+  '\bxit\s*\('
+  '\bxdescribe\s*\('
+  '\bxcontext\s*\('
+  'test\.todo\s*\('
+  '@Skip'
+  '@Disabled'
+  '@Ignore'
+)
+
+for pattern in "${SKIP_PATTERNS[@]}"; do
+  if echo "$CONTENT" | grep -qP "$pattern"; then
+    echo "BLOCKED: Found skip pattern '$pattern'"
+    echo "Remove the skip and either fix the test or delete it."
+    exit 1
+  fi
+done
+```
+
+## Gotchas
+
+- This catches NEW skips being written, not existing ones — run `grep -r '.skip(' tests/` to find existing skips
+- `.only()` is sometimes used intentionally during debugging — deactivate with `/no-skip off` if needed
+- Some frameworks use `pending()` instead of `.skip()` — add to patterns if using Jasmine

package/.claude/skills/no-skip/scripts/check-skips.sh

@@ -0,0 +1,28 @@
+#!/bin/bash
+# check-skips.sh — No-Skip hook
+# Blocks writes that add test-skipping patterns to test files.
+# Called by PreToolUse hook on Write/Edit to **/*.test.* or **/*.spec.*
+
+CONTENT="$1"
+
+if [ -z "$CONTENT" ]; then
+  # If no content passed, read from stdin
+  CONTENT=$(cat)
+fi
+
+FOUND=0
+
+# Check for skip patterns
+for pattern in '\.skip\s*(' '\.only\s*(' '\bxit\s*(' '\bxdescribe\s*(' '\bxcontext\s*(' 'test\.todo\s*(' '@Skip' '@Disabled' '@Ignore'; do
+  if echo "$CONTENT" | grep -qP "$pattern" 2>/dev/null || echo "$CONTENT" | grep -q "$pattern" 2>/dev/null; then
+    echo "BLOCKED: Found skip pattern: $pattern"
+    FOUND=1
+  fi
+done
+
+if [ $FOUND -eq 1 ]; then
+  echo "Remove the skip and either fix the test or delete it."
+  exit 1
+fi
+
+exit 0

package/.claude/skills/pair-programming/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: Pair Programming
-description: AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with truth-score verification.
+description: "Use when pair programming with AI assistance, practicing TDD with a navigator, debugging collaboratively, refactoring with real-time verification, or running learning sessions with continuous code review and quality monitoring."
 ---
 
 # Pair Programming

package/.claude/skills/pentest-validation/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: pentest-validation
-description: "Orchestrate security finding validation through graduated exploitation. 4-phase pipeline: recon (SAST/DAST), analysis (code review), validation (exploit proof), report (No Exploit, No Report gate). Eliminates false positives by proving exploitability."
+description: "Use when validating security findings from SAST/DAST scans, proving exploitability of reported vulnerabilities, eliminating false positives, or running the 4-phase pentest pipeline (recon, analysis, validation, report)."
 category: specialized-testing
 priority: critical
 tokenEstimate: 1500
@@ -253,8 +253,7 @@ aqe/pentest/
 
 ## Related Skills
 
-- [security-testing](../security-testing/) - OWASP vulnerability scanning
-- [qe-security-compliance](../qe-security-compliance/) - SAST/DAST automation
+- [security-testing](../security-testing/) - OWASP vulnerability scanning, SAST/DAST automation
 - [compliance-testing](../compliance-testing/) - Regulatory compliance
 - [api-testing-patterns](../api-testing-patterns/) - API security testing
 - [chaos-engineering-resilience](../chaos-engineering-resilience/) - Security under chaos

package/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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

package/.claude/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

package/.claude/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

package/.claude/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

package/.claude/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

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

@@ -1,6 +1,6 @@
 ---
 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
@@ -240,4 +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/.claude/skills/qe-code-intelligence/SKILL.md

@@ -1,6 +1,6 @@
 ---
 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
@@ -207,6 +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/.claude/skills/qe-coverage-analysis/SKILL.md

@@ -1,6 +1,6 @@
 ---
 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
@@ -185,6 +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/.claude/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/.claude/skills/qe-defect-intelligence/SKILL.md

@@ -1,6 +1,6 @@
 ---
 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

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

@@ -1,6 +1,6 @@
 ---
 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

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

@@ -1,6 +1,6 @@
 ---
 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
@@ -211,8 +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/.claude/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": []
+}