@atlashub/smartstack-cli 3.12.0 → 3.14.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@atlashub/smartstack-cli",
-  "version": "3.12.0",
+  "version": "3.14.0",
   "description": "SmartStack Claude Code automation toolkit - GitFlow, EF Core migrations, prompts and more",
   "author": {
     "name": "SmartStack",
@@ -80,7 +80,7 @@
     "test:all": "npm run test:mcp && npm run test:ba"
   },
   "dependencies": {
-    "@atlashub/smartstack-cli": "file:../02-Develop",
+    "@atlashub/smartstack-cli": "file:",
     "@modelcontextprotocol/sdk": "^1.0.0",
     "axios": "^1.7.0",
     "bcryptjs": "^2.4.3",

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

@@ -180,7 +180,7 @@ When step-00 detects that the description matches an existing application:
 | `{module_name}`         | string  | Target module name                                     |
 | `{context}`             | string  | Always "business" for BA                               |
 | `{workflow_mode}`       | string  | "application" or "module"                              |
-| `{vibe_coding}`         | boolean | `true` if developer builds with AI assistance (accelerated questionnaire) |
+| `{analysisMode}`        | string  | Always "interactive" — analysis phase is always interactive with the user |
 | `{docs_dir}`            | string  | `docs/business/{app}/{module}/business-analyse/v{X.Y}/` |
 
 </state_variables>
@@ -199,7 +199,8 @@ When step-00 detects that the description matches an existing application:
 | 00   | `steps/step-00-init.md`           | Sonnet | Auto-detect new/update, scan existing, create master feature.json |
 | 01   | `steps/step-01-cadrage.md`        | Opus   | Framing: context, stakeholders, scope, application roles |
 | 02   | `steps/step-02-decomposition.md`  | Opus   | Module decomposition, dependency graph, client checkpoint |
-| 03a  | `steps/step-03a-data.md`          | Opus   | Per-module: sections, entities, BRs, questionnaires |
+| 03a1 | `steps/step-03a1-setup.md`        | Opus   | Per-module: setup, sections, questionnaires, cross-refs |
+| 03a2 | `steps/step-03a2-analysis.md`     | Opus   | Per-module: objectives, entities, BRs, process flow |
 | 03b  | `steps/step-03b-ui.md`            | Opus   | Per-module: state machines, wireframes, layouts, dashboards |
 | 03c  | `steps/step-03c-compile.md`       | Opus   | Per-module: actors, UCs, FRs, permissions, navigation, seedDataCore (7 arrays), i18n |
 | 03d  | `steps/step-03d-validate.md`      | Sonnet | Per-module: validation, write, incremental HTML, loop decision |

package/templates/skills/business-analyse/_module-loop.md

@@ -1,6 +1,6 @@
 # Business Analysis - Module Loop Protocol (_module-loop.md)
 
-> **Loaded by:** step-03a-data, step-03b-ui, step-03c-compile, step-03d-validate
+> **Loaded by:** step-03a1-setup, step-03b-ui, step-03c-compile, step-03d-validate
 > **Purpose:** State management and iteration logic for multi-module specification loop
 
 ---
@@ -31,10 +31,10 @@
      currentModule = moduleOrder[currentModuleIndex]
      Write master feature.json
      Display: "Module {name} complete. Next: {next_name} ({N}/{total})"
-     RE-LOAD: steps/step-03a-data.md
+     RE-LOAD: steps/step-03a1-setup.md
 4. ELSE:
      master.status = "specified"
-     Load: steps/step-04-consolidation.md
+     Load: steps/step-04a-collect.md
 ```
 
 ## Context Management During Loop
@@ -50,7 +50,7 @@ To prevent context explosion as modules accumulate:
 1. ba-reader.findApplicationFeature() -> locate master feature.json
 2. Read metadata.workflow.currentModuleIndex
 3. IF currentModule has a feature.json with status != "validated":
-     Resume step-03a-data for that module
+     Resume step-03a1-setup for that module
 4. ELSE:
-     Start step-03a-data for next module
+     Start step-03a1-setup for next module
 ```

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

@@ -1,7 +1,7 @@
 # Elicitation Questionnaire - Business Analysis
 
 > **Usage:** Structured questions for step-01-cadrage and step-03a-data
-> **Standard:** BABOK v3 - Elicitation Techniques (VibeCoding-focused)
+> **Standard:** BABOK v3 - Elicitation Techniques (Interactive analysis)
 > **Model:** OPUS with ULTRATHINK
 > **Total:** ~68 targeted questions (dev-relevant only)
 

package/templates/skills/business-analyse/references/cache-warming-strategy.md

@@ -132,9 +132,7 @@ for (const file of questionnaireFiles) {
 // (Questionnaires no longer needed)
 ```
 
-**Optimization:** Only load questionnaires that will be used based on `vibe_coding` flag:
-- If `vibe_coding = true`: Load only 00, 01, 02, 03, 14, 15 (core 6 files, ~31KB)
-- If `vibe_coding = false`: Load all 16 files (~56KB)
+**Optimization:** Cadrage uses targeted questionnaires (selected questions from 01-context, 02-stakeholders, 03-scope, 14-risks, 15-success) — not all questions are asked. Module-level questionnaires (04, 07, 11, 12, 13) are loaded on demand in step-03.
 
 ---
 
@@ -167,7 +165,7 @@ Total: ~12KB, 1 file
 ├── spec-auto-inference.md     (~8KB)
 ├── ui-resource-cards.md       (~6KB)
 ├── ui-dashboard-spec.md       (~5KB)
-└── cadrage-vibe-coding.md     (~4KB)
+└── cadrage-pre-analysis.md    (~4KB)
 
 Total: ~23KB, 4 files
 ```
@@ -189,7 +187,7 @@ const moduleRefs = [
   "spec-auto-inference.md",
   "ui-resource-cards.md",
   "ui-dashboard-spec.md",
-  "cadrage-vibe-coding.md"
+  "cadrage-pre-analysis.md"
 ];
 for (const file of moduleRefs) {
   read(`~/.claude/skills/business-analyse/references/${file}`);
@@ -254,15 +252,9 @@ const htmlTemplate = read("~/.claude/skills/business-analyse/html/ba-interactive
 // 1. Schemas (42KB, 9 files) - CRITICAL
 glob("schemas/**/*.json").forEach(f => read(f));
 
-// 2. Questionnaires (31-56KB, 6-16 files) - HIGH
-// Conditional on vibe_coding flag
-if (vibe_coding) {
-  ["00", "01", "02", "03", "14", "15"].forEach(n =>
-    read(`questionnaire/${n}-*.md`)
-  );
-} else {
-  glob("questionnaire/*.md").forEach(f => read(f));
-}
+// 2. Core questionnaires (01, 02, 03, 14, 15) - pre-loaded for cadrage
+// Cadrage uses targeted questions from these 5 core questionnaires
+// Module-level questionnaires (04, 07, 11, 12, 13) deferred to step-03
 
 // 3. Suggestion catalog (12KB, 1 file) - HIGH
 read("patterns/suggestion-catalog.md");
@@ -304,7 +296,7 @@ const moduleRefs = [
   "spec-auto-inference.md",
   "ui-resource-cards.md",
   "ui-dashboard-spec.md",
-  "cadrage-vibe-coding.md"
+  "cadrage-pre-analysis.md"
 ];
 moduleRefs.forEach(f => read(`references/${f}`));
 
@@ -455,7 +447,7 @@ Step-${currentStep} cache statistics:
 ```javascript
 // Step-00: Analyze feature_description to predict workflow
 const predictions = {
-  willNeedQuestionnaires: !vibe_coding,  // Full questionnaires if not vibe coding
+  willNeedQuestionnaires: false,  // Cadrage uses zero questions (auto-inferred)
   willBeMultiModule: detectMultiModuleKeywords(feature_description),  // "modules", "applications"
   estimatedModuleCount: estimateModuleCount(feature_description)  // 1-10
 };
@@ -466,13 +458,9 @@ if (predictions.willBeMultiModule && predictions.estimatedModuleCount > 3) {
   loadModuleReferences();
 }
 
-if (!predictions.willNeedQuestionnaires) {
-  // Vibe coding → only load 6 core questionnaires
-  loadCoreQuestionnaires();
-} else {
-  // Full analysis → load all 16 questionnaires
-  loadAllQuestionnaires();
-}
+// Interactive cadrage → load 5 core questionnaires (01, 02, 03, 14, 15)
+// Module-level questionnaires (04, 07, 11, 12, 13) loaded on demand in step-03
+loadCoreQuestionnaires();
 ```
 
 **Benefits:**

package/templates/skills/business-analyse/references/cadrage-pre-analysis.md

@@ -0,0 +1,112 @@
+# Cadrage: Pre-Analysis Reference
+
+> Reference for step-01-cadrage.md — silent pre-analysis to PREPARE the interactive conversation.
+> **This file does NOT replace the conversation — it prepares it.**
+
+## Purpose
+
+Before engaging the client, the AI silently analyzes the `{feature_description}` to:
+1. Understand what was said (extract explicit requirements)
+2. Detect what was NOT said (identify shadow zones to challenge)
+3. Prepare targeted questions (not generic ones)
+4. Pre-identify modules, sections, and resources
+
+**The output of this pre-analysis is INTERNAL ONLY.** It is never shown directly to the client — it feeds the reformulation (Phase 2) and challenge questions (Phase 3).
+
+## Pre-Analysis Rules
+
+### 1. Problem Type Inference
+
+Derive the problem type from `{feature_description}` keywords:
+
+```yaml
+problem_type:
+  → Keywords "remplacer", "migrer", "existant" → "replace" (existing tool to replace)
+  → Keywords "automatiser", "manuel", "processus" → "automate" (manual process to automate)
+  → Keywords "centraliser", "dispersees", "eparpillees" → "centralize" (data scattered across systems)
+  → Default (new tool) → "new_tool" (no system in place)
+```
+
+### 2. Explicit Module/Feature Extraction
+
+Extract functional areas explicitly mentioned in the description:
+
+```yaml
+detected_modules:
+  → For each distinct functional area mentioned:
+    - name: "{PascalCase module name}"
+    - description: "{what the user said about it}"
+    - detected_sections: ["{inferred sections based on description}"]
+    - detected_resources: ["{inferred resources}"]
+```
+
+### 3. Shadow Zone Detection (CRITICAL)
+
+> **Shadow zones are the most valuable output of pre-analysis.**
+> They become the challenge questions in Phase 3.
+
+For EACH detected module, check for missing information:
+
+| What to check | Shadow zone if missing | Challenge question pattern |
+|--------------|----------------------|--------------------------|
+| Stakeholders | Who uses this module? | "Who interacts with {module} daily? Only {mentioned role} or also managers, admins, external users?" |
+| Cardinality | Relationships stated as fact | "You said {A} is 1:1 with {B}. Can {A} exist without {B}? Can {B} have multiple {A}?" |
+| Granularity | Level of detail unclear | "What granularity for {feature}? Day, half-day, hour? Single entry or batch?" |
+| Reports | Mentioned but not detailed | "Which reports exactly? For whom? What format? How often?" |
+| Validation workflow | Actions without approval | "Does {action} require approval? Who validates? What happens if rejected?" |
+| Edge cases | Only happy path described | "What happens when {something goes wrong}? When data is incomplete? When two users do it simultaneously?" |
+| Non-functional | Security, performance, compliance | "Is there sensitive data (GDPR)? Expected concurrent users? Compliance requirements?" |
+| Integration | Standalone or connected | "Does {module} need to exchange data with external systems? Import? Export? API?" |
+
+### 4. Domain-Specific Anticipation Patterns
+
+When the problem domain is identified, pre-load domain-specific needs:
+
+| Domain keywords | Anticipated needs (suggest in Phase 4) |
+|----------------|---------------------------------------|
+| RH, employes, personnel | Contrats, competences, organigramme, RGPD, conges, jours feries, calendriers |
+| Temps, activites, absences | Granularite saisie, validation manageriale, soldes conges, compteurs, export paie |
+| Ventes, commandes, clients | Devis, factures, pipeline, relances, taux conversion, segments client |
+| Stock, inventaire, produits | Categories, fournisseurs, seuils reapprovisionnement, mouvements, valorisation |
+| Projets, taches, planning | Jalons, ressources, Gantt, charge, budget, risques projet |
+| Tickets, support, incidents | SLA, escalade, base connaissances, satisfaction, priorites |
+| Documents, GED | Versionning, workflows validation, templates, OCR, archivage legal |
+
+### 5. Section & Resource Pre-Identification
+
+For each detected module, anticipate sections (Level 4) and resources (Level 5) based on feature type:
+
+| Feature type | Standard sections | Standard resources per section |
+|-------------|------------------|------------------------------|
+| data-centric | list, detail, create, edit | {entity}-grid, {entity}-form, {entity}-card |
+| workflow | list, detail, create, edit, approve, history | {entity}-grid, {entity}-form, approval-panel, status-timeline |
+| reporting | dashboard, detail, export | summary-chart, kpi-cards, export-panel |
+| integration | list, detail, config, sync, logs | sync-status-grid, config-form, log-viewer |
+
+**Always check:** Does the user's description imply additional sections beyond the standard set? (e.g., "reports" → dashboard + export, "calendar view" → calendar section)
+
+## Output Format (Internal Only)
+
+```yaml
+pre_analysis:
+  problem_type: "new_tool|replace|automate|centralize"
+  detected_modules:
+    - name: "ModuleName"
+      description: "What the user said"
+      detected_sections: ["list", "detail", "create"]
+      detected_resources: ["entity-grid", "entity-form"]
+  shadow_zones:
+    - topic: "Cardinality Employee-User"
+      why_it_matters: "1:1 assumption may not hold for temp workers"
+      challenge_question: "Can a user be linked to multiple employee records?"
+    - topic: "Report granularity"
+      why_it_matters: "Reports mentioned but not specified"
+      challenge_question: "Which reports exactly? For whom? What format?"
+  anticipated_suggestions:
+    - suggestion: "Leave balance management"
+      justification: "Time tracking without leave balances is incomplete"
+      module: "TimeTracking"
+    - suggestion: "GDPR compliance module"
+      justification: "HR data is personal data under GDPR"
+      module: "Employees"
+```

package/templates/skills/business-analyse/references/cadrage-structure-cards.md

@@ -63,11 +63,16 @@
   "category": "mustHave|shouldHave|couldHave|outOfScope|implicit",
   "module": "Users",
   "ucRef": "UC-UM-001",
-  "notes": "Foundation module, must be implemented first"
+  "notes": "Foundation module, must be implemented first",
+  "anticipatedSections": ["list", "detail", "create", "edit"],
+  "anticipatedResources": ["user-grid", "user-form", "user-card"]
 }
 ```
 **MANDATORY fields:** `item`, `category`, `module`
+**OPTIONAL fields:** `ucRef`, `notes`, `anticipatedSections`, `anticipatedResources`
 **category values:** `mustHave`, `shouldHave`, `couldHave`, `outOfScope`, `implicit` (camelCase)
+**anticipatedSections:** Array of section codes (Level 4) — e.g., `["list", "detail", "create", "edit", "dashboard", "export"]`
+**anticipatedResources:** Array of resource codes (Level 5) — e.g., `["user-grid", "user-form", "user-card"]`
 **FORBIDDEN fields:** Do NOT use `id`, `feature`, `priority`. Use `item` + `category`.
 
 ## codebaseContext

package/templates/skills/business-analyse/references/deploy-data-build.md

@@ -11,7 +11,7 @@ const FEATURE_DATA = {
     applicationId: master.feature_id,
     version: master.version,
     createdAt: ISO_TIMESTAMP,
-    vibeCoding: master.metadata.vibeCoding // "enabled" or "disabled" — controls UI section visibility
+    analysisMode: master.metadata.analysisMode || "interactive" // always "interactive" — analysis is always interactive
   },
   cadrage: {
     goal: master.cadrage.goal,

package/templates/skills/business-analyse/references/html-data-mapping.md

@@ -17,7 +17,7 @@ Build a JSON object following this **exact mapping** from feature.json to the HT
     version: master.version,                            // e.g. "1.0"
     createdAt: master.metadata.createdAt,
     lastModified: master.metadata.updatedAt,
-    vibeCoding: master.metadata.vibeCoding || false      // true if vibe coding mode
+    analysisMode: master.metadata.analysisMode || "interactive"  // always "interactive"
   },
   cadrage: {
     problem: {

package/templates/skills/business-analyse/references/robustness-checks.md

@@ -407,7 +407,7 @@ WHY: This will cause FK constraint violation in database
 HOW TO FIX:
   Option 1: Create "Task" entity in Projects module
   Option 2: Remove reference from TimeEntry (change taskId to projectId)
-WHERE: Return to step-03a-data.md for TimeTracking module
+WHERE: Return to step-03a1-setup.md for TimeTracking module
 ```
 
 ---

package/templates/skills/business-analyse/references/spec-auto-inference.md

@@ -1,6 +1,6 @@
 # Specification: Auto-Inference Rules
 
-> Reference for step-03a-data.md — convention/override depth auto-generation from entity definitions.
+> Reference for step-03a1-setup.md — convention/override depth auto-generation from entity definitions.
 
 ## Entity Attribute → SmartTable Column
 

package/templates/skills/business-analyse/schemas/application-schema.json

@@ -43,6 +43,11 @@
           "description": "Whether this is a new application or an update"
         },
         "mcpAvailable": { "type": "boolean" },
+        "analysisMode": {
+          "type": "string",
+          "const": "interactive",
+          "description": "Analysis mode — always interactive (AI listens, reformulates, challenges, validates)"
+        },
         "workflow": {
           "type": "object",
           "description": "Iterative module loop state",
@@ -173,7 +178,17 @@
               "category": { "type": "string", "enum": ["mustHave", "shouldHave", "couldHave", "outOfScope", "implicit"] },
               "module": { "type": ["string", "null"], "description": "Module code that covers this requirement (null if cross-cutting)" },
               "ucRef": { "type": ["string", "null"], "description": "UC ID if already assigned" },
-              "notes": { "type": "string" }
+              "notes": { "type": "string" },
+              "anticipatedSections": {
+                "type": "array",
+                "items": { "type": "string" },
+                "description": "Anticipated sections (Level 4) for this requirement — e.g., list, detail, create, edit, dashboard"
+              },
+              "anticipatedResources": {
+                "type": "array",
+                "items": { "type": "string" },
+                "description": "Anticipated resources (Level 5) for this requirement — e.g., user-grid, user-form, user-card"
+              }
             }
           }
         }
@@ -230,6 +245,23 @@
           "estimatedComplexity": {
             "type": "string",
             "enum": ["simple", "medium", "complex"]
+          },
+          "anticipatedSections": {
+            "type": "array",
+            "description": "Anticipated sections (Level 4) with their resources (Level 5), from cadrage coverage matrix",
+            "items": {
+              "type": "object",
+              "required": ["code"],
+              "properties": {
+                "code": { "type": "string", "description": "Section code (e.g., list, detail, create, edit, dashboard)" },
+                "description": { "type": "string" },
+                "resources": {
+                  "type": "array",
+                  "items": { "type": "string" },
+                  "description": "Anticipated resource codes for this section"
+                }
+              }
+            }
           }
         }
       }

package/templates/skills/business-analyse/schemas/sections/metadata-schema.json

@@ -24,7 +24,7 @@
         "permissionBase": { "type": "string", "description": "e.g., business.sales.orders" },
         "previousVersion": { "type": ["string", "null"] },
         "changeReason": { "type": ["string", "null"] },
-        "vibeCoding": { "type": "boolean", "default": false, "description": "True if project is built in vibe coding mode (developer + AI)" },
+        "analysisMode": { "type": "string", "const": "interactive", "description": "Analysis mode — always interactive (AI listens, reformulates, challenges, validates)" },
         "mcpAvailable": { "type": "boolean" },
         "scope": { "type": "string", "enum": ["application", "module"], "default": "module" },
         "applicationRef": { "type": ["string", "null"], "description": "Parent application feature ID (FEAT-XXX)" },

package/templates/skills/business-analyse/steps/step-00-init.md

@@ -9,6 +9,14 @@ next_step: steps/step-01-cadrage.md
 
 # Step 00: Initialize Business Analysis
 
+**Before anything else**, display the version banner:
+
+```
+═══════════════════════════════════════════════════════════════
+  SmartStack Business Analyse — v{{SMARTSTACK_VERSION}}
+═══════════════════════════════════════════════════════════════
+```
+
 Initialize the business analysis workflow by auto-detecting whether this is a new application or an update to an existing one, then creating the initial feature.json structure.
 
 ## Flow
@@ -170,29 +178,16 @@ Ask via AskUserQuestion:
 language: string (code, e.g., "en", "fr")
 ```
 
-## Step 5b: Detect Development Mode
+## Step 5b: Analysis Mode
 
-Determine if the project will be built in **vibe coding** mode (developer + AI) or by a human development team.
+> The analysis phase is ALWAYS interactive — the AI listens, reformulates,
+> challenges, and validates with the user. This is non-negotiable regardless
+> of development mode. Vibe coding applies to code execution (step-03+), NOT to analysis.
 
-```
-Ask via AskUserQuestion:
-  question: "Comment allez-vous developper ce projet ?"
-  header: "Mode dev"
-  options:
-    - label: "Vibe coding (avec IA)"
-      description: "Je developpe moi-meme avec l'aide de l'IA — questionnaire allege"
-    - label: "Equipe de developpement"
-      description: "Une equipe humaine va developper — analyse complete"
-
-IF user selects "Vibe coding (avec IA)":
-  vibe_coding = true
-ELSE:
-  vibe_coding = false
-```
+**Set directly (no question):**
 
-**Store:**
 ```yaml
-vibe_coding: boolean
+analysisMode: "interactive"  # Always interactive for cadrage
 ```
 
 ## Step 6: Generate Feature ID
@@ -288,7 +283,7 @@ ba-writer.createApplicationFeature({
     language: {language},
     featureDescription: {feature_description},
     workflowType: {workflow_type},
-    vibeCoding: {vibe_coding},
+    analysisMode: "interactive",
     mcpAvailable: true,
     workflow: {
       mode: "application",
@@ -328,6 +323,7 @@ Update `.business-analyse/config.json` with new feature information.
 ```
 ═══════════════════════════════════════════════════════════════
   BUSINESS ANALYSIS INITIALIZATION COMPLETE
+  SmartStack CLI v{{SMARTSTACK_VERSION}}
 ═══════════════════════════════════════════════════════════════
 
 | Field              | Value                                        |
@@ -339,7 +335,7 @@ Update `.business-analyse/config.json` with new feature information.
 | Language           | {language}                                   |
 | Version            | {version}                                    |
 | MCP Available      | true                                         |
-| Dev Mode           | {vibe_coding ? "Vibe coding" : "Standard"}   |
+| Analysis Mode      | Interactive (always)                         |
 
 NEXT STEP: step-01-cadrage
 ═══════════════════════════════════════════════════════════════
@@ -359,7 +355,7 @@ language: string
 docs_dir: string
 mcp_available: boolean
 workflow_mode: "application"
-vibe_coding: boolean
+analysisMode: "interactive"
 version: string
 ```