@atlashub/smartstack-cli 4.41.0 → 4.43.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@atlashub/smartstack-cli",
-  "version": "4.41.0",
+  "version": "4.43.0",
   "description": "SmartStack Claude Code automation toolkit - GitFlow, EF Core migrations, prompts and more",
   "author": {
     "name": "SmartStack",
@@ -54,7 +54,7 @@
   "scripts": {
     "postinstall": "node scripts/postinstall.js || exit 0",
     "dev": "tsup --watch",
-    "build:html": "node templates/skills/ba-generate-html/html/build-html.js",
+    "build:html": "node templates/skills/business-analyse-html/html/build-html.js",
     "build": "npm run build:html && npx tsup",
     "lint": "eslint src --ext .ts",
     "format": "prettier --write \"src/**/*.ts\"",

package/templates/agents/ba-reader.md

@@ -276,7 +276,7 @@ Generate compact context for use by other skills and agents.
 5. Keep output to max 100 lines
 
 **Used by:**
-- ralph-loop: for context during feature development
+- business-analyse-develop: for context during feature development
 - feature-full: for comprehensive documentation generation
 - Code generation skills: for understanding scope and permissions
 
@@ -356,7 +356,7 @@ When encountering ID references, resolve them by reading appropriate thematic fi
 ## Integration Points
 
 This agent provides context for:
-- **ralph-loop**: Entity and permission context during feature implementation
+- **business-analyse-develop**: Entity and permission context during feature implementation
 - **feature-full**: Source for comprehensive feature documentation
 - **Code generation**: Permission paths and entity definitions from thematic files
 - **ba-writer**: Finding features for enrichment operations

package/templates/agents/ba-writer.md

@@ -22,7 +22,7 @@ Write and update granular JSON files for project-level (multi-app), application-
 - `cadrage.json` — stakeholders, problem/vision, risks, acceptance criteria (ALL scopes)
 - `validation.json` — validation rules and consistency checks (ALL scopes)
 - `consolidation.json` — cross-module interactions and E2E flows (application/project ONLY)
-- `navigation.json` — navigation tree (application/project ONLY, created by ba-design-ui)
+- `navigation.json` — navigation tree (application/project ONLY, created by business-analyse-design)
 - `entities.json` — entity definitions with attributes and relationships (**MODULE ONLY**)
 - `rules.json` — business rules with categories and conditions (**MODULE ONLY**)
 - `usecases.json` — use cases and functional requirements (**MODULE ONLY**)
@@ -242,7 +242,7 @@ Write the handoff thematic file into a module index.json. Specialized operation
 
 **Process:**
 1. Locate the module index.json via findFeature
-2. Validate handoffData.filesToCreate has all 7 categories (domain, application, infrastructure, api, frontend, seedData, tests)
+2. Validate handoffData.filesToCreate has all 8 categories (domain, application, infrastructure, api, frontend, seedData, tests, documentation)
 3. Validate each fileSpec has at minimum path + type
 4. Read module rules.json and validate brToCodeMapping[].ruleId references exist
 5. Create handoff.json with handoffData
@@ -250,7 +250,7 @@ Write the handoff thematic file into a module index.json. Specialized operation
 7. Update fileHashes in index.json
 8. **POST-WRITE VERIFICATION:** Re-read handoff.json and confirm:
    - handoff !== {}
-   - filesToCreate contains all 7 categories
+   - filesToCreate contains all 8 categories
    - brToCodeMapping.length > 0
 9. IF verification fails → return error with details
 10. Return confirmation with stats (files per category, total BRs mapped)
@@ -270,14 +270,22 @@ Transition the status through defined workflow.
 - framed → decomposed
 - decomposed → specified
 - specified → consolidated
-- consolidated → handed-off
+- consolidated → designed
+- consolidated → handed-off (skip design/review)
+- designed → reviewed
+- designed → handed-off (skip review)
+- reviewed → handed-off
 
 **Valid transitions (project-level):**
 - draft → framed
 - framed → decomposed
 - decomposed → specified
 - specified → consolidated
-- consolidated → handed-off
+- consolidated → designed
+- consolidated → handed-off (skip design/review)
+- designed → reviewed
+- designed → handed-off (skip review)
+- reviewed → handed-off
 
 **Process:**
 1. Read index.json
@@ -391,7 +399,11 @@ Transition the status through defined workflow.
 - framed → decomposed
 - decomposed → specified
 - specified → consolidated
-- consolidated → handed-off
+- consolidated → designed
+- consolidated → handed-off (skip design/review)
+- designed → reviewed
+- designed → handed-off (skip review)
+- reviewed → handed-off
 
 **Process:**
 1. Read index.json
@@ -403,6 +415,29 @@ Transition the status through defined workflow.
 7. Write back index.json
 8. Return confirmation with new status
 
+### updateManifest
+
+Upsert an entry in docs/index.json manifest. Keyed by {appCode, moduleCode, version}.
+
+**Input:**
+- appCode: string (PascalCase application code)
+- moduleCode: string or null (PascalCase module code, null if application-level)
+- version: string (e.g., "1.0")
+- status: string (draft, framed, decomposed, specified, consolidated, designed, reviewed, handed-off)
+- lastModified: ISO timestamp
+
+**Process:**
+1. Read or create docs/index.json if not present
+2. Find entry keyed by {appCode, moduleCode, version}
+   - If entry exists: update status and lastModified
+   - If entry does not exist: create new entry with appCode, moduleCode, version, status, lastModified
+3. Write docs/index.json back with updated timestamp
+4. Return confirmation with total entries in manifest
+
+**Rules:**
+- This is the ONLY method that should write to docs/index.json — skills must NOT write directly.
+- All downstream operations that update status must call updateManifest to keep the manifest in sync.
+
 ## Schema Validation Rules
 
 Perform these structural checks before every write:
@@ -417,7 +452,7 @@ Perform these structural checks before every write:
 **Metadata:**
 - id, version, status, scope are required
 - metadata.createdAt, metadata.updatedAt must be valid ISO timestamps
-- For application scope: status must be in [draft, framed, decomposed, specified, consolidated, handed-off]
+- For application scope: status must be in [draft, framed, decomposed, specified, consolidated, designed, reviewed, handed-off]
 - For module scope: status must be in [draft, analysed, specified, approved, rejected, handed-off]
 
 **Thematic files:**
@@ -464,7 +499,7 @@ Perform these structural checks before every write:
 - layout: `{type, regions[]}` where regions[]: `{id, position, span?, components[]}`
 
 **handoff** in handoff.json — REQUIRED: `complexity`, `filesToCreate`, `brToCodeMapping[]`, `apiEndpointSummary[]`, `prdFile`, `totalFiles`, `totalTasks`, `handedOffAt`
-- filesToCreate: REQUIRED 7 categories: `domain[]`, `application[]`, `infrastructure[]`, `api[]`, `frontend[]`, `seedData[]`, `tests[]`
+- filesToCreate: REQUIRED 8 categories: `domain[]`, `application[]`, `infrastructure[]`, `api[]`, `frontend[]`, `seedData[]`, `tests[]`, `documentation[]`
 - brToCodeMapping[]: `{ruleId, files[], implementation}`
 
 ### Application-Level Thematic Files
@@ -499,7 +534,7 @@ docs/{app}/business-analyse/
     cadrage.json
     validation.json
     consolidation.json
-    navigation.json                     ← (created by ba-design-ui)
+    navigation.json                     ← (created by business-analyse-design)
     # NO entities/rules/usecases/permissions/screens/handoff — MODULE ONLY
 
 docs/{app}/{module}/business-analyse/

package/templates/hooks/stop-hook.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 # Ralph Loop Stop Hook
-# Prevents session exit when a ralph-loop is active
+# Prevents session exit when a business-analyse-develop is active
 # Feeds Claude's output back as input to continue the loop
 
 set -euo pipefail
@@ -9,8 +9,8 @@ set -euo pipefail
 # Read hook input from stdin (advanced stop hook API)
 HOOK_INPUT=$(cat)
 
-# Check if ralph-loop is active
-RALPH_STATE_FILE=".claude/ralph-loop.local.md"
+# Check if business-analyse-develop is active
+RALPH_STATE_FILE=".claude/business-analyse-develop.local.md"
 
 if [[ ! -f "$RALPH_STATE_FILE" ]]; then
   # No active loop - allow exit
@@ -31,7 +31,7 @@ if [[ ! "$ITERATION" =~ ^[0-9]+$ ]]; then
   echo "   Problem: 'iteration' field is not a valid number (got: '$ITERATION')" >&2
   echo "" >&2
   echo "   This usually means the state file was manually edited or corrupted." >&2
-  echo "   Ralph loop is stopping. Run /ralph-loop again to start fresh." >&2
+  echo "   Ralph loop is stopping. Run /business-analyse-develop again to start fresh." >&2
   rm "$RALPH_STATE_FILE"
   exit 0
 fi
@@ -42,7 +42,7 @@ if [[ ! "$MAX_ITERATIONS" =~ ^[0-9]+$ ]]; then
   echo "   Problem: 'max_iterations' field is not a valid number (got: '$MAX_ITERATIONS')" >&2
   echo "" >&2
   echo "   This usually means the state file was manually edited or corrupted." >&2
-  echo "   Ralph loop is stopping. Run /ralph-loop again to start fresh." >&2
+  echo "   Ralph loop is stopping. Run /business-analyse-develop again to start fresh." >&2
   rm "$RALPH_STATE_FILE"
   exit 0
 fi
@@ -144,7 +144,7 @@ if [[ -z "$PROMPT_TEXT" ]]; then
   echo "     • State file was manually edited" >&2
   echo "     • File was corrupted during writing" >&2
   echo "" >&2
-  echo "   Ralph loop is stopping. Run /ralph-loop again to start fresh." >&2
+  echo "   Ralph loop is stopping. Run /business-analyse-develop again to start fresh." >&2
   rm "$RALPH_STATE_FILE"
   exit 0
 fi

package/templates/ralph/README.md

@@ -53,7 +53,7 @@ claude mcp add context7 -- npx @upstash/context7-mcp
 
 3. In Claude Code, use:
    ```
-   /ralph-loop "Your feature description"
+   /business-analyse-develop "Your feature description"
    ```
 
 ## Logs

package/templates/scripts/setup-ralph-loop.sh

@@ -3,7 +3,7 @@
 # SmartStack CLI - https://atlashub.ch
 #
 # This script initializes the Ralph loop with MCP validation
-# Usage: setup-ralph-loop.sh "PROMPT" [--max-iterations N] [--completion-promise TEXT]
+# Usage: setup-business-analyse-develop.sh "PROMPT" [--max-iterations N] [--completion-promise TEXT]
 
 set -e
 
@@ -142,7 +142,7 @@ echo ""
 # Validate prompt
 if [[ -z "$PROMPT" ]]; then
     log_error "No prompt provided!"
-    log_info "Usage: /ralph-loop \"Your feature description\""
+    log_info "Usage: /business-analyse-develop \"Your feature description\""
     exit 1
 fi
 

package/templates/skills/_resources/context-digest-template.md

@@ -2,7 +2,7 @@
 
 ## Purpose
 
-Reduces token usage between multi-step skill executions (BA, ralph-loop) by compressing step outputs into compact summaries.
+Reduces token usage between multi-step skill executions (BA, business-analyse-develop) by compressing step outputs into compact summaries.
 
 ## How It Works
 

package/templates/skills/_shared.md

@@ -179,7 +179,7 @@ If MCP is not available, display this message and **STOP the skill immediately**
 | business-analyse | **YES** | Analysis, specification, validation |
 | application | **YES** | Navigation + code generation |
 | controller | **YES** | Controller scaffolding |
-| ralph-loop | **YES** | Iterative code generation |
+| business-analyse-develop | **YES** | Iterative code generation |
 | validate | **YES** | Convention validation |
 | efcore | **YES** | Migration management |
 | review-code | **YES** | Code review |
@@ -193,29 +193,29 @@ If MCP is not available, display this message and **STOP the skill immediately**
 
 | Tool | Usage | Used By |
 |------|-------|---------|
-| `mcp__smartstack__validate_conventions` | Valider conventions SmartStack (tables, migrations, services, namespaces, entities, tenants, controllers) | application, controller, ralph-loop |
-| `mcp__smartstack__scaffold_extension` | Génération code (feature, entity, service, controller, component, dto, validator, repository) | application, ralph-loop |
-| `mcp__smartstack__check_migrations` | Analyser migrations EF Core (conflits, ordre, ModelSnapshot) | application, ralph-loop |
+| `mcp__smartstack__validate_conventions` | Valider conventions SmartStack (tables, migrations, services, namespaces, entities, tenants, controllers) | application, controller, business-analyse-develop |
+| `mcp__smartstack__scaffold_extension` | Génération code (feature, entity, service, controller, component, dto, validator, repository) | application, business-analyse-develop |
+| `mcp__smartstack__check_migrations` | Analyser migrations EF Core (conflits, ordre, ModelSnapshot) | application, business-analyse-develop |
 | `mcp__smartstack__api_docs` | Documentation API depuis Swagger/OpenAPI ou controllers | controller |
-| `mcp__smartstack__suggest_migration` | Suggérer nom migration ({context}_v{version}_{sequence}_{Description}) | application, ralph-loop |
-| `mcp__smartstack__generate_permissions` | Générer permissions RBAC depuis NavRoute | application, ralph-loop |
+| `mcp__smartstack__suggest_migration` | Suggérer nom migration ({context}_v{version}_{sequence}_{Description}) | application, business-analyse-develop |
+| `mcp__smartstack__generate_permissions` | Générer permissions RBAC depuis NavRoute | application, business-analyse-develop |
 
 ### Outils Tests
 
 | Tool | Usage | Used By |
 |------|-------|---------|
-| `mcp__smartstack__scaffold_tests` | Générer tests unitaires/intégration/sécurité | application, ralph-loop |
-| `mcp__smartstack__analyze_test_coverage` | Analyser couverture de tests du projet | ralph-loop |
-| `mcp__smartstack__validate_test_conventions` | Valider conventions de nommage des tests | ralph-loop |
-| `mcp__smartstack__suggest_test_scenarios` | Suggérer scénarios de test basés sur le code | ralph-loop |
+| `mcp__smartstack__scaffold_tests` | Générer tests unitaires/intégration/sécurité | application, business-analyse-develop |
+| `mcp__smartstack__analyze_test_coverage` | Analyser couverture de tests du projet | business-analyse-develop |
+| `mcp__smartstack__validate_test_conventions` | Valider conventions de nommage des tests | business-analyse-develop |
+| `mcp__smartstack__suggest_test_scenarios` | Suggérer scénarios de test basés sur le code | business-analyse-develop |
 
 ### Outils Frontend
 
 | Tool | Usage | Used By |
 |------|-------|---------|
-| `mcp__smartstack__scaffold_api_client` | Générer client TypeScript avec NavRoute | application, ralph-loop |
-| `mcp__smartstack__scaffold_routes` | Générer React Router depuis NavRoute backend | application, ralph-loop |
-| `mcp__smartstack__validate_frontend_routes` | Valider synchronisation routes frontend/backend | application, ralph-loop |
+| `mcp__smartstack__scaffold_api_client` | Générer client TypeScript avec NavRoute | application, business-analyse-develop |
+| `mcp__smartstack__scaffold_routes` | Générer React Router depuis NavRoute backend | application, business-analyse-develop |
+| `mcp__smartstack__validate_frontend_routes` | Valider synchronisation routes frontend/backend | application, business-analyse-develop |
 | `mcp__smartstack__scaffold_frontend_extension` | Générer infrastructure extension frontend | application |
 | `mcp__smartstack__analyze_extension_points` | Analyser points d'extension dans les pages React | application |
 

package/templates/skills/apex/SKILL.md

@@ -5,7 +5,7 @@ description: |
   Use this skill when:
   - Adding a new section/resource to an existing module
   - Developing feature by feature without /business-analyse
-  - Fixing or extending code generated by /ralph-loop
+  - Fixing or extending code generated by /business-analyse-develop
   - Any incremental SmartStack development task
 argument-hint: "[-a] [-x] [-s] [-e] [-r] [-pr] <task description>"
 ---
@@ -19,11 +19,18 @@ Execute incremental SmartStack development using the APEX methodology. This skil
 <quick_start>
 
 ```bash
+# Direct use (you know exactly what to build):
 /apex add absence management to HR module           # Add section to module
 /apex -a fix the leave request controller            # Auto fix
 /apex -a -x -s -pr add PDF export to Orders           # Full workflow
 /apex -e add status field to Project entity          # Economy (no agents)
 /apex -r                                             # Resume previous
+
+# From /sketch (vague idea → precise command):
+/sketch une app RH avec employés et absences         # → generates /apex command
+
+# From /business-analyse-develop (automated multi-module):
+# /business-analyse-develop delegates to /apex -d automatically
 ```
 
 </quick_start>
@@ -38,8 +45,8 @@ Execute incremental SmartStack development using the APEX methodology. This skil
 | `-e` | Economy mode: no subagents |
 | `-r` | Resume: continue from previous state |
 | `-pr` | PR mode: create pull request at end |
-| `-d {path}` | Delegate mode: read context from PRD file at `{path}`. Implies `-a -e`. Used by `/ralph-loop`. |
-| `--foundation` | Foundation mode: generate ONLY entities + EF configs + migration. No services/controllers/frontend. Used by ralph-loop Phase 0. |
+| `-d {path}` | Delegate mode: read context from PRD file at `{path}`. Implies `-a -e`. Used by `/business-analyse-develop`. |
+| `--foundation` | Foundation mode: generate ONLY entities + EF configs + migration. No services/controllers/frontend. Used by business-analyse-develop Phase 0. |
 
 </parameters>
 
@@ -54,9 +61,9 @@ Execute incremental SmartStack development using the APEX methodology. This skil
 | `{save_mode}` | boolean | Save outputs to `.claude/output/apex/{task-id}/` |
 | `{economy_mode}` | boolean | No subagents |
 | `{pr_mode}` | boolean | Create PR at end |
-| `{delegate_mode}` | boolean | Delegated by `/ralph-loop` via `-d` flag |
+| `{delegate_mode}` | boolean | Delegated by `/business-analyse-develop` via `-d` flag |
 | `{delegate_prd_path}` | string? | Path to PRD file (`.ralph/prd.json` or `.ralph/prd-{module}.json`) |
-| `{foundation_mode}` | boolean | Foundation mode: entities-only (no services/controllers/frontend). Used by ralph-loop Phase 0. |
+| `{foundation_mode}` | boolean | Foundation mode: entities-only (no services/controllers/frontend). Used by business-analyse-develop Phase 0. |
 | `{app_name}` | string | Application name |
 | `{module_code}` | string | Module code |
 | `{sections}` | object[] | Sections (required, min 1) with code/labels/icon/displayOrder |
@@ -159,8 +166,8 @@ Execute incremental SmartStack development using the APEX methodology. This skil
 - **Frontend pages: ALWAYS via Skill("ui-components")** — economy_mode affects parallelization only, NOT whether /ui-components is called. NEVER generate .tsx pages directly, even in delegate or economy mode.
 - **Save outputs** if `{save_mode}` = true
 - **Commits per layer** - Atomic commits after each execution layer
-- **Delegate mode** (`-d`): Read PRD context, skip challenge questions, auto+economy mode implied. Used when `/ralph-loop` delegates code generation to `/apex`.
-- **Foundation mode** (`--foundation`): Generate ONLY entities + EF configs + migration (domain + infrastructure layers). Skip application/api/frontend/tests. Used by ralph-loop Phase 0 to create database foundation before spawning parallel teammates.
+- **Delegate mode** (`-d`): Read PRD context, skip challenge questions, auto+economy mode implied. Used when `/business-analyse-develop` delegates code generation to `/apex`.
+- **Foundation mode** (`--foundation`): Generate ONLY entities + EF configs + migration (domain + infrastructure layers). Skip application/api/frontend/tests. Used by business-analyse-develop Phase 0 to create database foundation before spawning parallel teammates.
 
 </execution_rules>
 

package/templates/skills/apex/_shared.md

@@ -19,7 +19,7 @@
 
 > **Active when:** `-d {path}` flag is set. Implies `-a` (auto) + `-e` (economy).
 
-When `/ralph-loop` invokes `/apex -d {prd_path}`:
+When `/business-analyse-develop` invokes `/apex -d {prd_path}`:
 
 1. **Read PRD** from `{delegate_prd_path}` (`.ralph/prd.json` or `.ralph/prd-{module}.json`)
 2. **Extract context:**

package/templates/skills/apex/references/challenge-questions.md

@@ -148,20 +148,53 @@ questions:
 
 ---
 
-## 5b. Dependencies & Key Properties
+## 5b. Dependency Auto-Detection (NO user question)
+
+> **Principle:** The agent detects dependencies — the user should NEVER be asked about this.
+
+### Algorithm
+
+```
+1. INTRA-MODULE FK detection (from {entities} collected in 5a):
+   For each entity pair (A, B) in {entities}:
+     IF entity A name appears as "{B}Id" pattern in typical HR/business domain:
+       → Record: { entity: A, fkProperty: "{B}Id", targetEntity: B, isInterModule: false }
+     Example: entities = [Employee, Absence] → Absence likely has EmployeeId FK
+
+2. INTER-MODULE FK detection (scan existing codebase):
+   existing_entities = Glob("**/Domain/Entities/**/*.cs") → extract class names (exclude enums, VOs)
+
+   IF existing_entities.length > 0:
+     For each entity in {entities}:
+       For each existing in existing_entities:
+         IF task description or entity context suggests relationship to existing:
+           → Record: { entity, fkProperty: "{existing}Id", targetEntity: existing, isInterModule: true }
+
+   IF existing_entities.length == 0 (fresh project):
+     → {has_dependencies} = "none" or "intra-only"
+     → Skip inter-module detection entirely
+
+3. STORE results:
+   {has_dependencies} = "none" | "intra-only" | "inter-module"
+   {detected_fks} = [{ entity, fkProperty, targetEntity, isInterModule }]
+
+4. DISPLAY summary (no question, just confirmation):
+   "Dependencies detected: Absence → Employee (intra-module FK)"
+   Or: "No inter-module dependencies detected (fresh project)"
+```
+
+### False Positive Guards
+
+- Only match against classes extending `BaseEntity` / `AuditableEntity` (not enums, value objects)
+- If entity name is a substring of another (e.g., "Employee" in "EmployeeStatus"), verify the target is a navigable entity
+- Limit inter-module scan to entities whose names appear in the task description or {entities} list
+
+---
+
+## 5b-bis. Key Properties
 
 ```yaml
 questions:
-  - header: "Dependencies"
-    question: "Does this module reference entities from other existing modules?"
-    options:
-      - label: "No dependencies"
-        description: "Standalone module — no FK relationships to other modules"
-      - label: "Yes, has FK references"
-        description: "References entities from other modules (specify in Other)"
-      - label: "Not sure yet"
-        description: "Will determine during analysis — may require EntityLookup components"
-    multiSelect: false
   - header: "Key fields"
     question: "Beyond standard fields (Id, TenantId, Audit), what are the key business properties of the main entity?"
     options:
@@ -183,7 +216,7 @@ questions:
 
 ```
 IF delegate_mode (-d flag):
-  → SKIP (ralph-loop / PRD already defines code patterns)
+  → SKIP (business-analyse-develop / PRD already defines code patterns)
 
 IF feature.json exists AND ALL entities have codePattern defined:
   → SKIP (BA already collected code patterns)
@@ -320,7 +353,7 @@ questions:
 
 ## Delegate Mode Skip (if -d flag)
 
-When `/ralph-loop` invokes `/apex -d {prd_path}`, ALL hierarchy is extracted from the PRD file:
+When `/business-analyse-develop` invokes `/apex -d {prd_path}`, ALL hierarchy is extracted from the PRD file:
 - Skip sections 4a-5b (no interactive questions)
 - Jump directly to MCP verify section
 ```

package/templates/skills/apex/references/core-seed-data.md

@@ -5,7 +5,7 @@
 > **Applies to:** Client projects only (seeding_strategy = "provider", ExtensionsDbContext)
 >
 > **Source of truth:** `/application` skill `templates-seed.md` (lines 608-916)
-> **Moved from:** `ralph-loop/references/core-seed-data.md` (delegation refactoring)
+> **Moved from:** `business-analyse-develop/references/core-seed-data.md` (delegation refactoring)
 
 ---
 
@@ -1309,7 +1309,7 @@ services.AddScoped<IClientSeedDataProvider, {AppPascalName}SeedDataProvider>();
 
 ## 7. Multi-Module Handling
 
-When processing multiple modules in the same ralph-loop run:
+When processing multiple modules in the same business-analyse-develop run:
 
 ### Module 1 (first): Creates everything from scratch
 
@@ -1352,7 +1352,7 @@ Before marking the task as completed, verify ALL:
 **Application-Level (FIRST — before modules):**
 - [ ] `NavigationApplicationSeedData.cs` created (once per application, at `Infrastructure/Persistence/Seeding/Data/`)
 - [ ] Application GUID is random (`Guid.NewGuid()`) — FK resolution is by Code lookup, not fixed ID
-- [ ] GetApplicationEntry() takes no parameters (no contextId), includes `Zone = ApplicationZone.Business`
+- [ ] GetApplicationEntry() takes no parameters, includes `Zone = ApplicationZone.Business`
 - [ ] Application translations created (4 languages: fr, en, it, de, EntityType = Application), using `app.Id` (actual DB ID) for EntityId
 - [ ] `IClientSeedDataProvider.SeedNavigationAsync()` uses `NavigationApplicationSeedData` (NO hardcoded `{appLabel_en}` / `{appIcon}` placeholders)
 - [ ] `ApplicationRolesSeedData.ApplicationId` references `NavigationApplicationSeedData.ApplicationId` (DTO only — provider code resolves from DB by Code)
@@ -1452,7 +1452,7 @@ public class {Module}DevDataSeeder : IDevDataSeeder
 > If you use a custom GUID, ensure it is created BEFORE `DevDataSeeder` runs (Order >= 200).
 >
 > **Pipeline validation:**
-> - ralph-loop POST-CHECK warns if GUID not found in project config
+> - business-analyse-develop POST-CHECK warns if GUID not found in project config
 > - validate-feature step-05 verifies FK exists in real database via SQL query
 
 ---

package/templates/skills/apex/references/error-classification.md

@@ -3,7 +3,7 @@
 > **Loaded by:** apex step-03-execute (build failure) and step-04-examine (validation)
 > **Purpose:** Classify build and runtime errors to apply the correct fix strategy.
 > **Key insight:** Not all errors are code errors. Package/config errors require different fixes than code errors.
-> **Moved from:** `ralph-loop/references/error-classification.md` (delegation refactoring)
+> **Moved from:** `business-analyse-develop/references/error-classification.md` (delegation refactoring)
 
 ---
 
@@ -88,7 +88,7 @@
 
 ### Category F: Code Error (FIX = edit source code)
 
-> **Only this category should trigger code editing in ralph-loop iterations.**
+> **Only this category should trigger code editing in business-analyse-develop iterations.**
 
 | Error Pattern | Example | Fix |
 |--------------|---------|-----|
@@ -140,5 +140,5 @@ BUILD/RUNTIME ERROR
 3. **Category C:** Edit DI file only. One targeted fix, rebuild, verify
 4. **Category D:** Run migration commands. Do NOT edit code
 5. **Category E:** Edit config file only
-6. **Category F:** Normal ralph-loop code fix iteration
+6. **Category F:** Normal business-analyse-develop code fix iteration
 7. **If 2+ consecutive iterations fail on same error after code fixes -> re-classify** (likely wrong category)

package/templates/skills/apex/references/smartstack-api.md

@@ -329,7 +329,7 @@ public class {Name}Controller : ControllerBase
 | Section | `{app}.{module}.{section}` (3 segments) | `administration.users.groups` |
 | Sub-resource | `{app}.{module}` + `Suffix` | `[NavRoute("administration.ai", Suffix = "prompts")]` |
 
-> POST-CONTEXT REMOVAL: Old "context" level removed. 2-segment minimum. `NavigationRouteRegistryBuilder` builds 2-segment paths from DB. 3+ segments use fallback route generator.
+> ROUTING: 2-segment minimum. `NavigationRouteRegistryBuilder` builds 2-segment paths from DB. 3+ segments use fallback route generator.
 
 **Sub-resource completeness:** If a parent page has a navigate() to a sub-resource route, the frontend MUST include a page for that route. Otherwise → dead link → white screen. Prefer separate controllers (with Suffix) over sub-endpoints in parent controller.
 

package/templates/skills/apex/references/smartstack-layers.md

@@ -537,7 +537,7 @@ See `references/parallel-execution.md` for agent launch patterns, task coordinat
 
 ## Delegate Mode Fast Path
 
-When `/ralph-loop` invokes `/apex -d {prd_path}`, PRD tasks already define the scope.
+When `/business-analyse-develop` invokes `/apex -d {prd_path}`, PRD tasks already define the scope.
 
 Map each PRD task to a layer based on `task.category`:
 - `domain` → Layer 0

package/templates/skills/apex/steps/step-00-init.md

@@ -61,6 +61,43 @@ When `-d {prd_path}` is used, extract all context from PRD file and skip section
 
 ---
 
+## 1c. Prompt Precision Guard
+
+> **APEX executes, it does not explore.** If the prompt is too vague, redirect to `/business-analyse`.
+
+**Score the prompt — count how many of these are present or inferable:**
+
+| Element | Example | Weight |
+|---------|---------|--------|
+| Module name/code | "employees", "absence management" | 1 |
+| At least 1 entity name | "Employee", "Absence" | 1 |
+| At least 1 property/field | "FirstName, StartDate, Status" | 1 |
+| Target application | "HR module", "HumanResources" | 0.5 |
+| Section hint | "list", "dashboard", "approval" | 0.5 |
+
+```
+precision_score = sum of weights for elements found in task description
+
+IF precision_score < 2:
+  DISPLAY:
+  ╔══════════════════════════════════════════════════════════════╗
+  ║  ⚠ Prompt too vague for /apex                              ║
+  ║                                                             ║
+  ║  /apex needs precise features to execute in one shot.       ║
+  ║  Your request looks more like a discovery/design task.      ║
+  ║                                                             ║
+  ║  Suggestions:                                               ║
+  ║  1. Use /sketch to quickly design your module (~2 min)      ║
+  ║  2. Use /business-analyse for full analysis (40+ questions) ║
+  ║  3. Rewrite your prompt with entities and fields, e.g.:     ║
+  ║     /apex add employees section with Employee entity        ║
+  ║     (FirstName, LastName, Email) to HumanResources module   ║
+  ╚══════════════════════════════════════════════════════════════╝
+  → STOP — do NOT proceed to section 2
+```
+
+---
+
 ## 2. Detect SmartStack Application
 
 Scan project: Glob("*.sln"), Glob("docs/business/**/*"), Glob(".ralph/prd-*.json"), Glob("src/pages/**/*.tsx")
@@ -112,11 +149,12 @@ Call `mcp__smartstack__validate_conventions` after computing derivations. Fix an
 
 ---
 
-## 5. Challenge the Need
+## 5. Collect Technical Parameters
 
-Rapid scope validation — load and execute questions from `references/challenge-questions.md`:
+Rapid technical parameter collection — load and execute questions from `references/challenge-questions.md`:
 - **5a:** Entity scope & relationships
-- **5b:** Dependencies & key properties
+- **5b:** Dependency auto-detection (NO question — agent scans codebase and infers from {entities})
+- **5b-bis:** Key properties (question kept — user may have specific field requirements)
 - **5c:** Code generation strategy
 
 **Skip 5c if:**
@@ -136,7 +174,7 @@ Propagated to: step-01 (code focus), step-02 (layer mapping), step-03 (scaffoldi
 
 ## 5e. Scope Complexity Guard
 
-**Design:** `/apex` handles 1 module at a time. Use `/ralph-loop` for multi-module projects.
+**Design:** `/apex` handles 1 module at a time. Use `/business-analyse-develop` for multi-module projects.
 
 **Calculate:**
 ```
@@ -144,10 +182,10 @@ scope_score = entity_count + (section_count * 0.5) + (app_count * 3)
 ```
 
 **Rules:**
-- `delegate_mode (-d)` → SKIP guard (ralph-loop handles scope per module)
-- `app_count > 1` → Warning: use `/ralph-loop` or split requests
-- `entity_count > 6` → BLOCKING: max 6 entities. Solutions: `/ralph-loop`, `/apex -d`, or split manually
-- `scope_score > 8` → WARNING: ask user to split or use `/ralph-loop`
+- `delegate_mode (-d)` → SKIP guard (business-analyse-develop handles scope per module)
+- `app_count > 1` → Warning: use `/business-analyse-develop` or split requests
+- `entity_count > 6` → BLOCKING: max 6 entities. Solutions: `/business-analyse-develop`, `/apex -d`, or split manually
+- `scope_score > 8` → WARNING: ask user to split or use `/business-analyse-develop`
 
 **Recommended Scope:**
 | Metric | Safe | Warning | Blocking |

package/templates/skills/apex/steps/step-01-analyze.md

@@ -39,7 +39,7 @@ This saves ~2 minutes of Glob searches on an empty project.
 
 ## 0b. Delegate Mode Fast Path (if delegate_mode)
 
-> **When called via `/ralph-loop -d`, PRD tasks provide pre-computed scope. Reduce exploration to verification only.**
+> **When called via `/business-analyse-develop -d`, PRD tasks provide pre-computed scope. Reduce exploration to verification only.**
 
 ```
 IF delegate_mode:

package/templates/skills/apex/steps/step-02-plan.md

@@ -21,7 +21,7 @@ Read `references/smartstack-layers.md` for layer execution rules, skill/MCP mapp
 
 ## 0. Delegate Mode Fast Path (if delegate_mode)
 
-> **When called via `/ralph-loop -d`, PRD tasks already define the scope. Map directly to layers.**
+> **When called via `/business-analyse-develop -d`, PRD tasks already define the scope. Map directly to layers.**
 
 ```
 IF delegate_mode:

package/templates/skills/apex/steps/step-03-execute.md

@@ -81,7 +81,7 @@ Load each sub-step sequentially:
 
 ## PRD State Update (delegate mode only)
 
-> **After completing EACH layer**, update the PRD file so `/ralph-loop` can track progress.
+> **After completing EACH layer**, update the PRD file so `/business-analyse-develop` can track progress.
 
 ```
 IF delegate_mode: