agentic-qe 3.4.1 → 3.4.2

package/.claude/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml

@@ -0,0 +1,154 @@
+skill: visual-testing-advanced
+version: 1.0.0
+description: >
+  Evaluation suite for visual-testing-advanced skill.
+  Tests advanced visual regression testing with sophisticated diff detection,
+  region analysis, and cross-viewport consistency verification.
+
+models_to_test:
+  - claude-3.5-sonnet
+  - claude-3-haiku
+
+mcp_integration:
+  enabled: true
+  namespace: skill-validation
+  query_patterns: true
+  track_outcomes: true
+  store_patterns: true
+  share_learning: true
+  target_agents:
+    - qe-learning-coordinator
+
+learning:
+  store_success_patterns: true
+  pattern_ttl_days: 90
+  min_confidence_to_store: 0.7
+
+result_format:
+  json_output: true
+  include_timing: true
+
+setup:
+  required_tools:
+    - jq
+  environment_variables:
+    VISUAL_DIFF_THRESHOLD: "0.05"
+    MIN_REGION_SIZE: "10"
+
+test_cases:
+  - id: tc001_visual_diff_detection
+    description: "Visual differences are correctly detected"
+    category: core
+    priority: critical
+
+    input:
+      baselineImage: "baseline.png"
+      actualImage: "actual.png"
+      context:
+        diffThreshold: 0.05
+
+    expected_output:
+      must_contain:
+        - "diff"
+        - "detected"
+      must_not_contain:
+        - "error"
+
+    validation:
+      schema_check: true
+      keyword_match_threshold: 0.8
+
+  - id: tc002_region_analysis
+    description: "Changed regions are identified and analyzed"
+    category: core
+    priority: critical
+
+    input:
+      compareImages: true
+      analyzeRegions: true
+      context:
+        regionMinSize: 10
+
+    expected_output:
+      must_contain:
+        - "region"
+        - "change"
+
+    validation:
+      schema_check: true
+
+  - id: tc003_cross_viewport_consistency
+    description: "Visual consistency is verified across viewports"
+    category: core
+    priority: high
+
+    input:
+      viewports:
+        - "1920x1080"
+        - "1024x768"
+        - "375x667"
+      context:
+        compareAcrossViewports: true
+
+    expected_output:
+      must_contain:
+        - "viewport"
+        - "consistent"
+
+    validation:
+      schema_check: true
+      allow_partial: true
+
+  - id: tc004_diff_percentage_calculation
+    description: "Diff percentage is accurately calculated"
+    category: core
+    priority: high
+
+    input:
+      totalPixels: 1000000
+      changedPixels: 5000
+      context:
+        calculateDiffPercentage: true
+
+    expected_output:
+      must_contain:
+        - "0.5"
+
+    validation:
+      schema_check: true
+      allow_partial: true
+
+  - id: tc005_responsive_design_validation
+    description: "Responsive design changes are properly validated"
+    category: core
+    priority: high
+
+    input:
+      pages:
+        - "homepage"
+        - "product-page"
+      viewports: ["desktop", "tablet", "mobile"]
+      context:
+        validateResponsive: true
+
+    expected_output:
+      must_contain:
+        - "responsive"
+        - "layout"
+
+    validation:
+      schema_check: true
+      allow_partial: true
+
+success_criteria:
+  pass_rate: 0.8
+  critical_pass_rate: 1.0
+  avg_reasoning_quality: 0.7
+  max_execution_time_ms: 300000
+  cross_model_variance: 0.15
+
+metadata:
+  author: "qe-visual-specialist"
+  created: "2026-02-02"
+  last_updated: "2026-02-02"
+  coverage_target: "Diff detection, region analysis, viewport consistency, responsive design, pixel-level accuracy"

package/.claude/skills/visual-testing-advanced/schemas/output.json

@@ -0,0 +1,294 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "https://agentic-qe.dev/schemas/visual-testing-advanced-output.json",
+  "title": "AQE Visual Testing Advanced Skill Output Schema",
+  "description": "Schema for advanced visual regression testing output including pixel comparison, AI-powered diff analysis, and cross-browser visual consistency.",
+  "type": "object",
+  "required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
+  "properties": {
+    "skillName": {
+      "type": "string",
+      "const": "visual-testing-advanced",
+      "description": "Skill identifier"
+    },
+    "version": {
+      "type": "string",
+      "pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9]+)?$"
+    },
+    "timestamp": {
+      "type": "string",
+      "pattern": "^\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}(\\.\\d+)?(Z|[+-]\\d{2}:\\d{2})?$"
+    },
+    "status": {
+      "type": "string",
+      "enum": ["success", "partial", "failed", "skipped"]
+    },
+    "trustTier": {
+      "type": "integer",
+      "const": 3
+    },
+    "output": {
+      "type": "object",
+      "required": ["summary", "comparisons", "regressionStatus", "metrics"],
+      "properties": {
+        "summary": {
+          "type": "string",
+          "minLength": 10,
+          "maxLength": 2000
+        },
+        "score": {
+          "$ref": "#/$defs/visualScore"
+        },
+        "comparisons": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/visualComparison"
+          },
+          "minItems": 1,
+          "description": "Visual comparison results"
+        },
+        "regressionStatus": {
+          "$ref": "#/$defs/regressionStatus",
+          "description": "Overall visual regression status"
+        },
+        "baselineInfo": {
+          "$ref": "#/$defs/baselineInfo",
+          "description": "Baseline screenshot information"
+        },
+        "responsiveResults": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/responsiveResult"
+          },
+          "description": "Results by viewport size"
+        },
+        "componentResults": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/componentResult"
+          },
+          "description": "Component-level visual results"
+        },
+        "findings": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/visualFinding"
+          },
+          "maxItems": 500
+        },
+        "recommendations": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/recommendation"
+          },
+          "maxItems": 100
+        },
+        "metrics": {
+          "$ref": "#/$defs/visualMetrics"
+        },
+        "artifacts": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/artifact"
+          },
+          "maxItems": 200
+        }
+      }
+    },
+    "metadata": {
+      "type": "object",
+      "properties": {
+        "executionTimeMs": { "type": "integer", "minimum": 0 },
+        "toolsUsed": {
+          "type": "array",
+          "items": {
+            "type": "string",
+            "enum": ["playwright", "percy", "applitools", "backstopjs", "chromatic", "reg-suit"]
+          }
+        },
+        "agentId": { "type": "string", "pattern": "^qe-[a-z][a-z0-9-]*$" },
+        "targetUrl": { "type": "string" },
+        "baselineBranch": { "type": "string" },
+        "comparisonBranch": { "type": "string" }
+      }
+    },
+    "validation": {
+      "type": "object",
+      "properties": {
+        "schemaValid": { "type": "boolean" },
+        "contentValid": { "type": "boolean" },
+        "confidence": { "type": "number", "minimum": 0, "maximum": 1 }
+      }
+    },
+    "learning": {
+      "type": "object",
+      "properties": {
+        "patternsDetected": { "type": "array", "items": { "type": "string" } },
+        "reward": { "type": "number", "minimum": 0, "maximum": 1 }
+      }
+    }
+  },
+  "$defs": {
+    "visualScore": {
+      "type": "object",
+      "required": ["value", "max"],
+      "properties": {
+        "value": { "type": "number", "minimum": 0, "maximum": 100 },
+        "max": { "type": "number", "const": 100 },
+        "grade": { "type": "string", "pattern": "^[A-F][+-]?$" },
+        "visualConsistency": {
+          "type": "number",
+          "minimum": 0,
+          "maximum": 100,
+          "description": "Visual consistency score"
+        }
+      }
+    },
+    "visualComparison": {
+      "type": "object",
+      "required": ["page", "status"],
+      "properties": {
+        "page": { "type": "string", "description": "Page or component name" },
+        "url": { "type": "string" },
+        "status": {
+          "type": "string",
+          "enum": ["passed", "failed", "new", "updated", "skipped"]
+        },
+        "diffPercent": {
+          "type": "number",
+          "minimum": 0,
+          "maximum": 100,
+          "description": "Difference percentage"
+        },
+        "diffPixels": { "type": "integer", "minimum": 0 },
+        "threshold": { "type": "number", "minimum": 0, "maximum": 100 },
+        "viewport": {
+          "type": "object",
+          "properties": {
+            "width": { "type": "integer" },
+            "height": { "type": "integer" }
+          }
+        },
+        "browser": { "type": "string" },
+        "baselineScreenshot": { "type": "string" },
+        "actualScreenshot": { "type": "string" },
+        "diffScreenshot": { "type": "string" },
+        "comparisonAlgorithm": {
+          "type": "string",
+          "enum": ["pixel-diff", "structural-similarity", "ai-semantic", "perceptual-hash"]
+        },
+        "maskedRegions": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/maskedRegion"
+          }
+        }
+      }
+    },
+    "maskedRegion": {
+      "type": "object",
+      "properties": {
+        "selector": { "type": "string" },
+        "reason": { "type": "string", "enum": ["dynamic-content", "timestamp", "ad", "user-data", "animation"] }
+      }
+    },
+    "regressionStatus": {
+      "type": "object",
+      "properties": {
+        "hasRegressions": { "type": "boolean" },
+        "regressionCount": { "type": "integer", "minimum": 0 },
+        "newScreenshots": { "type": "integer", "minimum": 0 },
+        "updatedBaselines": { "type": "integer", "minimum": 0 },
+        "requiresReview": { "type": "boolean" }
+      }
+    },
+    "baselineInfo": {
+      "type": "object",
+      "properties": {
+        "branch": { "type": "string" },
+        "commit": { "type": "string" },
+        "createdAt": { "type": "string" },
+        "screenshotCount": { "type": "integer", "minimum": 0 }
+      }
+    },
+    "responsiveResult": {
+      "type": "object",
+      "required": ["viewport", "status"],
+      "properties": {
+        "viewport": {
+          "type": "string",
+          "enum": ["mobile", "tablet", "desktop", "large-desktop"]
+        },
+        "width": { "type": "integer" },
+        "status": { "type": "string", "enum": ["passed", "failed", "partial"] },
+        "comparisonCount": { "type": "integer" },
+        "regressionCount": { "type": "integer" }
+      }
+    },
+    "componentResult": {
+      "type": "object",
+      "required": ["component", "status"],
+      "properties": {
+        "component": { "type": "string" },
+        "selector": { "type": "string" },
+        "status": { "type": "string", "enum": ["passed", "failed", "new"] },
+        "diffPercent": { "type": "number" },
+        "screenshotPath": { "type": "string" }
+      }
+    },
+    "visualFinding": {
+      "type": "object",
+      "required": ["id", "title", "severity", "category"],
+      "properties": {
+        "id": { "type": "string", "pattern": "^VIS-\\d{3,6}$" },
+        "title": { "type": "string", "minLength": 5, "maxLength": 200 },
+        "description": { "type": "string", "maxLength": 2000 },
+        "severity": { "type": "string", "enum": ["critical", "high", "medium", "low", "info"] },
+        "category": {
+          "type": "string",
+          "enum": ["layout-shift", "color-change", "font-rendering", "alignment", "missing-element", "overflow", "responsive", "animation"]
+        },
+        "page": { "type": "string" },
+        "viewport": { "type": "string" },
+        "browser": { "type": "string" },
+        "diffPercent": { "type": "number" },
+        "screenshotEvidence": { "type": "string" },
+        "remediation": { "type": "string" }
+      }
+    },
+    "visualMetrics": {
+      "type": "object",
+      "properties": {
+        "totalComparisons": { "type": "integer", "minimum": 0 },
+        "passed": { "type": "integer", "minimum": 0 },
+        "failed": { "type": "integer", "minimum": 0 },
+        "new": { "type": "integer", "minimum": 0 },
+        "passRate": { "type": "number", "minimum": 0, "maximum": 100 },
+        "avgDiffPercent": { "type": "number", "minimum": 0, "maximum": 100 },
+        "viewportsCovered": { "type": "integer", "minimum": 0 },
+        "browsersCovered": { "type": "integer", "minimum": 0 },
+        "componentsCovered": { "type": "integer", "minimum": 0 },
+        "executionTimeMs": { "type": "integer", "minimum": 0 }
+      }
+    },
+    "recommendation": {
+      "type": "object",
+      "required": ["id", "title", "priority"],
+      "properties": {
+        "id": { "type": "string", "pattern": "^REC-\\d{3,6}$" },
+        "title": { "type": "string" },
+        "description": { "type": "string" },
+        "priority": { "type": "string", "enum": ["critical", "high", "medium", "low"] }
+      }
+    },
+    "artifact": {
+      "type": "object",
+      "required": ["type", "path"],
+      "properties": {
+        "type": { "type": "string", "enum": ["baseline", "actual", "diff", "report", "video"] },
+        "path": { "type": "string" },
+        "format": { "type": "string", "enum": ["png", "jpg", "webp", "html", "json", "webm"] }
+      }
+    }
+  }
+}

package/.claude/skills/visual-testing-advanced/scripts/validate.sh

@@ -0,0 +1,77 @@
+#!/bin/bash
+# =============================================================================
+# AQE Skill Validator: visual-testing-advanced v1.0.0
+# Validates advanced visual testing output
+# =============================================================================
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+SKILL_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+PROJECT_ROOT="$(cd "$SKILL_DIR/../../.." && pwd)"
+
+VALIDATOR_LIB=""
+for lib_path in "$PROJECT_ROOT/.claude/skills/.validation/templates/validator-lib.sh" "$SKILL_DIR/scripts/validator-lib.sh"; do
+  [[ -f "$lib_path" ]] && VALIDATOR_LIB="$lib_path" && break
+done
+
+[[ -n "$VALIDATOR_LIB" ]] && source "$VALIDATOR_LIB" || exit 1
+
+SKILL_NAME="visual-testing-advanced"
+SKILL_VERSION="1.0.0"
+REQUIRED_TOOLS=("jq")
+OPTIONAL_TOOLS=("imagemagick" "playwright" "ajv" "jsonschema" "python3")
+SCHEMA_PATH="$SKILL_DIR/schemas/output.json"
+
+REQUIRED_FIELDS=("skillName" "status" "output")
+MUST_CONTAIN_TERMS=("visual" "test" "diff")
+MUST_NOT_CONTAIN_TERMS=("TODO" "placeholder")
+ENUM_VALIDATIONS=(".status:success,partial,failed,skipped")
+
+OUTPUT_FILE=""
+SELF_TEST=false
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --self-test) SELF_TEST=true; shift ;;
+    --verbose|-v) export AQE_DEBUG=1; shift ;;
+    --json|--list-tools|--help|-h) shift ;;
+    -*) error "Unknown option: $1"; exit 1 ;;
+    *) OUTPUT_FILE="$1"; shift ;;
+  esac
+done
+
+if [[ "$SELF_TEST" == "true" ]]; then
+  self_test_passed=true
+  for tool in "${REQUIRED_TOOLS[@]}"; do
+    command_exists "$tool" && success "Required: $tool" || { error "Missing: $tool"; self_test_passed=false; }
+  done
+  [[ -f "$SCHEMA_PATH" ]] && validate_json "$SCHEMA_PATH" 2>/dev/null && success "Schema valid" || self_test_passed=false
+  [[ "$self_test_passed" == "true" ]] && exit 0 || exit 1
+fi
+
+validate_skill_specific() {
+  local output_file="$1"
+  local has_comparisons=$(json_get "$output_file" ".output.comparisons" 2>/dev/null)
+  [[ -z "$has_comparisons" ]] || [[ "$has_comparisons" == "null" ]] && warn "No comparisons found"
+  return 0
+}
+
+main() {
+  [[ -z "$OUTPUT_FILE" ]] && error "No output file specified" && exit 1
+  [[ ! -f "$OUTPUT_FILE" ]] && error "Output file not found" && exit 1
+
+  echo "Validating $SKILL_NAME"
+
+  ! validate_tools && exit $EXIT_SKIP
+  ! validate_json "$OUTPUT_FILE" && exit $EXIT_FAIL
+  ! validate_schema "$OUTPUT_FILE" 2>/dev/null && exit $EXIT_FAIL
+  ! validate_required_fields "$OUTPUT_FILE" && exit $EXIT_FAIL
+  ! validate_content_terms "$OUTPUT_FILE" && exit $EXIT_FAIL
+  ! validate_skill_specific "$OUTPUT_FILE" && exit $EXIT_FAIL
+
+  success "Validation PASSED"
+  exit $EXIT_PASS
+}
+
+main

package/.claude/skills/xp-practices/SKILL.md

@@ -11,6 +11,9 @@ last_optimized: 2025-12-03
 dependencies: []
 quick_reference_card: true
 tags: [xp, agile, pair-programming, tdd, continuous-integration, collaboration]
+trust_tier: 0
+validation:
+
 ---
 
 # Extreme Programming (XP) Practices

package/README.md

@@ -13,13 +13,19 @@
 
 > **V3** brings Domain-Driven Design architecture, 12 bounded contexts, 51 specialized QE agents, TinyDancer intelligent model routing, ReasoningBank learning with Dream cycles, HNSW vector search, mathematical Coherence verification, full MinCut/Consensus integration across all 12 domains, and deep integration with [Claude Flow](https://github.com/ruvnet/claude-flow) and [Agentic Flow](https://github.com/ruvnet/agentic-flow).
 
+### What's New in v3.4.2
+
+- **Skill Validation System** - 4-layer trust tiers with schemas, validators, and evaluation suites (ADR-056)
+- **63 QE Skills with Trust Tiers** - 46 Tier 3 (Verified), 7 Tier 2, 5 Tier 1, 5 Tier 0 skills
+- **CLI Validation Commands** - `aqe skill report`, `aqe eval run`, regression detection
+
 ### What's New in v3.4.0
 
 - **AG-UI Protocol** - Anthropic's streaming agent-to-user interface with real-time progress updates
 - **A2A Protocol** - Google's agent-to-agent interoperability standard for cross-tool communication
 - **A2UI Components** - Unified UI combining AG-UI streaming with A2A event handling
 
-🏗️ **DDD Architecture** | 🧠 **ReasoningBank + Dream Cycles** | 🎯 **TinyDancer Model Routing** | 🔍 **HNSW Vector Search** | 👑 **Queen Coordinator** | 📊 **O(log n) Coverage** | 🔗 **Claude Flow Integration** | 🎯 **12 Bounded Contexts** | 📚 **63 QE Skills** | 🧬 **Coherence Verification** 
+🏗️ **DDD Architecture** | 🧠 **ReasoningBank + Dream Cycles** | 🎯 **TinyDancer Model Routing** | 🔍 **HNSW Vector Search** | 👑 **Queen Coordinator** | 📊 **O(log n) Coverage** | 🔗 **Claude Flow Integration** | 🎯 **12 Bounded Contexts** | 📚 **63 QE Skills** | 🧬 **Coherence Verification** | ✅ **Trust Tiers** 
 
 </div>
 
@@ -76,7 +82,7 @@ claude "Use qe-flaky-hunter to analyze the last 100 test runs and stabilize flak
 - ✅ **Memory Coordination**: Cross-agent communication via `aqe/v3/*` namespaces
 - ✅ **Coherence Verification** (v3.3.0): Mathematical proof of belief consistency using WASM engines
 - ✅ **V2 Backward Compatibility**: All V2 agents map to V3 equivalents
-- ✅ **63 QE Skills**: Domain-specific skills for testing, security, accessibility, QCSD, and more
+- ✅ **63 QE Skills with Trust Tiers**: 46 Tier 3 (Verified) skills with full validation suites
 
 ---
 
@@ -142,6 +148,37 @@ V3 is built on **12 DDD Bounded Contexts**, each with dedicated agents and clear
 
 ---
 
+### ✅ Skill Trust Tiers (v3.4.2)
+
+All 63 QE skills are categorized by **trust tier** based on their validation infrastructure:
+
+| Tier | Badge | Count | Description |
+|------|-------|-------|-------------|
+| **Tier 3 - Verified** | ![Tier 3](https://img.shields.io/badge/Tier%203-Verified-brightgreen) | 46 | Full evaluation test suite |
+| **Tier 2 - Validated** | ![Tier 2](https://img.shields.io/badge/Tier%202-Validated-green) | 7 | Has executable validator |
+| **Tier 1 - Structured** | ![Tier 1](https://img.shields.io/badge/Tier%201-Structured-yellow) | 5 | Has JSON output schema |
+| **Tier 0 - Advisory** | ![Tier 0](https://img.shields.io/badge/Tier%200-Advisory-lightgrey) | 5 | SKILL.md guidance only |
+
+**Tier 3 Skills** are recommended for production use - they have:
+- JSON Schema validation for output structure
+- Executable validator scripts for correctness
+- Evaluation test suites with multi-model testing
+
+```bash
+# Check skill trust tier
+aqe eval status --skill security-testing
+
+# Run skill evaluation
+aqe eval run --skill security-testing --model claude-sonnet-4
+
+# View all trust tiers
+cat .claude/skills/TRUST-TIERS.md
+```
+
+[Full documentation: docs/guides/skill-validation.md]
+
+---
+
 ### 🌐 Browser Automation Integration (v3.1.0)
 
 V3.1.0 adds full browser automation support via **@claude-flow/browser** integration:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-qe",
-  "version": "3.4.1",
+  "version": "3.4.2",
   "description": "Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 12 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 51 specialized QE agents, mathematical Coherence verification, deep Claude Flow integration",
   "main": "./v3/dist/index.js",
   "types": "./v3/dist/index.d.ts",
@@ -46,6 +46,9 @@
     "sync:cloud:status": "cd v3 && npm run sync:cloud:status",
     "sync:cloud:verify": "cd v3 && npm run sync:cloud:verify",
     "sync:cloud:config": "cd v3 && npm run sync:cloud:config",
+    "skills:update-manifest": "npx tsx scripts/update-skill-manifest.ts",
+    "skills:update-badges": "npx tsx scripts/update-skill-manifest.ts --generate-badges",
+    "skills:validate-tier3": "for skill in api-testing-patterns security-testing performance-testing; do .claude/skills/$skill/scripts/validate.sh --self-test; done",
     "prepublishOnly": "cd v3 && npm run build"
   },
   "keywords": [