@atlashub/smartstack-cli 3.4.0 → 3.5.0

package/templates/skills/business-analyse/steps/step-01-cadrage.md

@@ -60,22 +60,14 @@ IF mcp_available:
   Store findings in {codebase_context}
 ```
 
-**Phase 2b: Parallel Agents (unless economy_mode)**
+**Phase 2b: Parallel Codebase Agents**
 ```
-IF NOT economy_mode:
-  Launch 3 agents in parallel:
-    Agent 1: Search for existing domain entities (Glob: **/Domain/**/*.cs)
-    Agent 2: Search for existing services/integrations (Grep: IService, IRepository)
-    Agent 3: Search for existing page patterns (Glob: **/pages/business/**/*.tsx)
+Launch 3 agents in parallel:
+  Agent 1: Search for existing domain entities (Glob: **/Domain/**/*.cs)
+  Agent 2: Search for existing services/integrations (Grep: IService, IRepository)
+  Agent 3: Search for existing page patterns (Glob: **/pages/business/**/*.tsx)
 
-  Merge findings into {codebase_context}
-```
-
-**Phase 2c: Economy Mode**
-```
-IF economy_mode:
-  Use Glob/Grep directly (no subagents)
-  Quick scan of Domain/, Application/, pages/ directories
+Merge findings into {codebase_context}
 ```
 
 ### 3. Application-Level Questionnaire (application mode)

package/templates/skills/business-analyse/steps/step-05b-deploy.md

@@ -78,6 +78,49 @@ prd.json generated for module {moduleCode}:
 - prd.json version: "2.0.0"
 - source.type: "ba-handoff-programmatic"
 
+**POST-CHECK (BLOCKING — DO NOT SKIP):**
+
+After `ss derive-prd` execution, read the generated prd-{moduleCode}.json and verify structural integrity:
+
+```javascript
+const prd = readJSON(`.ralph/prd-${moduleCode}.json`);
+const featureHandoff = moduleFeature.handoff.filesToCreate;
+
+// 1. Verify structure: filesToCreate MUST be under implementation (NOT root level)
+if (prd.filesToCreate && !prd.implementation?.filesToCreate) {
+  BLOCKING_ERROR("prd.json has filesToCreate at ROOT level — this is NOT from ss derive-prd");
+  BLOCKING_ERROR("Re-run: ss derive-prd --feature {path} --output .ralph/prd-{moduleCode}.json");
+  STOP;
+}
+
+// 2. Verify ALL 7 categories present and match feature.json
+const categories = ['domain', 'application', 'infrastructure', 'api', 'frontend', 'seedData', 'tests'];
+for (const cat of categories) {
+  const prdCount = prd.implementation.filesToCreate[cat]?.length ?? 0;
+  const featureCount = featureHandoff[cat]?.length ?? 0;
+  if (prdCount !== featureCount) {
+    BLOCKING_ERROR(`${cat}: prd has ${prdCount} files but feature.json has ${featureCount}`);
+  }
+}
+```
+
+Display verification table:
+
+```
+POST-CHECK: prd-{moduleCode}.json integrity
+| Category       | feature.json | prd.json | Match |
+|----------------|-------------|----------|-------|
+| domain         | {n}         | {n}      | OK/FAIL |
+| application    | {n}         | {n}      | OK/FAIL |
+| infrastructure | {n}         | {n}      | OK/FAIL |
+| api            | {n}         | {n}      | OK/FAIL |
+| frontend       | {n}         | {n}      | OK/FAIL |
+| seedData       | {n}         | {n}      | OK/FAIL |
+| tests          | {n}         | {n}      | OK/FAIL |
+```
+
+IF ANY category shows FAIL → **STOP AND RE-RUN `ss derive-prd`**. DO NOT proceed with incomplete PRD.
+
 ---
 
 ### 2. Initialize Progress Tracker
@@ -224,13 +267,15 @@ prd.json generated for module {moduleCode}:
 
 ---
 
-### 5. User Choice: Next Agent
+### 5. Completion Summary
+
+Display the completion summary after successful handoff:
 
-Present development options after successful handoff:
+> **Reference:** Read `templates/tpl-launch-displays.md` for user-facing display templates.
 
 ```
 ═══════════════════════════════════════════════════════════════
-  ✓ HANDOFF COMPLETE - {application_name}
+  [OK] BUSINESS ANALYSE TERMINEE - {application_name}
 ═══════════════════════════════════════════════════════════════
 
 Modules:   {count} ({names})
@@ -240,82 +285,37 @@ Tasks:     {total tasks} ({core_count} CORE + {biz_count} business + {dev_count}
 Complexity: {complexity}
 Effort:    {total_days} days ({total_hours} hours)
 
-Generated Artifacts:
-  ✓ feature.json (master + per-module) - enhanced with handoff section
-  ✓ .ralph/prd.json or .ralph/prd-{module}.json - derived from feature.json
-  ✓ .ralph/progress.txt - comprehensive task tracker
-  ✓ ba-interactive.html - client-facing interactive review document
-  ✓ Implementation strategy selected: {strategy}
-
-Next: Choose development approach
-═══════════════════════════════════════════════════════════════
-```
-
-Ask via AskUserQuestion:
-
-```
-question: "Quelle approche de développement souhaitez-vous utiliser ?"
-header: "Approche de développement"
-options:
-  - label: "Feature Full (Recommandé)"
-    description: "Génération parallèle rapide (code + tests). Couverture 70-80%. ~{hours/3} heures."
-  - label: "Ralph Loop"
-    description: "Développement itératif task-par-task avec cycle : Analyse → Dev (backend + tests unitaires + tests non-régression + frontend + tests + documentation) → Validation → Correction → Test ... jusqu'à 100% tests pass. Couverture 95-100%. ~{hours} heures."
-  - label: "Terminer le BA"
-    description: "Finir l'analyse, développement manuel par l'équipe."
-```
-
-**Recommendations by complexity:**
-- **Simple:** Feature Full (1-3 days) or Ralph Loop (2-4 days)
-- **Medium:** Ralph Loop recommended (5-10 days), Feature Full possible (3-6 days)
-- **Complex:** Ralph Loop strongly recommended (10-20 days), Feature Full (8-12 days)
-
----
-
-### 5-bis. Execute User Choice (Automatic Skill Launch)
-
-> Automatically launch the chosen development approach for seamless transition.
-
-**After receiving AskUserQuestion response:**
+[DIR] Artefacts generés:
+  ✓ feature.json (master + per-module) - spécification complète
+  ✓ .ralph/prd.json or .ralph/prd-{module}.json - task breakdown
+  ✓ .ralph/progress.txt - tracker de progression
+  ✓ ba-interactive.html - document de revue interactif
 
-> **Reference:** Read `templates/tpl-launch-displays.md` for user-facing display templates.
+[TARGET] Prochaines étapes:
+  1. Ouvrir ba-interactive.html dans le navigateur
+  2. Partager avec les stakeholders pour validation
+  3. Si retours --> relancer /business-analyse pour une nouvelle itération
+  4. Une fois validé, lancer le développement:
 
-**Implementation:**
+     /ralph-loop -r
 
-```javascript
-const choice = userAnswer; // "Feature Full (Recommandé)" | "Ralph Loop" | "Terminer le BA"
-const choiceLabel = choice.replace(/\s*\(.*?\)\s*$/g, '').trim();
-
-if (choiceLabel === "Ralph Loop") {
-  // Display: Ralph Loop explanation and configuration (from tpl-launch-displays.md)
-  // Then launch: Skill({ skill: "ralph-loop" });
-  // EXIT - ralph-loop takes over
-
-} else if (choiceLabel === "Feature Full") {
-  // Display: Feature Full configuration summary (from tpl-launch-displays.md)
-  // Then launch: Skill({ skill: "feature-full" });
-  // EXIT
-
-} else {
-  // Display: BA completion summary and next steps (from tpl-launch-displays.md)
-  // EXIT gracefully
-}
+═══════════════════════════════════════════════════════════════
 ```
 
-**Error handling:** If Skill() call fails, display manual launch instructions (see tpl-launch-displays.md).
+**No AskUserQuestion here.** The BA ends after displaying the summary. The user will manually launch `/ralph-loop -r` when ready (typically after stakeholder validation).
 
 ---
 
 ## SELF-VERIFICATION (FINAL)
 
-Before presenting user choice, VERIFY:
+Before presenting completion summary, VERIFY:
 
 1. **`.ralph/prd-{module}.json`** exists for ALL modules (file size > 100 bytes each)
 2. **`.ralph/progress.txt`** exists (file size > 500 bytes)
 3. **`ba-interactive.html`** exists at `docs/business/{app}/business-analyse/v{version}/` and file size > 100KB (pre-populated, not empty template)
 4. **`docs/business/index.json`** exists with correct entry count (1 app + N modules)
 
-**IF any check fails → GENERATE the missing artifact before presenting user choice.**
+**IF any check fails → GENERATE the missing artifact before presenting completion summary.**
 
 ---
 
@@ -337,7 +337,7 @@ Simplified handoff with minimal scope:
 - 3 core SeedData entries (omit some optional ones)
 - Basic prd.json with simplified sections
 - Lightweight progress.txt
-- Auto-suggest Feature Full for rapid development
+- Display `/ralph-loop -r` command for later use
 
 ### Delta Mode (use_case = refactoring)
 
@@ -381,10 +381,7 @@ Also generates working files and updates the manifest:
   - Effort estimates per module
   - Cross-module integration tasks (if multi-module)
 
-Next agent selection via user question:
-1. **Feature Full** - Parallel rapid code generation (70-80% coverage)
-2. **Ralph Loop** - Sequential task-driven development (95-100% coverage)
-3. **End BA** - Manual development by team
+Completion: Display summary with `/ralph-loop -r` command for later execution after stakeholder validation.
 
 ---
 
@@ -471,7 +468,6 @@ Before presenting handoff to user:
 | progress.txt incomplete | Ensure all 5 CORE SeedData entries are present per module. Check topological order. |
 | ba-interactive.html deployment failed | Verify output directory exists. Check file permissions. Ensure HTML template is readable. |
 | BA manifest not found | Create docs/business/index.json if missing. Use schema provided in section 4. |
-| User choice question failed | Catch AskUserQuestion error and display manual instructions for skill launch. |
 | HTML pre-populated but empty | Verify FEATURE_DATA and EMBEDDED_ARTIFACTS objects are serialized correctly. Check JSON syntax. |
 
 ---

package/templates/skills/business-analyse/templates/tpl-handoff.md

@@ -12,23 +12,18 @@
 > **Version:** {version}
 > **Validated Specs:** feature.json (validation.decision = APPROVED)
 > **Source:** `docs/business/{app}/{module}/business-analyse/v{version}/feature.json`
-> **Implementation:** `/ralph-loop -r` (iterative) | `/feature-full business/{app}/{module}` (one-shot)
+> **Implementation:** `/ralph-loop -r`
 
 ## DEVELOPER INSTRUCTIONS
 
 This document is a self-contained prompt for Claude Code.
 
-**Option 1 - Iterative (recommended):**
+**Lancement:**
 ```
 /ralph-loop -r
 ```
 > Pre-generated `.ralph/prd.json` with atomic task breakdown.
 
-**Option 2 - One-shot:**
-```
-/feature-full business/{app}/{module}
-```
-
 ---
 
 ## 1. QUICK CONTEXT
@@ -52,8 +47,8 @@ BACKEND:
 - src/{project_namespace}.Domain/Business/ -> Entity structure + folder hierarchy
 - src/{project_namespace}.Application/Business/ -> DTOs + service interfaces
 - src/{project_namespace}.Application/Common/Interfaces/ -> Service contracts
-- src/{project_namespace}.Infrastructure/Persistence/Configurations/ -> EF Core configs (subfolder per module)
-- src/{project_namespace}.Infrastructure/Services/ -> Service implementations (subfolder per module)
+- src/{project_namespace}.Infrastructure/Persistence/Configurations/ -> EF Core configs (subfolder per context/app/module)
+- src/{project_namespace}.Infrastructure/Services/ -> Service implementations (subfolder per context/app/module)
 - src/{project_namespace}.Infrastructure/Persistence/Seeding/Data/ -> SeedData patterns
 
 SEED DATA (CRITICAL):
@@ -81,8 +76,8 @@ FRONTEND:
 | DTOs | `Application/Business/{Application}/{Module}/DTOs/{Entity}Dto.cs` | Response, Create, Update records |
 | Mapping | `Application/Business/{Application}/{Module}/DTOs/{Entity}MappingExtensions.cs` | Entity <-> DTO mapping |
 | Permission Constants | `Application/Business/{Application}/{Module}/Permissions.cs` | Compile-time constants |
-| EF Configuration | `Infrastructure/Persistence/Configurations/{Module}/{Entity}Configuration.cs` | Table + indexes + HasData |
-| Service Implementation | `Infrastructure/Services/{Module}/{Entity}Service.cs` | Business logic |
+| EF Configuration | `Infrastructure/Persistence/Configurations/{Context}/{Application}/{Module}/{Entity}Configuration.cs` | Table + indexes + HasData |
+| Service Implementation | `Infrastructure/Services/{Context}/{Application}/{Module}/{Entity}Service.cs` | Business logic |
 | Controller | `Api/Controllers/Business/{Application}/{Module}Controller.cs` | NavRoute + RequirePermission |
 
 ### 3.2 SeedData Core (CRITICAL -- without these, module is invisible and returns 403)
@@ -161,8 +156,8 @@ From: `feature.specification.seedDataCore` (5 core files), `feature.specificatio
 **Folder Conventions:**
 - [ ] Domain entities in `Domain/Business/{Application}/{Module}/`
 - [ ] Application DTOs in `Application/Business/{Application}/{Module}/DTOs/`
-- [ ] Infrastructure configs in `Configurations/{Module}/`
-- [ ] Infrastructure services in `Services/{Module}/`
+- [ ] Infrastructure configs in `Configurations/{Context}/{Application}/{Module}/`
+- [ ] Infrastructure services in `Services/{Context}/{Application}/{Module}/`
 - [ ] Controller in `Controllers/Business/{Application}/`
 
 **SeedData Core (CRITICAL):**
@@ -181,13 +176,8 @@ From: `feature.specification.seedDataCore` (5 core files), `feature.specificatio
 
 ## EXECUTION
 
-**Iterative (recommended):**
+**Lancement:**
 ```bash
 /ralph-loop -r
 ```
-
-**One-shot:**
-```bash
-/feature-full business/{app}/{module}
-```
 ```

package/templates/skills/business-analyse/templates/tpl-launch-displays.md

@@ -1,158 +1,53 @@
 # Skill Launch Display Templates (templates/tpl-launch-displays.md)
 
-> **Used by:** step-05b-deploy (section 5-bis: Execute User Choice)
-> **Purpose:** User-facing display templates for development approach choices
+> **Used by:** step-05b-deploy (section 5: Completion Summary)
+> **Purpose:** User-facing display templates for BA completion
 > **Note:** No emojis - uses text markers per Claude Code conventions
 
 ---
 
-## 1. Ralph Loop Launch Display
+## 1. BA Completion Display
 
-Display when user selects "Ralph Loop" development approach:
+Display at the end of the business analysis:
 
 ```
-[LAUNCH] Lancement de Ralph Loop - Développement itératif automatique
-
-╔══════════════════════════════════════════════════════════════╗
-║  CYCLE RALPH LOOP - Comment ça fonctionne ?                 ║
-╠══════════════════════════════════════════════════════════════╣
-║                                                              ║
-║  Ralph Loop exécute un cycle itératif jusqu'à 100% tests:   ║
-║                                                              ║
-║  1. ANALYSE      --> Charger task suivante du prd.json       ║
-║  2. DÉVELOPPEMENT --> Générer le code demandé                ║
-║     • Backend (Entities, Services, Controllers, Repos)      ║
-║     • Tests unitaires (xUnit) + non-régression              ║
-║     • Frontend (Pages, Components, Hooks)                   ║
-║     • Tests frontend (React Testing Library)                ║
-║     • SeedData (Core RBAC + business data)                  ║
-║     • Documentation utilisateur (inline + tooltips)         ║
-║  3. VALIDATION   --> Commit + MCP conventions check           ║
-║  4. TEST         --> Exécuter dotnet test + npm test          ║
-║  5. CORRECTION   --> Si échec, analyser et corriger           ║
-║  6. BOUCLE       --> Répéter 4-5 jusqu'à 100% tests pass      ║
-║  7. NEXT TASK    --> Passer à la task suivante (retour à 1)  ║
-║                                                              ║
-║  [TARGET] Objectif: ZÉRO ERREUR avant de passer à la task suivante║
-║  [STATS] Couverture: 95-100% (tests générés automatiquement)     ║
-║                                                              ║
-╚══════════════════════════════════════════════════════════════╝
-
-   Configuration du projet:
-   ┌────────────────────────────────────────────────────────────┐
-   │ Modules:   {modules_list}
-   │ Stratégie: {implementation_strategy}
-   │ PRD:       {prd_file_path}
-   │ Progress:  .ralph/progress.txt
-   │ Ordre:     {module_order}
-   │ └────────────────────────────────────────────────────────────┘
-
-   Modules à traiter (dans l'ordre):
-   {modules_numbered_list}
-
-   [DIR] Fichiers générés par le BA (inputs pour Ralph):
-   ├─ feature.json (master + modules) --> Spécification source
-   ├─ prd.json (ou prd-{module}.json) --> Task breakdown avec UC/FR/BR
-   ├─ progress.txt                    --> Tracker hiérarchique (module --> layer --> tasks)
-   └─ ba-interactive.html             --> Revue client (mockups, wireframes)
-
-   [LOOP] Ralph Loop va maintenant:
-   1. Détecter les prd-*.json par module (si multi-module)
-   2. Créer modules-queue.json avec l'ordre de traitement
-   3. Traiter module par module dans l'ordre topologique
-   4. Pour chaque module: parcourir les tasks (domain --> seeddata --> application --> infrastructure --> api --> frontend --> i18n --> tests)
-   5. Pour chaque task: générer code --> commit --> tests --> correction si échec --> re-test --> next task
-   6. Passer au module suivant quand 100% tasks du module actuel = completed
-   7. Générer rapport final avec métriques de couverture
-
 ═══════════════════════════════════════════════════════════════
-
---> Transition vers Ralph Loop...
-```
-
----
-
-## 2. Feature Full Launch Display
-
-Display when user selects "Feature Full" development approach:
-
-```
-[LAUNCH] Lancement de Feature Full...
-
-   Configuration:
-   - Mode: Parallel generation
-   - Couverture: 70-80%
-   - Durée estimée: ~{estimated_hours} heures
-
+  [OK] BUSINESS ANALYSE TERMINEE - {application_name}
 ═══════════════════════════════════════════════════════════════
-```
 
----
-
-## 3. Manual Development Complete Display
-
-Display when user selects "Terminer le BA" (end Business Analysis):
-
-```
-[OK] Business Analysis terminée.
-
-   Les équipes peuvent commencer le développement manuel.
-   Tous les artefacts sont prêts pour l'implémentation.
+Modules:   {count} ({names})
+Strategy:  {strategy}
+Files:     {total files across all modules}
+Tasks:     {total tasks} ({core_count} CORE + {biz_count} business + {dev_count} development)
+Complexity: {complexity}
+Effort:    {total_days} days ({total_hours} hours)
 
-[DIR] Fichiers générés:
-   - feature.json (master + modules) - Spécification complète
-   - .ralph/prd.json (ou prd-{module}.json) - Task breakdown
-   - .ralph/progress.txt - Tracker de progression
-   - ba-interactive.html - Document de revue client
+[DIR] Artefacts générés:
+  ✓ feature.json (master + per-module) - spécification complète
+  ✓ .ralph/prd.json or .ralph/prd-{module}.json - task breakdown
+  ✓ .ralph/progress.txt - tracker de progression
+  ✓ ba-interactive.html - document de revue interactif
 
-[STATS] Métriques:
-   - Modules: {modules_count}
-   - Entités: {total_entities}
-   - Use cases: {total_use_cases}
-   - Business rules: {total_business_rules}
-   - Fichiers à créer: {total_files}
+[TARGET] Prochaines étapes:
+  1. Ouvrir ba-interactive.html dans le navigateur
+  2. Partager avec les stakeholders pour validation
+  3. Si retours --> relancer /business-analyse pour une nouvelle itération
+  4. Une fois validé, lancer le développement:
 
-[TARGET] Prochaines étapes recommandées:
-   1. Ouvrir ba-interactive.html dans le navigateur
-   2. Partager avec les stakeholders pour validation finale
-   3. Utiliser progress.txt comme guide de développement
-   4. Implémenter module par module selon l'ordre topologique
-
-[TIP] Pour lancer le développement assisté plus tard:
-   - Ralph Loop: /ralph-loop (détecte automatiquement .ralph/prd.json)
-   - Feature Full: /feature-full
+     /ralph-loop -r
 
 ═══════════════════════════════════════════════════════════════
 ```
 
 ---
 
-## 4. Error Handling Display
-
-Display when skill launch fails:
-
-```
-[!] Échec du lancement automatique de Ralph Loop
-
-   Veuillez lancer manuellement:
-   /ralph-loop
-
-   Si le problème persiste:
-   1. Vérifier que la skill ralph-loop est installée
-   2. Vérifier les permissions Claude Code
-   3. Consulter les logs: .ralph/logs/
-```
-
----
-
 ## Text Marker Legend
 
 | Marker | Replaces | Usage |
 |--------|----------|-------|
-| `-->` | `➡️` or `→` | Directional flow, transitions |
+| `-->` | `->` or `→` | Directional flow, transitions |
 | `[OK]` | `✅` | Success, completion |
 | `[!]` | `⚠️` | Warning, caution |
-| `[LAUNCH]` | `🚀` | Skill launch, startup |
 | `[DIR]` | `📂` | Files, directories, structure |
 | `[STATS]` | `📊` | Metrics, statistics, coverage |
 | `[TIP]` | `💡` | Advice, suggestions |

package/templates/skills/business-analyse/templates-frd.md

@@ -353,23 +353,18 @@ Feature: {FEAT-XXX} {Feature Name}
 > **Module:** business/{application}/{module}
 > **Version:** 1.0
 > **Validated Specs:** Specification v1.0 (validation.json)
-> **Implementation:** `/ralph-loop -r` (iterative) | `/feature-full business/{app}/{module}` (one-shot)
+> **Implementation:** `/ralph-loop -r`
 
 ## DEVELOPER INSTRUCTIONS
 
 This document is a self-contained prompt for Claude Code.
 
-**Option 1 - Iterative (recommended):**
+**Lancement:**
 ```
 /ralph-loop -r
 ```
 > Pre-generated `.ralph/prd.json` with atomic task breakdown.
 
-**Option 2 - One-shot:**
-```
-/feature-full business/{app}/{module}
-```
-
 ---
 
 ## 1. QUICK CONTEXT
@@ -462,21 +457,10 @@ FRONTEND:
 
 ## EXECUTION
 
-**Iterative (recommended):**
+**Lancement:**
 ```bash
 /ralph-loop -r
 ```
-
-**One-shot:**
-```bash
-/feature-full business/{app}/{module}
-```
-
-Options (one-shot only):
-- `--phase=1` : Backend only
-- `--phase=2` : Frontend only
-- `--phase=3` : Tests only
-- `--phase=4` : Documentation only
 ```
 
 ---