agentic-qe 3.7.8 → 3.7.9

package/assets/skills/brutal-honesty-review/schemas/output.json

@@ -0,0 +1,291 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://agentic-qe.dev/schemas/skills/brutal-honesty-review/output.json",
+  "title": "Brutal Honesty Review Skill Output Schema",
+  "description": "Schema for brutal-honesty-review skill output. Validates unvarnished technical criticism with actionable recommendations.",
+  "type": "object",
+  "required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
+  "properties": {
+    "skillName": {
+      "type": "string",
+      "const": "brutal-honesty-review"
+    },
+    "version": {
+      "type": "string",
+      "pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9]+)?$"
+    },
+    "timestamp": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "status": {
+      "type": "string",
+      "enum": ["success", "partial", "failed", "skipped"]
+    },
+    "trustTier": {
+      "type": "integer",
+      "const": 3
+    },
+    "output": {
+      "type": "object",
+      "required": ["summary", "reviewFindings", "codeQuality"],
+      "properties": {
+        "summary": {
+          "type": "string",
+          "minLength": 50,
+          "maxLength": 3000,
+          "description": "Brutally honest executive summary"
+        },
+        "reviewFindings": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/reviewFinding"
+          },
+          "minItems": 1,
+          "maxItems": 200,
+          "description": "Detailed findings with no sugar-coating"
+        },
+        "codeQuality": {
+          "$ref": "#/$defs/codeQuality"
+        },
+        "severity": {
+          "$ref": "#/$defs/severityBreakdown"
+        },
+        "recommendations": {
+          "type": "array",
+          "items": {
+            "$ref": "#/$defs/recommendation"
+          },
+          "maxItems": 100,
+          "description": "Actionable improvement recommendations"
+        },
+        "technicalDebt": {
+          "$ref": "#/$defs/technicalDebt"
+        },
+        "readabilityScore": {
+          "type": "number",
+          "minimum": 0,
+          "maximum": 100
+        },
+        "maintainabilityScore": {
+          "type": "number",
+          "minimum": 0,
+          "maximum": 100
+        },
+        "verdict": {
+          "type": "string",
+          "enum": ["ship-it", "needs-work", "major-issues", "do-not-merge", "rewrite-needed"],
+          "description": "Final honest verdict"
+        },
+        "metrics": {
+          "$ref": "#/$defs/metrics"
+        }
+      }
+    },
+    "metadata": {
+      "$ref": "#/$defs/metadata"
+    },
+    "validation": {
+      "$ref": "#/$defs/validationResult"
+    },
+    "learning": {
+      "$ref": "#/$defs/learningData"
+    }
+  },
+  "$defs": {
+    "reviewFinding": {
+      "type": "object",
+      "required": ["id", "title", "severity", "category", "honestAssessment"],
+      "properties": {
+        "id": {
+          "type": "string",
+          "pattern": "^REV-\\d{3,6}$"
+        },
+        "title": {
+          "type": "string",
+          "minLength": 10,
+          "maxLength": 200
+        },
+        "description": {
+          "type": "string",
+          "maxLength": 2000
+        },
+        "severity": {
+          "type": "string",
+          "enum": ["critical", "high", "medium", "low", "nitpick"]
+        },
+        "category": {
+          "type": "string",
+          "enum": ["architecture", "design", "implementation", "performance", "security", "maintainability", "readability", "testing", "documentation", "naming"]
+        },
+        "honestAssessment": {
+          "type": "string",
+          "minLength": 20,
+          "maxLength": 2000,
+          "description": "Brutally honest assessment with no softening"
+        },
+        "location": {
+          "type": "object",
+          "properties": {
+            "file": { "type": "string" },
+            "line": { "type": "integer", "minimum": 1 },
+            "endLine": { "type": "integer", "minimum": 1 },
+            "function": { "type": "string" }
+          }
+        },
+        "codeSnippet": {
+          "type": "string",
+          "maxLength": 5000
+        },
+        "suggestedFix": {
+          "type": "string",
+          "maxLength": 5000
+        },
+        "effort": {
+          "type": "string",
+          "enum": ["trivial", "low", "medium", "high", "major"]
+        },
+        "blocking": {
+          "type": "boolean",
+          "description": "Whether this blocks merging"
+        }
+      }
+    },
+    "codeQuality": {
+      "type": "object",
+      "required": ["overallScore", "grade"],
+      "properties": {
+        "overallScore": {
+          "type": "number",
+          "minimum": 0,
+          "maximum": 100
+        },
+        "grade": {
+          "type": "string",
+          "pattern": "^[A-F][+-]?$"
+        },
+        "dimensions": {
+          "type": "object",
+          "properties": {
+            "correctness": { "type": "number", "minimum": 0, "maximum": 100 },
+            "readability": { "type": "number", "minimum": 0, "maximum": 100 },
+            "maintainability": { "type": "number", "minimum": 0, "maximum": 100 },
+            "performance": { "type": "number", "minimum": 0, "maximum": 100 },
+            "security": { "type": "number", "minimum": 0, "maximum": 100 },
+            "testability": { "type": "number", "minimum": 0, "maximum": 100 }
+          }
+        },
+        "strengths": {
+          "type": "array",
+          "items": { "type": "string" }
+        },
+        "weaknesses": {
+          "type": "array",
+          "items": { "type": "string" }
+        }
+      }
+    },
+    "severityBreakdown": {
+      "type": "object",
+      "properties": {
+        "critical": { "type": "integer", "minimum": 0 },
+        "high": { "type": "integer", "minimum": 0 },
+        "medium": { "type": "integer", "minimum": 0 },
+        "low": { "type": "integer", "minimum": 0 },
+        "nitpick": { "type": "integer", "minimum": 0 },
+        "blocking": { "type": "integer", "minimum": 0 }
+      }
+    },
+    "recommendation": {
+      "type": "object",
+      "required": ["id", "title", "priority", "impact"],
+      "properties": {
+        "id": {
+          "type": "string",
+          "pattern": "^REC-\\d{3,6}$"
+        },
+        "title": {
+          "type": "string",
+          "maxLength": 200
+        },
+        "description": {
+          "type": "string",
+          "maxLength": 2000
+        },
+        "priority": {
+          "type": "string",
+          "enum": ["critical", "high", "medium", "low"]
+        },
+        "impact": {
+          "type": "string",
+          "enum": ["transformative", "significant", "moderate", "minor"]
+        },
+        "relatedFindings": {
+          "type": "array",
+          "items": { "type": "string" }
+        },
+        "effort": {
+          "type": "string",
+          "enum": ["trivial", "low", "medium", "high", "major"]
+        },
+        "codeExample": {
+          "type": "string",
+          "maxLength": 5000
+        }
+      }
+    },
+    "technicalDebt": {
+      "type": "object",
+      "properties": {
+        "totalDebtHours": { "type": "number", "minimum": 0 },
+        "debtRatio": { "type": "number", "minimum": 0, "maximum": 100 },
+        "categories": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "properties": {
+              "category": { "type": "string" },
+              "hours": { "type": "number" },
+              "priority": { "type": "string" }
+            }
+          }
+        }
+      }
+    },
+    "metrics": {
+      "type": "object",
+      "properties": {
+        "filesReviewed": { "type": "integer", "minimum": 0 },
+        "linesReviewed": { "type": "integer", "minimum": 0 },
+        "totalFindings": { "type": "integer", "minimum": 0 },
+        "blockingIssues": { "type": "integer", "minimum": 0 },
+        "suggestedFixes": { "type": "integer", "minimum": 0 }
+      }
+    },
+    "metadata": {
+      "type": "object",
+      "properties": {
+        "executionTimeMs": { "type": "integer", "minimum": 0 },
+        "toolsUsed": { "type": "array", "items": { "type": "string" } },
+        "agentId": { "type": "string", "pattern": "^qe-[a-z][a-z0-9-]*$" },
+        "reviewScope": { "type": "string" },
+        "reviewType": { "type": "string", "enum": ["full", "incremental", "focused"] }
+      }
+    },
+    "validationResult": {
+      "type": "object",
+      "properties": {
+        "schemaValid": { "type": "boolean" },
+        "contentValid": { "type": "boolean" },
+        "confidence": { "type": "number", "minimum": 0, "maximum": 1 }
+      }
+    },
+    "learningData": {
+      "type": "object",
+      "properties": {
+        "patternsDetected": { "type": "array", "items": { "type": "string" } },
+        "reward": { "type": "number", "minimum": 0, "maximum": 1 }
+      }
+    }
+  }
+}

package/assets/skills/brutal-honesty-review/scripts/validate-config.json

@@ -0,0 +1,34 @@
+{
+  "skillName": "brutal-honesty-review",
+  "skillVersion": "1.0.0",
+  "requiredTools": [
+    "jq"
+  ],
+  "optionalTools": [],
+  "schemaPath": "schemas/output.json",
+  "requiredFields": [
+    "skillName",
+    "status",
+    "output",
+    "output.summary",
+    "output.reviewFindings",
+    "output.codeQuality"
+  ],
+  "requiredNonEmptyFields": [],
+  "mustContainTerms": [
+    "review",
+    "code"
+  ],
+  "mustNotContainTerms": [
+    "TODO",
+    "FIXME"
+  ],
+  "enumValidations": {
+    ".status": [
+      "success",
+      "partial",
+      "failed",
+      "skipped"
+    ]
+  }
+}

package/assets/skills/cicd-pipeline-qe-orchestrator/README.md

@@ -280,7 +280,7 @@ See main SKILL.md [Troubleshooting section](SKILL.md#troubleshooting) for:
 - [Microservice Pipeline Workflow](resources/workflows/microservice-pipeline.md)
 - [Monolith Pipeline Workflow](resources/workflows/monolith-pipeline.md)
 - [Mobile Pipeline Workflow](resources/workflows/mobile-pipeline.md)
-- [All 60 QE Skills Reference](https://github.com/proffesor-for-testing/agentic-qe/blob/main/docs/reference/skills.md)
+- [All 61 QE Skills Reference](https://github.com/proffesor-for-testing/agentic-qe/blob/main/docs/reference/skills.md)
 - [All 50 QE Agents Reference](https://github.com/proffesor-for-testing/agentic-qe/blob/main/docs/reference/agents.md)
 
 ## Contributing

package/assets/skills/cicd-pipeline-qe-orchestrator/SKILL.md

@@ -11,6 +11,12 @@ last_optimized: 2025-12-02
 dependencies: [agentic-quality-engineering, shift-left-testing]
 quick_reference_card: true
 tags: [cicd, pipeline, orchestration, quality-gates, shift-left, shift-right, fleet]
+trust_tier: 3
+validation:
+  schema_path: schemas/output.json
+  validator_path: scripts/validate-config.json
+  eval_path: evals/cicd-pipeline-qe-orchestrator.yaml
+
 ---
 
 # CI/CD Pipeline QE Orchestrator

package/assets/skills/cicd-pipeline-qe-orchestrator/evals/cicd-pipeline-qe-orchestrator.yaml

@@ -0,0 +1,157 @@
+skill: cicd-pipeline-qe-orchestrator
+version: 1.0.0
+description: >
+  Evaluation suite for CI/CD pipeline QE orchestration.
+  Tests orchestration plan generation, test execution scheduling,
+  and quality gate configuration across multiple models.
+
+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
+  store_failure_patterns: true
+  pattern_ttl_days: 90
+  min_confidence_to_store: 0.7
+
+result_format:
+  json_output: true
+  markdown_report: true
+  include_timing: true
+  include_token_usage: true
+
+setup:
+  required_tools:
+    - jq
+
+test_cases:
+
+  - id: tc001_basic_pipeline_orchestration
+    description: "Generate orchestration plan for basic pipeline"
+    category: orchestration
+    priority: critical
+
+    input:
+      pipeline_config:
+        stages:
+          - build
+          - test
+          - deploy
+        languages:
+          - javascript
+          - python
+
+    expected_output:
+      must_contain:
+        - "orchestration"
+        - "test"
+        - "quality"
+      must_not_contain:
+        - "error"
+
+    validation:
+      schema_check: true
+      keyword_match_threshold: 0.8
+
+  - id: tc002_parallel_execution_plan
+    description: "Generate parallel test execution schedule"
+    category: orchestration
+    priority: high
+
+    input:
+      test_count: 50
+      parallel_workers: 5
+      test_types:
+        - unit
+        - integration
+        - e2e
+
+    expected_output:
+      must_contain:
+        - "parallel"
+        - "schedule"
+        - "execution"
+
+    validation:
+      schema_check: true
+      keyword_match_threshold: 0.7
+
+  - id: tc003_quality_gates
+    description: "Configure quality gates and thresholds"
+    category: quality_gates
+    priority: high
+
+    input:
+      coverage_threshold: 80
+      test_pass_rate: 95
+      performance_budget_ms: 2000
+
+    expected_output:
+      must_contain:
+        - "gate"
+        - "threshold"
+        - "coverage"
+
+    validation:
+      schema_check: true
+
+  - id: tc004_flaky_test_handling
+    description: "Generate strategy for flaky test detection"
+    category: resilience
+    priority: medium
+
+    input:
+      test_results: [
+        { "name": "test_a", "run1": "pass", "run2": "fail", "run3": "pass" },
+        { "name": "test_b", "run1": "pass", "run2": "pass", "run3": "pass" }
+      ]
+
+    expected_output:
+      must_contain:
+        - "flaky"
+        - "retry"
+        - "strategy"
+
+    validation:
+      schema_check: true
+
+  - id: tc005_negative_invalid_config
+    description: "Handle invalid pipeline configuration gracefully"
+    category: error_handling
+    priority: medium
+
+    input:
+      pipeline_config: null
+
+    expected_output:
+      must_contain:
+        - "invalid"
+        - "require"
+
+    validation:
+      schema_check: true
+      allow_partial: true
+
+success_criteria:
+  pass_rate: 0.9
+  critical_pass_rate: 1.0
+  avg_reasoning_quality: 0.75
+  max_execution_time_ms: 300000
+
+metadata:
+  author: "qe-coordinator"
+  created: "2026-02-02"
+  coverage_target: >
+    CI/CD orchestration with 5 test cases covering basic pipeline setup,
+    parallel execution, quality gates, flaky test handling, and error cases.