@atlashub/smartstack-cli 4.22.0 → 4.24.0

package/templates/skills/ba-generate-html/steps/step-01-collect.md

@@ -36,20 +36,7 @@ ELSE:
 Store: workflow.mode
 ```
 
-### 3. Verify PRD Exists
-
-```
-FOR each module in modules:
-  prdPath = ".ralph/prd-{moduleCode}.json"
-  IF NOT exists(prdPath):
-    BLOCKING ERROR: "PRD not found: {prdPath} — Run /derive-prd first"
-    STOP
-  IF fileSize(prdPath) < 100:
-    BLOCKING ERROR: "PRD file too small: {prdPath} — Run /derive-prd to regenerate"
-    STOP
-```
-
-### 4. Verify Consolidation Status
+### 3. Verify Consolidation Status
 
 ```
 IF workflow.mode === "project":
@@ -64,13 +51,13 @@ ELSE:
     BLOCKING ERROR: "Feature status: {feature.status}, expected consolidated"
 ```
 
-### 5. Read All JSON Files
+### 4. Read All JSON Files
 
 ```
 collected_data = {
   master: {
     index: READ(index.json),           // metadata, modules[], consolidation, handoff
-    cadrage: READ(cadrage.json)         // context, stakeholders, scope, risks
+    cadrage: READ(cadrage.json)         // context, stakeholders, scope
   },
   modules: {}
 }
@@ -86,13 +73,9 @@ FOR each module in master.index.modules[]:
   }
 ```
 
-### 6. Display Collection Summary
+### 5. Display Collection Summary
 
 ```
-PRD verified: {module_count} modules
-  .ralph/prd-{module1}.json ({size} bytes)
-  .ralph/prd-{module2}.json ({size} bytes)
-
 JSON collected:
   Master: index.json + cadrage.json
   Modules: {module_count} module index files
@@ -105,7 +88,6 @@ JSON collected:
 
 - BLOCK if index.json absent
 - BLOCK if 0 modules found
-- BLOCK if any PRD file missing
 - BLOCK if feature not consolidated
 
 ## NEXT STEP

package/templates/skills/ba-generate-html/steps/step-02-build-data.md

@@ -69,15 +69,6 @@ scope: {
 
 > Safety net: also check `master.cadrage.coverageMatrix` as alternative source for scope items.
 
-**cadrage.risks:**
-```javascript
-risks: (master.cadrage.risks || []).map(r => ({
-  description: r.description,
-  probability: r.probability,
-  impact: r.impact,
-  mitigation: r.mitigation || ""
-}))
-```
 
 **modules[]:**
 ```javascript
@@ -119,8 +110,8 @@ moduleSpecs[moduleCode] = {
     name: ent.name,
     description: ent.description || "",
     attributes: (ent.attributes || []).length > 0
-      ? ent.attributes.map(a => ({ name: a.name, description: a.description || "" }))
-      : (ent.fields || []).map(f => ({ name: f.name, description: f.description || f.type || "" })),
+      ? ent.attributes.map(a => ({ name: a.name, type: a.type || "string", required: a.required || false, description: a.description || "" }))
+      : (ent.fields || []).map(f => ({ name: f.name, type: f.type || "string", required: f.required || false, description: f.description || "" })),
     relationships: (ent.relationships || []).map(r =>
       typeof r === 'string' ? r : r.target + " (" + r.type + ") - " + (r.description || ""))
   })),

package/templates/skills/ba-review/SKILL.md

@@ -32,7 +32,22 @@ Apply corrections exported from the interactive HTML review (`ba-review.json`) t
 |------|------|------|
 | 01 | `steps/step-01-apply.md` | Read ba-review.json, create new version, apply corrections to JSON files |
 
-After step-01 completes, delegate to `/ba-generate-html` to regenerate the interactive HTML document.
+After step-01 completes:
+1. Determine correction scope (analysis data vs UI design vs both)
+2. Route to the appropriate phase for re-execution
+3. Regenerate HTML via `/ba-generate-html`
+
+## Correction Routing
+
+After applying corrections, ask the client which phase to re-execute:
+
+| Correction type | Route to | Reason |
+|-----------------|----------|--------|
+| Entities, rules, UCs, permissions changed | `/business-analyse` step-03 (specify) | Re-run analysis for affected modules |
+| Screens, wireframes, navigation changed | `/ba-design-ui` | Re-run UI design for affected modules |
+| Both analysis and UI changed | `/business-analyse` step-03, then `/ba-design-ui` | Full re-specification |
+| Only cadrage/scope corrections | `/ba-generate-html` | Just regenerate HTML |
+| Client approves (no corrections) | `/derive-prd` | Proceed to PRD generation |
 
 ## References
 

package/templates/skills/ba-review/steps/step-01-apply.md

@@ -180,7 +180,31 @@ review_section = {
 Create review.json with review_section and update hash in index.json
 ```
 
-## Step 8: Regenerate Interactive HTML
+## Step 8: Determine Correction Routing
+
+Analyze the corrections applied to determine which phase needs re-execution:
+
+```
+analysis_changes = false
+ui_changes = false
+
+FOR EACH module in corrected_modules:
+  IF entities, rules, usecases, or permissions were modified:
+    analysis_changes = true
+  IF screens, wireframes, or navigation were modified:
+    ui_changes = true
+
+IF analysis_changes AND ui_changes:
+  route = "both"
+ELSE IF analysis_changes:
+  route = "analysis"
+ELSE IF ui_changes:
+  route = "ui"
+ELSE:
+  route = "html-only"
+```
+
+## Step 9: Regenerate Interactive HTML
 
 Delegate HTML generation to `/ba-generate-html` skill:
 
@@ -190,7 +214,7 @@ Delegate HTML generation to `/ba-generate-html` skill:
 3. Output: {new_version_dir}/ba-interactive.html
 ```
 
-## Step 9: Update Manifest
+## Step 10: Update Manifest
 
 ```
 1. Read docs/index.json
@@ -200,12 +224,12 @@ Delegate HTML generation to `/ba-generate-html` skill:
 5. Write docs/index.json
 ```
 
-## Step 10: Display Completion Summary
+## Step 11: Display Completion Summary
 
 ```
-═══════════════════════════════════════════════════════════════
+=====================================================================
   REVIEW CORRECTIONS APPLIED SUCCESSFULLY
-═══════════════════════════════════════════════════════════════
+=====================================================================
 
 | Field                | Value                                |
 |----------------------|--------------------------------------|
@@ -231,11 +255,37 @@ Artifacts regenerated:
 | Thematic files       | {new_version_dir}/*.json             |
 | Manifest             | docs/index.json                      |
 
-NEXT STEPS:
-1. Open the new ba-interactive.html to verify corrections
-2. Run /ralph-loop to start development from the updated analysis
-   (Use /ralph-loop -r ONLY to resume an interrupted loop)
-═══════════════════════════════════════════════════════════════
+NEXT STEPS (based on correction routing: {route}):
+```
+
+Display next steps based on `route`:
+
+```
+IF route == "analysis":
+  "1. Run /business-analyse step-03 for modules: {corrected_module_list}"
+  "2. Then run /ba-design-ui to update UI specs"
+  "3. Then run /ba-generate-html to regenerate documentation"
+
+IF route == "ui":
+  "1. Run /ba-design-ui for modules: {corrected_module_list}"
+  "2. Then run /ba-generate-html to regenerate documentation"
+
+IF route == "both":
+  "1. Run /business-analyse step-03 for modules: {analysis_corrected_modules}"
+  "2. Then run /ba-design-ui for modules: {ui_corrected_modules}"
+  "3. Then run /ba-generate-html to regenerate documentation"
+
+IF route == "html-only":
+  "HTML has been regenerated. Review the updated document."
+  "If satisfied, run /derive-prd to generate PRD files."
+
+IF no corrections (client approves):
+  "No corrections needed. Run /derive-prd to generate PRD files."
+  "Then run /ralph-loop to start development."
+```
+
+```
+=====================================================================
 ```
 
 ## Error Handling

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

@@ -23,23 +23,27 @@ user_invocable: true
 
 | Step | File | Model | Role |
 |------|------|-------|------|
-| 03 | `step-03-specify.md` | Opus | Deep dive per module: entities, BRs, UCs, permissions, screens. Sequential internal loop |
+| 03 | `step-03-specify.md` | Opus | Deep dive per module: entities, BRs, UCs, permissions. Sequential internal loop |
 | 04 | `step-04-consolidate.md` | Opus | Cross-module validation: data model, permission coherence, E2E flows |
 
 ### Post-BA Workflow
 ```
-Phase 1 (steps 00-02) → Phase 2 (steps 03-04) → /ba-generate-html → Client reviews HTML
-                                                                            ↓
-                                                               Client comments/enriches
-                                                                            ↓
-                                                               Export ba-review.json
-                                                                            ↓
-                                                               /ba-review → /ba-generate-html
-                                                                            ↓
-                                                               /derive-prd → /ralph-loop
+Phase 1: /business-analyse (steps 00-04)
+    |
+    v
+Phase 2: /ba-design-ui (screens, wireframes, navigation)
+    |
+    v
+Phase 3: /ba-generate-html (interactive HTML with mockups, ERD, permissions)
+    |
+    v
+Phase 4: /ba-review (client corrections → back to Phase 1 or 2)
+    |
+    v (client approves)
+Phase 5: /derive-prd → Phase 6: /ralph-loop
 ```
 
-> After step-04, invoke `/ba-generate-html` to generate the HTML, then `/ba-review` for the client correction cycle.
+> After step-04, invoke `/ba-design-ui` to design interfaces, then `/ba-generate-html` to generate the HTML, then `/ba-review` for the client correction cycle.
 > **PRD generation:** Handoff data and PRD files are generated by the `/derive-prd` skill.
 
 ## JSON Architecture — Granular files + Index
@@ -54,7 +58,7 @@ docs/{app}/{module}/business-analyse/v1.0/
   rules.json              ← Business rules (BRs)
   usecases.json           ← Use cases (UCs)
   permissions.json        ← Permissions, roles, access matrix
-  screens.json            ← Interface specs (sections, resources, mockups)
+  screens.json            ← Interface specs (produced by /ba-design-ui)
   validation.json         ← Validation results, checks
   handoff.json            ← File mapping, APIs, handoff data
 ```
@@ -135,15 +139,15 @@ STEP 02 (structure)
 STEP 03 (specify) — SEQUENTIAL MODULE LOOP
   → For each module (in dependency order):
     → Load: _shared.md, step-03-specify.md, module index.json
-    → Execute: entities, BRs, UCs, permissions, screens
-    → Output: entities.json, rules.json, usecases.json, permissions.json, screens.json
+    → Execute: entities, BRs, UCs, permissions
+    → Output: entities.json, rules.json, usecases.json, permissions.json
   → No team mode — sequential ensures 100% context per module
 
 STEP 04 (consolidate) — FINAL BA STEP
   → Load: _shared.md, step-04-consolidate.md, all index.json
   → Execute: Data model validation, permission coherence, E2E flows
   → Output: validation.json, consolidated data
-  → Next: invoke /ba-generate-html, then /ba-review for client cycle
+  → Next: invoke /ba-design-ui (Phase 2), then /ba-generate-html, then /ba-review for client cycle
 ```
 
 ## References

package/templates/skills/business-analyse/steps/step-03-specify.md

@@ -1,6 +1,6 @@
 ---
 name: step-03-specify
-description: Sequential deep dive per module - entities, BRs, UCs, permissions, screens
+description: Sequential deep dive per module - entities, BRs, UCs, permissions
 model: opus
 next_step: steps/step-04-consolidate.md
 ---
@@ -9,7 +9,7 @@ next_step: steps/step-04-consolidate.md
 
 ## Objective
 
-For each module (in dependency order), produce complete specifications: entities, business rules, use cases, permissions, and interface specs (screens).
+For each module (in dependency order), produce complete specifications: entities, business rules, use cases, and permissions. Interface specs (screens, wireframes, navigation) are handled by Phase 2 (`/ba-design-ui`).
 
 ## Prerequisites
 
@@ -123,40 +123,11 @@ Define the permission matrix:
 }
 ```
 
-### F. Interface Specs (Screens)
+### F. Interface Specs — Delegated to /ba-design-ui
 
-For each section/resource identified in step 02, specify the full interface:
-
-```json
-{
-  "sectionCode": "list",
-  "sectionLabel": "Liste des employes",
-  "resources": [
-    {
-      "code": "employees-grid",
-      "type": "SmartTable",
-      "label": "Grille des employes",
-      "columns": [
-        { "field": "code", "label": "Code", "type": "text", "sortable": true },
-        { "field": "fullName", "label": "Nom complet", "type": "text", "sortable": true },
-        { "field": "department.name", "label": "Departement", "type": "lookup", "filterable": true },
-        { "field": "status", "label": "Statut", "type": "badge", "filterable": true }
-      ],
-      "actions": ["create", "edit", "delete", "export"],
-      "filters": ["department", "status"],
-      "permission": "HumanResources.Employees.Read"
-    }
-  ]
-}
-```
-
-Resource types:
-- **SmartTable**: columns[], actions[], filters[], permission
-- **SmartForm**: tabs[{ label, fields[{ field, label, type, required, readonly, options }] }], actions[], permission
-- **SmartCard**: columns/fields[], permission
-- **SmartKanban**: options/columns[], permission
-- **SmartDashboard**: kpis[{ label, value }], permission
-- **SmartFilter**: options[], permission
+> **Screen specifications are NOT produced in this step.**
+> Interface design (SmartTable columns, SmartForm fields, wireframes, navigation) is handled by Phase 2: `/ba-design-ui`.
+> This separation allows iterating on UI design without replaying the full analysis cycle.
 
 ### G. Write & Advance
 
@@ -167,7 +138,6 @@ After completing all sub-steps for a module:
    - `rules.json`
    - `usecases.json`
    - `permissions.json`
-   - `screens.json`
    - Update `index.json` (hashes, summary counts)
 
 2. Update module status to `specified`
@@ -178,7 +148,8 @@ After completing all sub-steps for a module:
 
 After all modules are specified:
 - Verify all modules have status `specified`
-- Display summary: total entities, rules, UCs, permissions, screens across all modules
+- Display summary: total entities, rules, UCs, permissions across all modules
+- Remind user: "Run /ba-design-ui to design interfaces for these modules"
 - Transition to step 04
 
 ## POST-CHECK
@@ -188,7 +159,7 @@ Before advancing to step 04, verify:
 - [ ] Every module has at least 1 use case
 - [ ] Every module has at least 1 business rule
 - [ ] Every module has permissions defined
-- [ ] Every module has at least 1 screen defined
+- [ ] Entity attributes have `type` defined (string, int, date, enum, guid, etc.)
 - [ ] All entity relationships reference existing entities
 - [ ] All UC business rule references exist
 - [ ] All permission paths follow the convention

package/templates/skills/derive-prd/SKILL.md

@@ -29,8 +29,8 @@ Transforms consolidated BA data into structured handoff and PRD files.
 
 ## Input
 
-- Consolidated BA feature (`status = "consolidated"`)
-- Source: `docs/{app}/{module}/business-analyse/v{X.Y}/index.json`
+- Consolidated BA feature (`status = "consolidated"` or `"specified"`)
+- Source: `docs/{app}/business-analyse/v{X.Y}/index.json` (app-level) + `docs/{app}/{module}/business-analyse/v{X.Y}/` (flat files per module)
 - Usage: `--feature <path>` or auto-detection from `docs/`
 
 ## Output
@@ -45,14 +45,14 @@ Transforms consolidated BA data into structured handoff and PRD files.
 
 ## Handoff Categories (8)
 
-| Category | Source | Key rules |
+| Category | Source (flat files) | Key rules |
 |----------|--------|-----------|
-| **domain** | `analysis.entities[]` | Entities, ValueObjects, Enums |
-| **application** | `analysis.useCases[]` | Services, DTOs, Validators |
-| **infrastructure** | `analysis.entities[]` | EF Configurations, DbSet |
-| **api** | `specification.apiEndpoints[]` | Controllers (exact copy) |
-| **frontend** | `specification.uiWireframes[]` | Pages, Components, Hooks |
-| **seedData** | `specification.seedDataCore` | CORE + business |
+| **domain** | `entities.json > entities[]` | Entities, ValueObjects, Enums |
+| **application** | `usecases.json > useCases[]` | Services, DTOs, Validators |
+| **infrastructure** | `entities.json > entities[]` | EF Configurations, DbSet |
+| **api** | Generated from useCases + entities | Controllers |
+| **frontend** | `screens.json > screens[]` | Pages, Components, Hooks |
+| **seedData** | Generated from entities + permissions | CORE + business |
 | **tests** | All layers | Unit, Integration, Security tests |
 | **documentation** | All layers | Technical docs, user guides, API specs |