@atlashub/smartstack-cli 3.39.0 → 3.40.0

package/templates/skills/business-analyse/steps/step-04b-analyze.md

@@ -1,163 +1,163 @@
----
-name: step-04b-analyze
-description: Analyze permission coherence, semantic validation, E2E flows, and global risks
-model: opus
-next_step: steps/step-04c-decide.md
----
-
-> **Context files:** `_shared.md`
-
-# Step 4b: Analyze - Permission Coherence & Validation
-
-## MANDATORY EXECUTION RULES
-- ALWAYS validate permission coherence across modules
-- ALWAYS execute semantic validation checks
-- E2E flows are OPTIONAL (informational only)
-
-## YOUR TASK
-Validate permission coherence, execute semantic checks, identify E2E business flows, and assess global application risks.
-
----
-
-## EXECUTION SEQUENCE
-
-### 3. Permission Coherence
-
-> **Reference:** Load `references/analysis-semantic-checks.md` § "Permission Coherence Checks" for complete validation logic.
-
-**All modules MUST use the same application-level roles.**
-
-Execute these checks:
-
-**3a. Role Consistency** — Verify all modules use the applicationRoles defined in cadrage
-
-**3b. Permission Path Format** — Verify paths follow 3-segment (module-level) or 4-segment (section-level) patterns
-
-**3c. Role Hierarchy Coherence** — Verify: Admin ⊃ Manager ⊃ Contributor ⊃ Viewer
-
-**3d. Permission Conflicts** — Detect conflicts (e.g., Manager can approve in Orders but not Invoices)
-- Present conflicts to user via AskUserQuestion for intentionality confirmation
-
-**3e. Permission-Role Coherence Across Modules (WARNING)** — For each role, verify permission PATTERN is consistent across ALL modules
-- Some permission differences may be intentional (store as WARNING, not ERROR)
-
-### 4. Semantic Validation (MANDATORY)
-
-> **Reference:** Load `references/analysis-semantic-checks.md` for complete semantic check definitions and blocking rules.
-
-For EACH module feature.json, execute 13 checks:
-- Permission orpheline (WARNING)
-- UC sans FR (WARNING)
-- Entity sans endpoint (WARNING)
-- UC sans scenario (WARNING)
-- Role sans permissions (WARNING)
-- Navigation sans traduction (ERROR)
-- LifeCycle terminal (WARNING)
-- Schema conformity (ERROR)
-- Wireframe coverage (ERROR)
-- Doublon entity (ERROR)
-- Permission fantome (ERROR)
-- Dashboard coverage (WARNING)
-- Permission-UC alignment (WARNING)
-
-Store results in consolidation.semanticChecks[] with format: {check, module, status, details, autoFixed}
-
-**Blocking rule:**
-- 0 ERROR → PASS
-- ≥1 ERROR → BLOCK (fix before handoff, ask user for each)
-- WARNING only → PASS with user notification
-
-### 4-bis. Structural Schema Conformity Check (MANDATORY)
-
-> **Post-generation validation.** After semantic checks, verify ALL module feature.json files conform to JSON schema.
-
-See [references/consolidation-structural-checks.md](../references/consolidation-structural-checks.md) for the full 6-category structural check:
-- **A.** Required Sections Presence (18 sections)
-- **B.** Field Name Conformity (forbidden vs correct fields)
-- **C.** ID Pattern Conformity (BR, UC, FR, Permissions)
-- **D.** Cross-Module ID Uniqueness
-- **E.** Wireframe Layout Completeness
-- **F.** SeedDataCore Translation Coverage
-
-**Blocking rule:** 0 ERROR → PASS. ≥1 ERROR → BLOCK (attempt auto-fix, re-write, re-check).
-
-### 5. End-to-End Flows
-
-> **Reference:** Load `references/analysis-semantic-checks.md` § "E2E Flow Template" for the complete format.
-
-Identify business processes that span multiple modules:
-- Build flow with module → action → permission chain
-- List actors involved and their roles
-- Map data flow (entities referenced across modules)
-- Display as diagrams for user understanding
-
-### 6. Global Risk Assessment
-
-> **Reference:** Load `references/analysis-semantic-checks.md` § "Global Risk Assessment Metrics" for complete evaluation.
-
-Evaluate application-level risks using these metrics:
-- Total entities (≤20)
-- Total BRs (≤50)
-- Cross-module dependencies (≤10)
-- Shared entities (≤5)
-- E2E flow length (≤8 steps max)
-- Permission paths (≤100)
-
-### 7. Consolidation Summary
-
-Display comprehensive summary:
-```
-═══════════════════════════════════════════════════════════
-  CONSOLIDATION - {application_name}
-═══════════════════════════════════════════════════════════
-
-### Modules ({count})
-| Module | Entités | BRs | UCs | Complexité |
-|--------|---------|-----|-----|------------|
-{for each module}
-
-### Interactions Cross-Module
-- FK References: {count}
-- Shared Entities: {count}
-- Events: {count}
-- Shared Data: {count}
-
-### Permissions
-- Roles: {count} (coherent: ✓/✗)
-- Total paths: {count}
-- Conflicts resolved: {count}
-
-### E2E Flows
-{for each flow: name, modules involved, actors}
-
-### Risques Globaux
-{risk assessment table}
-
-═══════════════════════════════════════════════════════════
-```
-
----
-
-## SINGLE-MODULE MODE
-
-When only 1 module:
-1. Skip permission coherence check (only one module)
-2. Skip E2E flows (single module)
-3. Execute semantic validation (still required)
-4. Auto-approve global risks (no cross-module complexity)
-
----
-
-## CONTEXT MANAGEMENT
-
-| Loaded | Not Loaded |
-|--------|------------|
-| _shared.md | Full module feature.json files |
-| Module summaries | Questionnaires |
-| consolidation section (from step-04a) | Templates |
-
----
-
-## NEXT STEP
-
-Load: `./step-04c-decide.md`
+---
+name: step-04b-analyze
+description: Analyze permission coherence, semantic validation, E2E flows, and global risks
+model: opus
+next_step: steps/step-04c-decide.md
+---
+
+> **Context files:** `_shared.md`
+
+# Step 4b: Analyze - Permission Coherence & Validation
+
+## MANDATORY EXECUTION RULES
+- ALWAYS validate permission coherence across modules
+- ALWAYS execute semantic validation checks
+- E2E flows are OPTIONAL (informational only)
+
+## YOUR TASK
+Validate permission coherence, execute semantic checks, identify E2E business flows, and assess global application risks.
+
+---
+
+## EXECUTION SEQUENCE
+
+### 3. Permission Coherence
+
+> **Reference:** Load `references/analysis-semantic-checks.md` § "Permission Coherence Checks" for complete validation logic.
+
+**All modules MUST use the same application-level roles.**
+
+Execute these checks:
+
+**3a. Role Consistency** — Verify all modules use the applicationRoles defined in cadrage
+
+**3b. Permission Path Format** — Verify paths follow 3-segment (module-level) or 4-segment (section-level) patterns
+
+**3c. Role Hierarchy Coherence** — Verify: Admin ⊃ Manager ⊃ Contributor ⊃ Viewer
+
+**3d. Permission Conflicts** — Detect conflicts (e.g., Manager can approve in Orders but not Invoices)
+- Present conflicts to user via AskUserQuestion for intentionality confirmation
+
+**3e. Permission-Role Coherence Across Modules (WARNING)** — For each role, verify permission PATTERN is consistent across ALL modules
+- Some permission differences may be intentional (store as WARNING, not ERROR)
+
+### 4. Semantic Validation (MANDATORY)
+
+> **Reference:** Load `references/analysis-semantic-checks.md` for complete semantic check definitions and blocking rules.
+
+For EACH module feature.json, execute 13 checks:
+- Permission orpheline (WARNING)
+- UC sans FR (WARNING)
+- Entity sans endpoint (WARNING)
+- UC sans scenario (WARNING)
+- Role sans permissions (WARNING)
+- Navigation sans traduction (ERROR)
+- LifeCycle terminal (WARNING)
+- Schema conformity (ERROR)
+- Wireframe coverage (ERROR)
+- Doublon entity (ERROR)
+- Permission fantome (ERROR)
+- Dashboard coverage (WARNING)
+- Permission-UC alignment (WARNING)
+
+Store results in consolidation.semanticChecks[] with format: {check, module, status, details, autoFixed}
+
+**Blocking rule:**
+- 0 ERROR → PASS
+- ≥1 ERROR → BLOCK (fix before handoff, ask user for each)
+- WARNING only → PASS with user notification
+
+### 4-bis. Structural Schema Conformity Check (MANDATORY)
+
+> **Post-generation validation.** After semantic checks, verify ALL module feature.json files conform to JSON schema.
+
+See [references/consolidation-structural-checks.md](../references/consolidation-structural-checks.md) for the full 6-category structural check:
+- **A.** Required Sections Presence (18 sections)
+- **B.** Field Name Conformity (forbidden vs correct fields)
+- **C.** ID Pattern Conformity (BR, UC, FR, Permissions)
+- **D.** Cross-Module ID Uniqueness
+- **E.** Wireframe Layout Completeness
+- **F.** SeedDataCore Translation Coverage
+
+**Blocking rule:** 0 ERROR → PASS. ≥1 ERROR → BLOCK (attempt auto-fix, re-write, re-check).
+
+### 5. End-to-End Flows
+
+> **Reference:** Load `references/analysis-semantic-checks.md` § "E2E Flow Template" for the complete format.
+
+Identify business processes that span multiple modules:
+- Build flow with module → action → permission chain
+- List actors involved and their roles
+- Map data flow (entities referenced across modules)
+- Display as diagrams for user understanding
+
+### 6. Global Risk Assessment
+
+> **Reference:** Load `references/analysis-semantic-checks.md` § "Global Risk Assessment Metrics" for complete evaluation.
+
+Evaluate application-level risks using these metrics:
+- Total entities (≤20)
+- Total BRs (≤50)
+- Cross-module dependencies (≤10)
+- Shared entities (≤5)
+- E2E flow length (≤8 steps max)
+- Permission paths (≤100)
+
+### 7. Consolidation Summary
+
+Display comprehensive summary:
+```
+═══════════════════════════════════════════════════════════
+  CONSOLIDATION - {application_name}
+═══════════════════════════════════════════════════════════
+
+### Modules ({count})
+| Module | Entités | BRs | UCs | Complexité |
+|--------|---------|-----|-----|------------|
+{for each module}
+
+### Interactions Cross-Module
+- FK References: {count}
+- Shared Entities: {count}
+- Events: {count}
+- Shared Data: {count}
+
+### Permissions
+- Roles: {count} (coherent: ✓/✗)
+- Total paths: {count}
+- Conflicts resolved: {count}
+
+### E2E Flows
+{for each flow: name, modules involved, actors}
+
+### Risques Globaux
+{risk assessment table}
+
+═══════════════════════════════════════════════════════════
+```
+
+---
+
+## SINGLE-MODULE MODE
+
+When only 1 module:
+1. Skip permission coherence check (only one module)
+2. Skip E2E flows (single module)
+3. Execute semantic validation (still required)
+4. Auto-approve global risks (no cross-module complexity)
+
+---
+
+## CONTEXT MANAGEMENT
+
+| Loaded | Not Loaded |
+|--------|------------|
+| _shared.md | Full module feature.json files |
+| Module summaries | Questionnaires |
+| consolidation section (from step-04a) | Templates |
+
+---
+
+## NEXT STEP
+
+Load: `./step-04c-decide.md`