agentic-qe 3.7.18 → 3.7.19

package/.claude/skills/validation-pipeline/schemas/output.json

@@ -0,0 +1,193 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://agentic-qe.dev/schemas/validation-pipeline-output.json",
+  "title": "AQE Validation Pipeline Skill Output Schema",
+  "description": "Schema for validation pipeline skill output. Includes step results, scores, findings, and blockers.",
+  "type": "object",
+  "required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
+  "properties": {
+    "skillName": {
+      "type": "string",
+      "const": "validation-pipeline",
+      "description": "Must be 'validation-pipeline'"
+    },
+    "version": {
+      "type": "string",
+      "pattern": "^\\d+\\.\\d+\\.\\d+(-[a-zA-Z0-9]+)?$"
+    },
+    "timestamp": {
+      "type": "string",
+      "format": "date-time"
+    },
+    "status": {
+      "type": "string",
+      "enum": ["success", "partial", "failed", "skipped"]
+    },
+    "trustTier": {
+      "type": "integer",
+      "const": 3,
+      "description": "Trust tier 3 indicates full validation with eval suite"
+    },
+    "output": {
+      "type": "object",
+      "required": ["pipelineId", "pipelineName", "overall", "score", "steps"],
+      "properties": {
+        "pipelineId": {
+          "type": "string",
+          "description": "Pipeline identifier"
+        },
+        "pipelineName": {
+          "type": "string",
+          "description": "Human-readable pipeline name"
+        },
+        "overall": {
+          "type": "string",
+          "enum": ["pass", "fail", "warn"],
+          "description": "Overall pipeline verdict"
+        },
+        "score": {
+          "type": "integer",
+          "minimum": 0,
+          "maximum": 100,
+          "description": "Weighted average score across all steps"
+        },
+        "steps": {
+          "type": "array",
+          "items": { "$ref": "#/$defs/stepResult" },
+          "minItems": 1,
+          "description": "Per-step results"
+        },
+        "blockers": {
+          "type": "array",
+          "items": { "$ref": "#/$defs/finding" },
+          "description": "Findings from blocking steps that failed"
+        },
+        "halted": {
+          "type": "boolean",
+          "description": "Whether pipeline halted early"
+        },
+        "haltedAt": {
+          "type": "string",
+          "description": "Step ID where pipeline halted"
+        },
+        "totalDuration": {
+          "type": "integer",
+          "minimum": 0,
+          "description": "Total execution time in ms"
+        },
+        "summary": {
+          "type": "string",
+          "minLength": 20,
+          "maxLength": 2000,
+          "description": "Human-readable summary"
+        }
+      }
+    },
+    "metadata": { "$ref": "#/$defs/metadata" },
+    "validation": { "$ref": "#/$defs/validationResult" },
+    "learning": { "$ref": "#/$defs/learningData" }
+  },
+  "$defs": {
+    "stepResult": {
+      "type": "object",
+      "required": ["stepId", "stepName", "status", "score", "findings", "evidence", "duration"],
+      "properties": {
+        "stepId": {
+          "type": "string",
+          "description": "Step identifier"
+        },
+        "stepName": {
+          "type": "string",
+          "description": "Human-readable step name"
+        },
+        "status": {
+          "type": "string",
+          "enum": ["pass", "fail", "warn", "skip"],
+          "description": "Step verdict"
+        },
+        "score": {
+          "type": "integer",
+          "minimum": 0,
+          "maximum": 100,
+          "description": "Step score"
+        },
+        "findings": {
+          "type": "array",
+          "items": { "$ref": "#/$defs/finding" }
+        },
+        "evidence": {
+          "type": "array",
+          "items": { "type": "string" },
+          "description": "What was checked"
+        },
+        "duration": {
+          "type": "integer",
+          "minimum": 0,
+          "description": "Step duration in ms"
+        }
+      }
+    },
+    "finding": {
+      "type": "object",
+      "required": ["id", "stepId", "severity", "title", "description"],
+      "properties": {
+        "id": {
+          "type": "string"
+        },
+        "stepId": {
+          "type": "string"
+        },
+        "severity": {
+          "type": "string",
+          "enum": ["critical", "high", "medium", "low", "info"]
+        },
+        "title": {
+          "type": "string",
+          "minLength": 5,
+          "maxLength": 200
+        },
+        "description": {
+          "type": "string",
+          "maxLength": 2000
+        },
+        "location": {
+          "type": "string",
+          "description": "File path or document section"
+        },
+        "suggestion": {
+          "type": "string",
+          "description": "Suggested fix"
+        }
+      }
+    },
+    "metadata": {
+      "type": "object",
+      "properties": {
+        "executionTimeMs": { "type": "integer", "minimum": 0 },
+        "toolsUsed": { "type": "array", "items": { "type": "string" } },
+        "agentId": { "type": "string" },
+        "pipelineType": { "type": "string" },
+        "targetFile": { "type": "string" },
+        "stepsExecuted": { "type": "integer", "minimum": 0 },
+        "stepsSkipped": { "type": "integer", "minimum": 0 }
+      }
+    },
+    "validationResult": {
+      "type": "object",
+      "properties": {
+        "schemaValid": { "type": "boolean" },
+        "contentValid": { "type": "boolean" },
+        "confidence": { "type": "number", "minimum": 0, "maximum": 1 },
+        "warnings": { "type": "array", "items": { "type": "string" }, "maxItems": 20 },
+        "errors": { "type": "array", "items": { "type": "string" }, "maxItems": 20 }
+      }
+    },
+    "learningData": {
+      "type": "object",
+      "properties": {
+        "patternsDetected": { "type": "array", "items": { "type": "string" }, "maxItems": 20 },
+        "reward": { "type": "number", "minimum": 0, "maximum": 1 }
+      }
+    }
+  }
+}

package/.claude/skills/validation-pipeline/scripts/validate-config.json

@@ -0,0 +1,34 @@
+{
+  "skillName": "validation-pipeline",
+  "skillVersion": "1.0.0",
+  "requiredTools": [],
+  "optionalTools": ["jq"],
+  "schemaPath": "schemas/output.json",
+  "requiredFields": [
+    "skillName",
+    "status",
+    "output",
+    "output.pipelineId",
+    "output.pipelineName",
+    "output.overall",
+    "output.score",
+    "output.steps"
+  ],
+  "requiredNonEmptyFields": [
+    "output.pipelineName",
+    "output.steps"
+  ],
+  "mustContainTerms": [
+    "pipeline",
+    "validation"
+  ],
+  "mustNotContainTerms": [
+    "TODO",
+    "placeholder",
+    "FIXME"
+  ],
+  "enumValidations": {
+    ".status": ["success", "partial", "failed", "skipped"],
+    ".output.overall": ["pass", "fail", "warn"]
+  }
+}

package/README.md

@@ -159,19 +159,19 @@ Plus **7 TDD subagents** (red, green, refactor, code/integration/performance/sec
 
 ---
 
-## 78 QE Skills
+## 80 QE Skills
 
 Agents automatically apply relevant skills from the skill library. Skills are rated by **trust tier**:
 
 | Tier | Count | Meaning |
 |------|-------|---------|
-| **Tier 3 — Verified** | 46 | Full evaluation test suite, production-ready |
+| **Tier 3 — Verified** | 48 | Full evaluation test suite, production-ready |
 | **Tier 2 — Validated** | 7 | Has executable validator |
 | **Tier 1 — Structured** | 5 | Has JSON output schema |
 | **Tier 0 — Advisory** | 5 | Guidance only |
 
 <details>
-<summary><b>View all 78 skills</b></summary>
+<summary><b>View all 80 skills</b></summary>
 
 **Core Testing (12):** agentic-quality-engineering, holistic-testing-pact, context-driven-testing, tdd-london-chicago, xp-practices, risk-based-testing, test-automation-strategy, refactoring-patterns, shift-left-testing, shift-right-testing, regression-testing, verification-quality
 
@@ -191,6 +191,8 @@ Agents automatically apply relevant skills from the skill library. Skills are ra
 
 **Enterprise Integration (5):** enterprise-integration-testing, middleware-testing-patterns, observability-testing-patterns, wms-testing-patterns, pentest-validation
 
+**Validation (1):** validation-pipeline
+
 </details>
 
 ---

package/assets/skills/skills-manifest.json

@@ -1,7 +1,7 @@
 {
   "version": "1.2.0",
   "generated": "2026-01-27T00:00:00.000Z",
-  "totalSkills": 43,
+  "totalSkills": 44,
   "description": "Agentic QE Fleet skills manifest - Quality Engineering focused skills only. Claude Flow platform skills are managed separately.",
   "categories": {
     "qcsd-phases": {
@@ -31,6 +31,7 @@
       "priority": "medium",
       "skills": [
         "security-testing",
+        "validation-pipeline",
         "performance-testing",
         "accessibility-testing",
         "a11y-ally",
@@ -655,6 +656,21 @@
       "dependencies": [],
       "agents": ["qe-quality-analyzer"]
     },
+    "validation-pipeline": {
+      "id": "validation-pipeline",
+      "name": "Validation Pipeline",
+      "description": "Run structured 13-step requirements validation pipeline with gate enforcement, weighted scoring, and detailed findings.",
+      "category": "specialized-testing",
+      "priority": "high",
+      "file": "validation-pipeline/SKILL.md",
+      "tokenEstimate": 1500,
+      "optimizationStatus": "active",
+      "optimizationVersion": "1.0",
+      "lastOptimized": "2026-03-12",
+      "tags": ["validation", "requirements", "pipeline", "gate-enforcement", "scoring", "bmad"],
+      "dependencies": ["agentic-quality-engineering"],
+      "agents": ["qe-requirements-validator"]
+    },
     "bug-reporting-excellence": {
       "id": "bug-reporting-excellence",
       "name": "Bug Reporting Excellence",

package/assets/skills/validation-pipeline/SKILL.md

@@ -0,0 +1,164 @@
+---
+name: "Validation Pipeline"
+description: "Structured step-by-step validation of requirements, code, and artifacts with gate enforcement, per-step scoring, and structured reports."
+trust_tier: 3
+validation:
+  schema_path: schemas/output.json
+  validator_path: scripts/validate-config.json
+  eval_path: evals/validation-pipeline.yaml
+
+---
+
+# Validation Pipeline
+
+## Purpose
+
+Run structured validation pipelines that execute steps sequentially, enforce gates at blocking failures, and produce scored reports. Uses the `src/validation/pipeline.ts` framework with 13 requirements validation steps (BMAD-003).
+
+## Activation
+
+- When validating requirements documents
+- When running structured quality gates
+- When assessing document completeness, testability, or traceability
+- When invoked via `/validation-pipeline`
+
+## Quick Start
+
+```bash
+# Validate a requirements document (all 13 steps)
+/validation-pipeline requirements docs/requirements.md
+
+# Validate with specific steps only
+/validation-pipeline requirements docs/requirements.md --steps format-check,completeness-check,invest-criteria
+
+# Continue past blocking failures
+/validation-pipeline requirements docs/requirements.md --continue-on-failure
+
+# Output as JSON
+/validation-pipeline requirements docs/requirements.md --json
+```
+
+## Workflow
+
+### Step 1: Read the Target Document
+
+Read the file specified by the user. If no file is provided, ask for one.
+
+```
+Read the target document using the Read tool.
+Store the content for pipeline execution.
+```
+
+### Step 2: Select Pipeline
+
+Choose the appropriate pipeline based on the user's request:
+
+| Pipeline | Steps | Use Case |
+|----------|-------|----------|
+| `requirements` | 13 | Requirements documents, PRDs, user stories |
+
+Additional pipelines can be created by defining new step sets in `src/validation/steps/`.
+
+### Step 3: Execute Pipeline
+
+The pipeline framework (`src/validation/pipeline.ts`) handles execution:
+
+1. **Sequential execution** — steps run in order, each receiving results from prior steps
+2. **Gate enforcement** — blocking steps that fail halt the pipeline (unless `--continue-on-failure`)
+3. **Per-step scoring** — each step produces a 0-100 score with findings and evidence
+4. **Weighted rollup** — overall score uses category weights (format=10%, content=30%, quality=25%, traceability=20%, compliance=15%)
+
+#### Requirements Pipeline Steps (13 total)
+
+| # | Step ID | Category | Severity | What It Checks |
+|---|---------|----------|----------|----------------|
+| 1 | `format-check` | format | blocking | Headings, required sections, document length |
+| 2 | `completeness-check` | content | blocking | Required fields populated, acceptance criteria present |
+| 3 | `invest-criteria` | quality | warning | Independent, Negotiable, Valuable, Estimable, Small, Testable |
+| 4 | `smart-acceptance` | quality | warning | Specific, Measurable, Achievable, Relevant, Time-bound |
+| 5 | `testability-score` | quality | warning | Can each requirement be tested? |
+| 6 | `vague-term-detection` | content | info | Flags "should", "might", "various", "etc." |
+| 7 | `information-density` | content | info | Every sentence carries weight, no filler |
+| 8 | `traceability-check` | traceability | warning | Requirements-to-tests mapping exists |
+| 9 | `implementation-leakage` | quality | warning | Requirements don't prescribe implementation |
+| 10 | `domain-compliance` | compliance | info | Alignment with domain model |
+| 11 | `dependency-analysis` | traceability | info | Cross-requirement dependencies identified |
+| 12 | `bdd-scenario-generation` | quality | warning | Can generate Given/When/Then for each requirement |
+| 13 | `holistic-quality` | compliance | blocking | Overall coherence, no contradictions |
+
+### Step 4: Report Results
+
+Format the pipeline result as a structured report:
+
+```markdown
+# Validation Report: Requirements Pipeline
+
+**Overall**: PASS/FAIL/WARN | **Score**: 85/100 | **Duration**: 42ms
+
+## Step Results
+| # | Step | Status | Score | Findings | Duration |
+|---|------|--------|-------|----------|----------|
+| 1 | Format Check | PASS | 100 | 0 | 2ms |
+| 2 | Completeness | WARN | 60 | 2 | 5ms |
+...
+
+## Blockers
+- (blocking findings listed here)
+
+## All Findings
+- [HIGH] Missing acceptance criteria: Requirement US-104 has no AC
+- [MEDIUM] Vague term: "should" used 5 times without specifics
+...
+```
+
+### Step 5: Record Learning
+
+After pipeline execution, record the outcome for learning:
+
+```typescript
+// Store validation pattern
+memory store --namespace validation-pipeline --key "req-validation-{timestamp}" --value "{score, findings_count, halted}"
+```
+
+## Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `pipeline` | string | `requirements` | Pipeline type to run |
+| `file` | string | required | Path to document to validate |
+| `--steps` | string[] | all | Specific step IDs to run |
+| `--continue-on-failure` | boolean | false | Skip blocking gates |
+| `--json` | boolean | false | Output as JSON instead of markdown |
+| `--metadata` | object | {} | Additional context for steps |
+
+## Integration Points
+
+- **qe-requirements-validator agent** — delegates structured validation to this pipeline
+- **qe-quality-gate agent** — uses pipeline for gate evaluation
+- **YAML Pipelines** — can invoke validation steps as workflow actions
+- **MCP** — accessible via `pipeline_validate` tool
+
+## Output Schema
+
+The pipeline produces a `PipelineResult` object (see `schemas/output.json`):
+
+```typescript
+{
+  pipelineId: string;
+  pipelineName: string;
+  overall: 'pass' | 'fail' | 'warn';
+  score: number;           // 0-100 weighted average
+  steps: StepResult[];     // per-step details
+  blockers: Finding[];     // blocking findings
+  halted: boolean;
+  haltedAt?: string;       // step ID where halted
+  totalDuration: number;
+  timestamp: string;
+}
+```
+
+## Error Handling
+
+- **Step throws exception** — captured as a FAIL with critical finding, pipeline continues or halts per severity
+- **File not found** — report error, do not run pipeline
+- **Empty document** — format-check step will catch this as a blocking failure