aiox-core 5.0.4 → 5.0.7

package/pro/squads/squad-creator/data/quality-dimensions-framework.md

@@ -0,0 +1,405 @@
+# Quality Dimensions Framework
+
+> **Version:** 1.0.0
+> **Source:** AIOX Quality Standards
+
+Framework for evaluating squad outputs using multi-dimensional quality scoring.
+
+---
+
+## 1. Overview
+
+A comprehensive quality assessment uses 10 standardized dimensions. Each dimension has:
+- **Weight:** Relative importance (0.0-1.0)
+- **Threshold:** Minimum acceptable score
+- **Veto Power:** Whether low score blocks progress
+
+---
+
+## 2. Standard Quality Dimensions
+
+### Configuration
+
+```yaml
+quality_dimensions:
+  pattern_reference: "squad-creator/data/quality-dimensions-framework.md"
+  total_dimensions: 10
+
+  scoring:
+    overall_threshold: 7.0
+    minimum_per_dimension: 6.0
+    veto_on_failure: false  # Default to REVIEW, not VETO
+
+  dimensions:
+    1_accuracy:
+      name: "Accuracy"
+      weight: 1.0
+      threshold: 7.0
+      veto_power: true
+      description: "Correctness verified by data/evidence"
+
+    2_coherence:
+      name: "Coherence"
+      weight: 0.9
+      threshold: 6.0
+      veto_power: false
+      description: "Internal consistency and alignment"
+
+    3_strategic_alignment:
+      name: "Strategic Alignment"
+      weight: 0.9
+      threshold: 6.0
+      veto_power: false
+      description: "Connection to goals and vision"
+
+    4_operational_excellence:
+      name: "Operational Excellence"
+      weight: 0.8
+      threshold: 6.0
+      veto_power: false
+      description: "Process quality and efficiency"
+
+    5_innovation_capacity:
+      name: "Innovation Capacity"
+      weight: 0.7
+      threshold: 5.0
+      veto_power: false
+      description: "Ability to create novel solutions"
+
+    6_risk_management:
+      name: "Risk Management"
+      weight: 0.8
+      threshold: 6.0
+      veto_power: false
+      description: "Identification and mitigation of risks"
+
+    7_resource_optimization:
+      name: "Resource Optimization"
+      weight: 0.8
+      threshold: 6.0
+      veto_power: false
+      description: "Efficient use of time, money, people"
+
+    8_stakeholder_value:
+      name: "Stakeholder Value"
+      weight: 0.7
+      threshold: 6.0
+      veto_power: false
+      description: "Value delivered to all parties"
+
+    9_sustainability:
+      name: "Sustainability"
+      weight: 0.7
+      threshold: 6.0
+      veto_power: false
+      description: "Long-term viability"
+
+    10_adaptability:
+      name: "Adaptability"
+      weight: 0.6
+      threshold: 5.0
+      veto_power: false
+      description: "Ability to respond to change"
+```
+
+---
+
+## 3. Dimension Details
+
+### 3.1 Accuracy (Weight: 1.0, VETO)
+
+**Definition:** Correctness verified by data/evidence.
+
+**Scoring Criteria:**
+- 9-10: All claims verified, zero errors
+- 7-8: Minor inaccuracies, easily corrected
+- 5-6: Some unverified claims, needs review
+- 3-4: Significant errors or contradictions
+- 1-2: Fundamentally incorrect
+
+**Red Flags:**
+- Claims without supporting evidence
+- Contradictions within the output
+- Outdated or incorrect data
+
+### 3.2 Coherence (Weight: 0.9)
+
+**Definition:** Internal consistency and alignment.
+
+**Scoring Criteria:**
+- 9-10: Perfect internal consistency
+- 7-8: Minor inconsistencies, easily reconciled
+- 5-6: Some logical gaps
+- 3-4: Significant contradictions
+- 1-2: Incoherent
+
+**Red Flags:**
+- Statements contradict each other
+- Logic gaps in reasoning
+- Disconnected sections
+
+### 3.3 Strategic Alignment (Weight: 0.9)
+
+**Definition:** Connection to goals and vision.
+
+**Scoring Criteria:**
+- 9-10: Directly enables strategic goals
+- 7-8: Clearly supports strategy
+- 5-6: Neutral, neither helps nor hinders
+- 3-4: Questionable alignment
+- 1-2: Contradicts strategic direction
+
+**Red Flags:**
+- No clear connection to objectives
+- Works against stated goals
+- Short-term focus at expense of long-term
+
+### 3.4 Operational Excellence (Weight: 0.8)
+
+**Definition:** Process quality and efficiency.
+
+**Scoring Criteria:**
+- 9-10: Optimal process, best practices
+- 7-8: Well-designed, minor improvements possible
+- 5-6: Functional but inefficient
+- 3-4: Significant process issues
+- 1-2: Broken or missing processes
+
+**Red Flags:**
+- Manual work that should be automated
+- Missing documentation
+- Inconsistent execution
+
+### 3.5 Innovation Capacity (Weight: 0.7)
+
+**Definition:** Ability to create novel solutions.
+
+**Scoring Criteria:**
+- 9-10: Breakthrough innovation
+- 7-8: Creative improvements
+- 5-6: Standard solutions
+- 3-4: Outdated approaches
+- 1-2: No innovation
+
+**Red Flags:**
+- Copy-paste solutions without adaptation
+- Ignoring new tools/methods
+- Resistance to improvement
+
+### 3.6 Risk Management (Weight: 0.8)
+
+**Definition:** Identification and mitigation of risks.
+
+**Scoring Criteria:**
+- 9-10: All risks identified and mitigated
+- 7-8: Major risks addressed
+- 5-6: Some risks identified, partial mitigation
+- 3-4: Significant blind spots
+- 1-2: No risk consideration
+
+**Red Flags:**
+- No contingency plans
+- Ignoring known risks
+- Single points of failure
+
+### 3.7 Resource Optimization (Weight: 0.8)
+
+**Definition:** Efficient use of time, money, people.
+
+**Scoring Criteria:**
+- 9-10: Optimal resource allocation
+- 7-8: Efficient with minor waste
+- 5-6: Acceptable efficiency
+- 3-4: Significant waste
+- 1-2: Grossly inefficient
+
+**Red Flags:**
+- Redundant work
+- Over-engineering
+- Under-utilization of available resources
+
+### 3.8 Stakeholder Value (Weight: 0.7)
+
+**Definition:** Value delivered to all parties.
+
+**Scoring Criteria:**
+- 9-10: Exceptional value for all stakeholders
+- 7-8: Good value, meets expectations
+- 5-6: Minimal viable value
+- 3-4: Some stakeholders underserved
+- 1-2: No clear value
+
+**Red Flags:**
+- Ignoring key stakeholder needs
+- Unbalanced value distribution
+- No clear benefit articulation
+
+### 3.9 Sustainability (Weight: 0.7)
+
+**Definition:** Long-term viability.
+
+**Scoring Criteria:**
+- 9-10: Built for perpetuity
+- 7-8: Sustainable with maintenance
+- 5-6: Medium-term viability
+- 3-4: Short-term solution
+- 1-2: Not sustainable
+
+**Red Flags:**
+- Technical debt accumulation
+- Dependency on unsustainable resources
+- No maintenance plan
+
+### 3.10 Adaptability (Weight: 0.6)
+
+**Definition:** Ability to respond to change.
+
+**Scoring Criteria:**
+- 9-10: Highly flexible, easy to modify
+- 7-8: Adaptable with reasonable effort
+- 5-6: Some flexibility
+- 3-4: Rigid, hard to change
+- 1-2: Inflexible, locked in
+
+**Red Flags:**
+- Hardcoded assumptions
+- No extension points
+- Tightly coupled components
+
+---
+
+## 4. Assessment Template
+
+```yaml
+quality_assessment:
+  subject: "What is being assessed"
+  assessment_date: "YYYY-MM-DD"
+  assessor: "Who/what performed assessment"
+
+  dimensions:
+    - name: "Accuracy"
+      score: 0-10
+      evidence: "Supporting observations"
+      recommendations: ["Improvements"]
+
+    - name: "Coherence"
+      score: 0-10
+      evidence: "Observations"
+      recommendations: []
+
+    # ... repeat for all 10 dimensions
+
+  overall_score: number  # Weighted average
+  pass_threshold: 7.0
+  status: "PASS | FAIL | REVIEW"
+
+  summary:
+    strengths: ["What's working well"]
+    weaknesses: ["What needs improvement"]
+    critical_issues: ["Blocking issues"]
+    recommendations: ["Prioritized actions"]
+```
+
+---
+
+## 5. Scoring Calculation
+
+### Weighted Average Formula
+
+```
+overall_score = Σ(dimension_score × weight) / Σ(weights)
+```
+
+### Pass/Fail Logic
+
+```
+IF (overall_score >= 7.0 AND no_dimension < 6.0)
+  THEN status = PASS
+ELSE IF (any_veto_dimension < threshold)
+  THEN status = FAIL
+ELSE
+  status = REVIEW
+```
+
+---
+
+## 6. Domain-Specific Weights
+
+Adjust weights based on domain:
+
+### Software Development
+
+```yaml
+weights_override:
+  accuracy: 1.0        # Code must work
+  operational_excellence: 0.9
+  risk_management: 0.9
+  sustainability: 0.8
+```
+
+### Marketing/Copy
+
+```yaml
+weights_override:
+  stakeholder_value: 1.0  # Must resonate with audience
+  innovation_capacity: 0.9
+  coherence: 0.9
+```
+
+### Operations/Process
+
+```yaml
+weights_override:
+  operational_excellence: 1.0
+  resource_optimization: 0.9
+  risk_management: 0.9
+```
+
+---
+
+## 7. Integration with Workflows
+
+Add quality assessment as a checkpoint:
+
+```yaml
+checkpoint:
+  id: "quality-gate"
+  type: "quality_dimensions"
+  phase: "final"
+
+  dimensions_to_evaluate: "all"  # or specific list
+
+  thresholds:
+    overall: 7.0
+    per_dimension: 6.0
+
+  veto_dimensions:
+    - "accuracy"
+
+  pass_action: "Approve and publish"
+  fail_action: "Return for revision"
+  review_action: "Escalate to human"
+```
+
+---
+
+## 8. Continuous Improvement
+
+Track scores over time:
+
+```yaml
+tracking:
+  aggregate_by: ["month", "quarter"]
+  metrics:
+    - average_overall_score
+    - dimension_averages
+    - fail_rate
+    - veto_rate
+  alerts:
+    - condition: "average_score < 7.0"
+      action: "Review process quality"
+```
+
+---
+
+*AIOX Quality Dimensions Framework v1.0*

package/pro/squads/squad-creator/data/quality-gates.yaml

@@ -0,0 +1,135 @@
+meta:
+  id: squad-creator-quality-gates
+  version: 1.0.0
+  purpose: "Thresholds numéricos canônicos para criação, QA e publicação de squads."
+
+quality_thresholds:
+  discovery:
+    viability_score:
+      threshold: 6
+    overlap_confidence:
+      threshold: 0.7
+    use_case_coverage:
+      threshold: 0.8
+    evidence_paths:
+      threshold: 3
+  architecture:
+    roster_completeness:
+      threshold: 0.9
+    template_alignment:
+      threshold: 0.85
+    composition_coverage:
+      threshold: 0.8
+    command_surface_readiness:
+      threshold: 0.75
+  generation:
+    scaffold_completeness:
+      threshold: 0.95
+    schema_pass_rate:
+      threshold: 1.0
+    artifact_binding:
+      threshold: 0.9
+    task_contract_coverage:
+      threshold: 0.95
+  validation:
+    structure_score:
+      threshold: 8.5
+    compatibility_score:
+      threshold: 8.0
+    references_score:
+      threshold: 8.0
+    completeness_score:
+      threshold: 8.5
+  installation:
+    sync_success_rate:
+      threshold: 1.0
+    runtime_boot_success:
+      threshold: 1.0
+    command_registry_match:
+      threshold: 0.95
+    ide_projection_health:
+      threshold: 0.9
+  cross_provider:
+    baseline_quality:
+      threshold: 7.0
+    candidate_reliability:
+      threshold: 0.8
+    pt_br_fidelity:
+      threshold: 0.85
+    cost_saving_ratio:
+      threshold: 0.15
+  publication:
+    publish_readiness:
+      threshold: 0.9
+    handoff_completeness:
+      threshold: 0.95
+    registry_update_health:
+      threshold: 1.0
+    post_publish_validation:
+      threshold: 0.9
+  governance:
+    executor_coverage:
+      threshold: 1.0
+    domain_registry_coverage:
+      threshold: 1.0
+    token_family_coverage:
+      threshold: 1.0
+    artifact_lifecycle_coverage:
+      threshold: 0.95
+  runtime:
+    state_persistence_health:
+      threshold: 1.0
+    retry_policy_coverage:
+      threshold: 0.9
+    log_retention_health:
+      threshold: 0.9
+    recovery_handoff_quality:
+      threshold: 0.85
+  observability:
+    quality_dashboard_freshness:
+      threshold: 0.9
+    analytics_signal_coverage:
+      threshold: 0.85
+    deviation_register_completeness:
+      threshold: 0.8
+    evidence_traceability:
+      threshold: 0.95
+
+veto_conditions:
+  - id: SC_QG_001
+    condition: "schema_pass_rate < 1.0"
+    action: "Bloquear publicação"
+  - id: SC_QG_002
+    condition: "viability_score < 6"
+    action: "Bloquear criação direta"
+  - id: SC_QG_003
+    condition: "publish_readiness < 0.9"
+    action: "Emitir handoff de correção"
+
+# migrated_from: squads/kaizen/data/quality-gates.yaml | migration_story: STORY-108.3 | date: 2026-04-04
+kaizen:
+  version: "1.0.0"
+  gates:
+    QG-KZ-001:
+      checkpoint: data_collection
+      threshold: 1
+      rule: "squad_inventory_present == true"
+      veto: true
+    QG-KZ-002:
+      checkpoint: evidence_quality
+      threshold: 3
+      rule: "critical_recommendation_evidence_count >= 3"
+      veto: true
+    QG-KZ-003:
+      checkpoint: report_completeness
+      threshold: 6
+      rule: "dimensions_covered >= 6"
+    QG-KZ-004:
+      checkpoint: weekly_digest_quality
+      threshold: 5
+      rule: "top_recommendations <= 5"
+      veto: true
+    QG-KZ-005:
+      checkpoint: output_quality_audit
+      threshold: 0.8
+      rule: "quality_audit_score >= 0.8"

package/pro/squads/squad-creator/data/radar/initial-radar.yaml

@@ -0,0 +1,76 @@
+# migrated_from: squads/kaizen/data/radar/initial-radar.yaml | migration_story: STORY-108.3 | date: 2026-04-04
+# Initial Technology Radar — Kaizen Squad
+# Date: 2026-02-15
+# Status: Baseline (to be updated by tech-radar agent)
+
+quadrants:
+  APIs:
+    adopt:
+      - name: "Gemini API"
+        since: "2025-Q4"
+        used_by: ["content-engine", "marketing"]
+        notes: "Primary image gen + text gen"
+      - name: "OpenAI API"
+        since: "2025-Q3"
+        used_by: ["content-engine"]
+        notes: "GPT-4 for specific tasks"
+    trial:
+      - name: "Together.ai"
+        since: "2026-Q1"
+        used_by: ["marketing"]
+        notes: "FLUX Schnell image gen"
+    assess: []
+    hold: []
+
+  "MCPs/Integrations":
+    adopt:
+      - name: "Context7"
+        since: "2025-Q4"
+        used_by: ["all"]
+        notes: "Library documentation"
+      - name: "Exa"
+        since: "2025-Q4"
+        used_by: ["all"]
+        notes: "Web search + research"
+    trial:
+      - name: "Browser (Puppeteer)"
+        since: "2025-Q4"
+        used_by: ["content-engine"]
+        notes: "Screenshot + automation"
+      - name: "Notion"
+        since: "2026-Q1"
+        used_by: ["kaizen"]
+        notes: "Knowledge management"
+    assess:
+      - name: "Magic (21st.dev)"
+        since: "2026-Q1"
+        notes: "Component builder"
+    hold: []
+
+  "Libraries/Frameworks":
+    adopt:
+      - name: "React + Vite"
+        since: "2025-Q3"
+        used_by: ["dashboard"]
+      - name: "TypeScript"
+        since: "2025-Q3"
+        used_by: ["all"]
+    trial: []
+    assess: []
+    hold: []
+
+  "AI Models":
+    adopt:
+      - name: "Claude Opus 4.6"
+        since: "2026-Q1"
+        used_by: ["all squads via Claude Code"]
+      - name: "Gemini 2.0 Flash"
+        since: "2025-Q4"
+        used_by: ["content-engine"]
+    trial:
+      - name: "Moonshot Kimi K2.5"
+        since: "2026-Q1"
+        used_by: ["openclaw"]
+        notes: "VPS agent model"
+    assess: []
+    hold: []

package/pro/squads/squad-creator/data/recommendation-tracker.yaml

@@ -0,0 +1,53 @@
+# migrated_from: squads/kaizen/data/recommendation-tracker.yaml | migration_story: STORY-108.3 | date: 2026-04-04
+# Recommendation Tracker — Kaizen Squad
+# Purpose: Rastrear implementação de recomendações ao longo do tempo
+# Updated by: wf-self-improve
+
+tracker:
+  last_updated: "2026-02-15"
+
+  reports:
+    week-07-2026-02-15:
+      recommendations:
+        - id: "W07-R1"
+          action: "Clonar minds YouTube (Paddy Galloway, Matt D'Avella, vidIQ)"
+          priority: "CRÍTICO"
+          status: "PENDENTE"
+          evidence_of_implementation: null
+          date_implemented: null
+
+        - id: "W07-R2"
+          action: "Atualizar squad-registry (lista 1 de 9 squads)"
+          priority: "ALTO"
+          status: "PENDENTE"
+          evidence_of_implementation: null
+          date_implemented: null
+
+        - id: "W07-R3"
+          action: "Avaliar fusão copy → content-engine"
+          priority: "RECOMENDADO"
+          status: "PENDENTE"
+          evidence_of_implementation: null
+          date_implemented: null
+
+        - id: "W07-R4"
+          action: "Adicionar Whisper API e YouTube Data API ao radar"
+          priority: "SUGERIDO"
+          status: "PENDENTE"
+          evidence_of_implementation: null
+          date_implemented: null
+
+        - id: "W07-R5"
+          action: "Reusar George Blackman mind (content-engine → youtube-scripts)"
+          priority: "SUGERIDO"
+          status: "PENDENTE"
+          evidence_of_implementation: null
+          date_implemented: null
+
+      summary:
+        total: 5
+        implemented: 0
+        partial: 0
+        pending: 5
+        ignored: 0
+        rate: "0% (primeiro ciclo, esperado)"