@dzhechkov/keysarium 1.7.18 → 1.7.20

package/templates/.claude/skills/feature-adr/references/agentic-qe/qe-ref-performance-testing/scripts/validate-config.json

@@ -0,0 +1,55 @@
+{
+  "skillName": "performance-testing",
+  "skillVersion": "1.0.0",
+  "requiredTools": [
+    "jq"
+  ],
+  "optionalTools": [
+    "k6",
+    "artillery",
+    "jmeter",
+    "node",
+    "ajv",
+    "jsonschema",
+    "python3"
+  ],
+  "schemaPath": "schemas/output.json",
+  "requiredFields": [
+    "skillName",
+    "status",
+    "output",
+    "output.summary",
+    "output.testType",
+    "output.metrics"
+  ],
+  "requiredNonEmptyFields": [
+    "output.summary"
+  ],
+  "mustContainTerms": [
+    "response",
+    "throughput"
+  ],
+  "mustNotContainTerms": [
+    "TODO",
+    "placeholder",
+    "FIXME"
+  ],
+  "enumValidations": {
+    ".status": [
+      "success",
+      "partial",
+      "failed",
+      "skipped"
+    ],
+    ".output.testType": [
+      "load",
+      "stress",
+      "endurance",
+      "spike",
+      "volume",
+      "scalability",
+      "smoke",
+      "soak"
+    ]
+  }
+}

package/templates/.claude/skills/feature-adr/references/agentic-qe/qe-ref-qcsd-production-swarm/REFERENCE.md

@@ -0,0 +1,222 @@
+---
+name: qcsd-production-swarm
+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
+tokenEstimate: 32000
+# DDD Domain Mapping (from QCSD-AGENTIC-QE-MAPPING-FRAMEWORK.md)
+domains:
+  primary:
+    - domain: learning-optimization
+      agents: [qe-metrics-optimizer]
+    - domain: defect-intelligence
+      agents: [qe-defect-predictor, qe-root-cause-analyzer]
+  conditional:
+    - domain: chaos-resilience
+      agents: [qe-chaos-engineer, qe-performance-tester]
+    - domain: defect-intelligence
+      agents: [qe-regression-analyzer, qe-pattern-learner]
+    - domain: enterprise-integration
+      agents: [qe-middleware-validator, qe-sap-rfc-tester, qe-sod-analyzer]
+  feedback:
+    - domain: learning-optimization
+      agents: [qe-learning-coordinator, qe-transfer-specialist]
+# Agent Inventory
+agents:
+  core: [qe-metrics-optimizer, qe-defect-predictor, qe-root-cause-analyzer]
+  conditional: [qe-chaos-engineer, qe-performance-tester, qe-regression-analyzer, qe-pattern-learner, qe-middleware-validator, qe-sap-rfc-tester, qe-sod-analyzer]
+  feedback: [qe-learning-coordinator, qe-transfer-specialist]
+  total: 12
+  sub_agents: 0
+skills: [shift-right-testing, chaos-engineering-resilience, quality-metrics, performance-testing, holistic-testing-pact]
+# Execution Models (Task Tool is PRIMARY)
+execution:
+  primary: task-tool
+  alternatives: [mcp-tools, cli]
+swarm_pattern: true
+parallel_batches: 3
+last_updated: 2026-02-17
+enforcement_level: strict
+tags: [qcsd, production, telemetry, dora, rca, defect-prediction, feedback-loop, learning, swarm, parallel, ddd]
+trust_tier: 3
+validation:
+  schema_path: schemas/output.json
+  validator_path: scripts/validate-config.json
+  eval_path: evals/qcsd-production-swarm.yaml
+---
+
+<!-- Vendored from https://github.com/proffesor-for-testing/agentic-qe at 0a6de058575cbe292afe220df105cc74120f7674 (MIT, Copyright (c) 2025 Agentic QE Contributors), 2026-10-24. Bundled references do not install aqe, MCP tools, pattern memory, or fleet runtime. See ../LICENSE.agentic-qe and ../README.md. -->
+
+## Keysarium execution adapter
+
+This pinned upstream body is methodology inside the bundled feature-ADR pipeline. In Reference Mode, the feature-ADR module that loaded this file owns orchestration and checkpoints. Use the reasoning and output shape below with the host's available tools. Do not treat upstream `aqe` CLI/MCP calls, named agent roles, browser tools, or example absolute paths as installed capabilities. Name a missing capability or evidence in the checkpoint instead of reporting that an upstream step ran. The schemas and eval files are bundled for explicit validation; bundling them does not run those checks automatically.
+
+Relative paths such as `schemas/output.json`, `evals/...` and `steps/...` resolve from this skill directory under `references/agentic-qe/`. Direct Extended Mode still requires a separately installed `aqe` runtime; verify each required runtime capability before using it.
+
+The upstream `run-history.json` is execution history, not a reference contract, and is intentionally omitted. Do not run an upstream example that reads or writes it unless an installed aqe runtime supplies its own history.
+
+<!-- BEGIN AGENTIC-QE UPSTREAM BODY -->
+
+# QCSD Production Swarm v1.0
+
+Post-release production health assessment and QCSD feedback loop closure.
+
+---
+
+## Overview
+
+The Production Swarm assesses release health in the live production environment using
+DORA metrics, incident RCA, defect prediction, and cross-phase feedback loops. It renders
+a HEALTHY / DEGRADED / CRITICAL decision and is the only QCSD phase with dual
+responsibility: assessing current production health AND closing the feedback loop
+back to Ideation and Refinement phases.
+
+### QCSD Phase Positioning
+
+| Phase | Swarm | Decision | When |
+|-------|-------|----------|------|
+| Ideation | qcsd-ideation-swarm | GO / CONDITIONAL / NO-GO | PI/Sprint Planning |
+| Refinement | qcsd-refinement-swarm | READY / CONDITIONAL / NOT-READY | Sprint Refinement |
+| Development | qcsd-development-swarm | SHIP / CONDITIONAL / HOLD | During Sprint |
+| Verification | qcsd-cicd-swarm | RELEASE / REMEDIATE / BLOCK | Pre-Release / CI-CD |
+| **Production** | **qcsd-production-swarm** | **HEALTHY / DEGRADED / CRITICAL** | **Post-Release** |
+
+### Parameters
+
+- `TELEMETRY_DATA`: Path to production telemetry, incident reports, and DORA metrics (required)
+- `RELEASE_ID`: Release identifier for tracking (optional)
+- `OUTPUT_FOLDER`: Where to save reports (default: `${PROJECT_ROOT}/Agentic QCSD/production/`)
+- `SLA_DEFINITIONS`: Path to SLA/SLO target definitions (optional)
+
+---
+
+## ENFORCEMENT RULES - READ FIRST
+
+| Rule | Enforcement |
+|------|-------------|
+| **E1** | You MUST spawn ALL THREE core agents in Step 2. No exceptions. |
+| **E2** | You MUST put all parallel Task calls in a SINGLE message. |
+| **E3** | You MUST STOP and WAIT after each batch. No proceeding early. |
+| **E4** | You MUST spawn conditional agents if flags are TRUE. No skipping. |
+| **E5** | You MUST apply HEALTHY/DEGRADED/CRITICAL logic exactly as specified in Step 5. |
+| **E6** | You MUST generate the full report structure. No abbreviated versions. |
+| **E7** | Each agent MUST read its reference files before analysis. |
+| **E8** | You MUST run BOTH feedback agents in Step 8 SEQUENTIALLY. Always. Both agents. |
+| **E9** | You MUST execute Step 7 learning persistence. No skipping. |
+
+**PROHIBITED BEHAVIORS:**
+- Summarizing instead of spawning agents
+- Skipping agents "for brevity"
+- Proceeding before background tasks complete
+- Providing your own analysis instead of spawning specialists
+- Omitting report sections or using placeholder text
+
+---
+
+## Step Execution Protocol
+
+This skill uses a micro-file step architecture. Each step is a self-contained file
+loaded one at a time to avoid "lost in the middle" context degradation.
+
+**Execute steps sequentially by reading each step file with the Read tool.**
+
+### Steps
+
+1. **Flag Detection** -- `steps/01-flag-detection.md` -- Retrieve CI/CD signals, detect telemetry source, evaluate all 7 flags
+2. **Core Agents** -- `steps/02-core-agents.md` -- Spawn qe-metrics-optimizer, qe-defect-predictor, qe-root-cause-analyzer in parallel
+3. **Batch 1 Results** -- `steps/03-batch1-results.md` -- Wait for core agents, extract all metrics
+4. **Conditional Agents** -- `steps/04-conditional-agents.md` -- Spawn flagged conditional agents in parallel
+5. **Decision Synthesis** -- `steps/05-decision-synthesis.md` -- Apply HEALTHY/DEGRADED/CRITICAL logic
+6. **Report Generation** -- `steps/06-report-generation.md` -- Generate executive summary and full report
+7. **Learning Persistence** -- `steps/07-learning-persistence.md` -- Store findings to memory, save persistence record
+8. **Feedback Loop** -- `steps/08-feedback-loop.md` -- Run learning coordinator then transfer specialist (sequential)
+9. **Final Output** -- `steps/09-final-output.md` -- Display completion summary with all scores
+
+### Execution Instructions
+
+1. Use the Read tool to load the current step file (e.g., `Read({ file_path: ".claude/skills/qcsd-production-swarm/steps/01-flag-detection.md" })`)
+2. Execute the step's instructions completely
+3. Verify all success criteria are met before proceeding
+4. Pass the step's output as context to the next step
+5. If a step fails, halt and report the failure point -- do not skip ahead
+
+### Resume Support
+
+To resume from a specific step: specify `--from-step N` and the orchestrator will
+skip to step N. Ensure you have the required prerequisite data from prior steps.
+
+---
+
+## Agent Inventory
+
+| Agent | Type | Domain | Batch |
+|-------|------|--------|-------|
+| qe-metrics-optimizer | Core (always) | learning-optimization | 1 |
+| qe-defect-predictor | Core (always) | defect-intelligence | 1 |
+| qe-root-cause-analyzer | Core (always) | defect-intelligence | 1 |
+| qe-chaos-engineer | Conditional (HAS_INFRASTRUCTURE_CHANGE) | chaos-resilience | 2 |
+| qe-performance-tester | Conditional (HAS_PERFORMANCE_SLA) | chaos-resilience | 2 |
+| qe-regression-analyzer | Conditional (HAS_REGRESSION_RISK) | defect-intelligence | 2 |
+| qe-pattern-learner | Conditional (HAS_RECURRING_INCIDENTS) | defect-intelligence | 2 |
+| qe-middleware-validator | Conditional (HAS_MIDDLEWARE) | enterprise-integration | 2 |
+| qe-sap-rfc-tester | Conditional (HAS_SAP_INTEGRATION) | enterprise-integration | 2 |
+| qe-sod-analyzer | Conditional (HAS_AUTHORIZATION) | enterprise-integration | 2 |
+| qe-learning-coordinator | Feedback (always, sequential) | learning-optimization | 3 |
+| qe-transfer-specialist | Feedback (always, sequential) | learning-optimization | 3 |
+
+**Total: 12 agents (3 core + 7 conditional + 2 feedback)**
+
+---
+
+## Quality Gate Thresholds
+
+| Metric | HEALTHY | DEGRADED | CRITICAL |
+|--------|---------|----------|----------|
+| DORA Score | >= 0.7 | 0.4 - 0.69 | < 0.4 |
+| SLA Compliance | >= 99% | 95 - 98.9% | < 95% |
+| Incident Severity | P3/P4/NONE | P2 | P0/P1 |
+| Defect Trend | declining/stable | stable (density > 2) | increasing + density > 5 |
+| RCA Completeness | >= 80% | 50 - 79% | < 50% |
+
+---
+
+## Report Filename Mapping
+
+| Agent | Report Filename | Step |
+|-------|----------------|------|
+| qe-metrics-optimizer | `02-dora-metrics.md` | 2 |
+| qe-defect-predictor | `03-defect-prediction.md` | 2 |
+| qe-root-cause-analyzer | `04-root-cause-analysis.md` | 2 |
+| qe-chaos-engineer | `05-chaos-resilience.md` | 4 |
+| qe-performance-tester | `06-performance-sla.md` | 4 |
+| qe-regression-analyzer | `07-regression-analysis.md` | 4 |
+| qe-pattern-learner | `08-pattern-analysis.md` | 4 |
+| Learning Persistence | `09-learning-persistence.json` | 7 |
+| qe-middleware-validator | `10-middleware-health.md` | 4 |
+| qe-sap-rfc-tester | `11-sap-health.md` | 4 |
+| qe-sod-analyzer | `12-sod-compliance.md` | 4 |
+| Feedback agents | `13-feedback-loops.md` | 8 |
+| Synthesis | `01-executive-summary.md` | 6 |
+
+---
+
+## Execution Model Options
+
+| Model | When to Use | Agent Spawn |
+|-------|-------------|-------------|
+| **Task Tool** (PRIMARY) | Claude Code sessions | `Task({ subagent_type, run_in_background: true })` |
+| **MCP Tools** | MCP server available | `fleet_init({})` / `task_submit({})` |
+| **CLI** | Terminal/scripts | `swarm init` / `agent spawn` |
+
+---
+
+## Key Principle
+
+**Production health is measured by outcomes, not intentions. This swarm provides
+evidence-based production assessment and closes the QCSD feedback loop.**
+<!-- END AGENTIC-QE UPSTREAM BODY -->
+
+## Keysarium addition: feature-ADR handoff
+
+Use the production feedback structure to frame Step 9 post-deploy monitoring and future feature-ADR research. A reference-only run may propose a monitoring checklist, but must not report HEALTHY, DEGRADED, CRITICAL, DORA scores, incident analysis, agent execution, or memory persistence without actual production evidence and available runtime tools.

package/templates/.claude/skills/feature-adr/references/agentic-qe/qe-ref-qcsd-production-swarm/evals/qcsd-production-swarm.yaml

@@ -0,0 +1,246 @@
+skill: qcsd-production-swarm
+version: 1.0.0
+description: >
+  Evaluation suite for QCSD production telemetry swarm orchestration.
+  Tests DORA metrics analysis, root cause analysis, defect prediction, agent coordination, and feedback loop synthesis.
+
+models_to_test:
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
+
+mcp_integration:
+  enabled: true
+  namespace: skill-validation
+  query_patterns: true
+  track_outcomes: true
+  store_patterns: true
+  target_agents:
+    - qe-learning-coordinator
+    - qe-queen-coordinator
+
+learning:
+  store_success_patterns: true
+  pattern_ttl_days: 90
+
+result_format:
+  json_output: true
+  include_timing: true
+  include_token_usage: true
+
+setup:
+  required_tools:
+    - jq
+
+test_cases:
+
+  - id: tc001_dora_metrics_analysis
+    description: "Perform DORA metrics analysis from production telemetry"
+    category: dora
+    priority: critical
+
+    input:
+      telemetry_data: "Production metrics for v3.6.9 release"
+      project_type: "web_application"
+
+    expected_output:
+      must_contain:
+        - "deployment frequency"
+        - "lead time"
+        - "MTTR"
+        - "change failure"
+
+    validation:
+      schema_check: true
+      keyword_match_threshold: 0.8
+
+  - id: tc002_root_cause_analysis
+    description: "Systematic root cause analysis of production incidents"
+    category: rca
+    priority: critical
+
+    input:
+      incidents: "P1 incident: API timeout spike after v3.6.9 deploy"
+      has_infrastructure_change: true
+      has_performance_sla: true
+
+    expected_output:
+      must_contain:
+        - "root cause"
+        - "severity"
+        - "resolution"
+
+    validation:
+      schema_check: true
+
+  - id: tc003_domain_flag_detection
+    description: "Detect HAS_INFRASTRUCTURE_CHANGE, HAS_PERFORMANCE_SLA, HAS_RECURRING_INCIDENTS flags"
+    category: flags
+    priority: high
+
+    input:
+      content: "Recent Kubernetes scaling policy change causing SLA breaches with recurring pod eviction incidents"
+      analyze_flags: true
+
+    expected_output:
+      must_contain:
+        - "HAS_INFRASTRUCTURE_CHANGE"
+        - "HAS_PERFORMANCE_SLA"
+        - "HAS_RECURRING_INCIDENTS"
+
+    validation:
+      schema_check: true
+
+  - id: tc004_agent_coordination
+    description: "Coordinate multi-agent production telemetry swarm execution"
+    category: orchestration
+    priority: high
+
+    input:
+      domain_flags:
+        HAS_INFRASTRUCTURE_CHANGE: true
+        HAS_PERFORMANCE_SLA: true
+        HAS_RECURRING_INCIDENTS: false
+
+    expected_output:
+      must_contain:
+        - "agent"
+        - "coordinate"
+
+    validation:
+      schema_check: true
+
+  - id: tc005_feedback_loop_synthesis
+    description: "Execute feedback loop synthesis to Ideation and Refinement phases"
+    category: feedback
+    priority: medium
+
+    input:
+      production_data: "Post-release monitoring for authentication service upgrade"
+      include_feedback_loops: true
+
+    expected_output:
+      must_contain:
+        - "feedback"
+        - "ideation"
+        - "refinement"
+
+    validation:
+      schema_check: true
+
+  - id: tc006_decision_logic_critical
+    description: "Decision logic must produce CRITICAL when any core metric breaches critical threshold"
+    category: decision_logic
+    priority: critical
+
+    input:
+      metrics:
+        doraScore: 0.35
+        slaCompliance: 93.0
+        incidentSeverity: "P1"
+        rcaCompleteness: 40
+        defectTrend: "increasing"
+        defectDensity: 6.2
+        resilienceScore: 45
+        middlewareHealth: 12
+        sapHealth: null
+        sodCompliance: null
+      domain_flags:
+        HAS_INFRASTRUCTURE_CHANGE: true
+        HAS_PERFORMANCE_SLA: true
+        HAS_RECURRING_INCIDENTS: true
+        HAS_MIDDLEWARE: true
+
+    expected_output:
+      must_contain:
+        - "CRITICAL"
+      must_not_contain:
+        - "HEALTHY"
+
+    validation:
+      schema_check: true
+      decision_deterministic: true
+
+  - id: tc007_decision_logic_healthy
+    description: "Decision logic must produce HEALTHY when all metrics exceed healthy thresholds"
+    category: decision_logic
+    priority: critical
+
+    input:
+      metrics:
+        doraScore: 0.85
+        slaCompliance: 99.5
+        incidentSeverity: "NONE"
+        rcaCompleteness: 95
+        defectTrend: "declining"
+        defectDensity: 0.8
+        resilienceScore: 92
+        middlewareHealth: 88
+        sapHealth: null
+        sodCompliance: 95
+      domain_flags:
+        HAS_INFRASTRUCTURE_CHANGE: true
+        HAS_PERFORMANCE_SLA: true
+        HAS_RECURRING_INCIDENTS: false
+        HAS_MIDDLEWARE: true
+        HAS_AUTHORIZATION: true
+
+    expected_output:
+      must_contain:
+        - "HEALTHY"
+      must_not_contain:
+        - "CRITICAL"
+
+    validation:
+      schema_check: true
+      decision_deterministic: true
+
+  - id: tc008_decision_logic_degraded
+    description: "Decision logic must produce DEGRADED when metrics fall between CRITICAL and HEALTHY thresholds"
+    category: decision_logic
+    priority: critical
+
+    input:
+      metrics:
+        doraScore: 0.55
+        slaCompliance: 97.0
+        incidentSeverity: "P3"
+        rcaCompleteness: 60
+        defectTrend: "stable"
+        defectDensity: 3.1
+        resilienceScore: 65
+        middlewareHealth: 55
+        sapHealth: 40
+        sodCompliance: null
+      domain_flags:
+        HAS_INFRASTRUCTURE_CHANGE: true
+        HAS_PERFORMANCE_SLA: true
+        HAS_RECURRING_INCIDENTS: false
+        HAS_MIDDLEWARE: true
+        HAS_SAP_INTEGRATION: true
+
+    expected_output:
+      must_contain:
+        - "DEGRADED"
+      must_not_contain:
+        - "CRITICAL"
+        - "HEALTHY"
+
+    validation:
+      schema_check: true
+      decision_deterministic: true
+
+success_criteria:
+  pass_rate: 0.875
+  critical_pass_rate: 1.0
+  avg_reasoning_quality: 0.75
+  max_execution_time_ms: 300000
+  decision_logic_pass_rate: 1.0
+
+metadata:
+  author: "qe-qcsd-orchestrator"
+  created: "2026-02-17"
+  updated: "2026-02-17"
+  coverage_target: >
+    QCSD production swarm with 8 test cases covering DORA metrics analysis,
+    root cause analysis, domain flag detection, agent coordination, feedback loop synthesis,
+    and 3 decision logic determinism tests (CRITICAL, HEALTHY, DEGRADED paths).