@atlashub/smartstack-cli 4.17.1 → 4.18.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@atlashub/smartstack-cli",
-  "version": "4.17.1",
+  "version": "4.18.0",
   "description": "SmartStack Claude Code automation toolkit - GitFlow, EF Core migrations, prompts and more",
   "author": {
     "name": "SmartStack",

package/templates/agents/ba-reader.md

@@ -13,8 +13,8 @@ You are a business analysis reader agent specialized in extracting and synthesiz
 Read feature.json files at both application-level and module-level, and provide structured answers, context summaries, or cross-feature insights. Support discovery, documentation, and skill orchestration.
 
 **File locations:**
-- Application-level: `docs/business/{app}/business-analyse/v{X.Y}/feature.json`
-- Module-level: `docs/business/{app}/{module}/business-analyse/v{X.Y}/feature.json`
+- Application-level: `docs/{app}/business-analyse/v{X.Y}/feature.json`
+- Module-level: `docs/{app}/{module}/business-analyse/v{X.Y}/feature.json`
 
 ## Core Operations
 
@@ -27,7 +27,7 @@ Locate a feature by ID and return its latest version path.
 - Optional: scope ("application" | "module" | "any") — default: "any"
 
 **Process:**
-1. Glob pattern: `docs/business/**/business-analyse/*/feature.json`
+1. Glob pattern: `docs/**/business-analyse/*/feature.json`
 2. Read each feature.json and check id field
 3. If scope filter provided, also check scope field
 4. If multiple versions exist, sort numerically by version
@@ -49,7 +49,7 @@ Locate the master (application-level) feature.json for a given app.
 - OR featureId: FEAT-NNN
 
 **Process:**
-1. Glob: `docs/business/{app}/business-analyse/*/feature.json`
+1. Glob: `docs/{app}/business-analyse/*/feature.json`
 2. Read and verify scope = "application"
 3. Return latest version path
 
@@ -215,7 +215,7 @@ Search all features for matching content.
 - Optional: scope (all | names-only | ids-only)
 
 **Process:**
-1. Glob all feature.json files in docs/business/
+1. Glob all feature.json files in docs/
 2. Search across:
    - Feature IDs
    - Entity names
@@ -240,8 +240,8 @@ Get the highest version number for a feature or module.
 
 **Process:**
 1. Glob paths:
-   - Single feature: `docs/business/**/business-analyse/v*/feature.json` filtered by ID
-   - Module: `docs/business/{app}/{module}/business-analyse/v*/feature.json`
+   - Single feature: `docs/**/business-analyse/v*/feature.json` filtered by ID
+   - Module: `docs/{app}/{module}/business-analyse/v*/feature.json`
 2. Extract version numbers (v1.0, v1.5, v2.1, etc.)
 3. Sort numerically
 4. Return highest version path and number
@@ -321,8 +321,8 @@ Generate compact context for use by other skills and agents.
 
 When searching for feature data:
 
-1. **Primary (application):** `docs/business/{app}/business-analyse/*/feature.json` (scope: application)
-2. **Primary (module):** `docs/business/{app}/{module}/business-analyse/*/feature.json` (scope: module)
+1. **Primary (application):** `docs/{app}/business-analyse/*/feature.json` (scope: application)
+2. **Primary (module):** `docs/{app}/{module}/business-analyse/*/feature.json` (scope: module)
 3. **Fallback:** `.business-analyse/` (legacy format)
    - Read: `00-context.md` + `3-functional-specification.md`
    - Warn user about old format

package/templates/agents/ba-writer.md

@@ -431,7 +431,7 @@ Perform these structural checks before every write:
 - BR IDs: must match `BR-(VAL|CALC|WF|SEC|DATA)-[A-Z]{2,4}-\d{3}` (e.g., BR-SEC-RM-042) — module prefix MANDATORY in multi-module mode
 - UC IDs: must match `UC-[A-Z]{2,4}-\d{3}` (e.g., UC-RM-007) — module prefix MANDATORY in multi-module mode
 - FR IDs: must match `FR-[A-Z]{2,4}-\d{3}` (e.g., FR-RM-012) — module prefix MANDATORY in multi-module mode
-- Permission paths: must match `{app}\.{module}\.{resource}\.{action}` (e.g., crm.contacts.read)
+- Permission paths: module-level `{app}\.{module}\.{action}` (3 segments, e.g., `crm.contacts.read`) OR section-level `{app}\.{module}\.{section}\.{action}` (4 segments, e.g., `crm.contacts.dashboard.read`) — all segments kebab-case lowercase
 
 **Metadata:**
 - id, version, status, scope are required
@@ -455,9 +455,10 @@ Perform these structural checks before every write:
 ### Module-Level Sections
 
 **analysis.entities[]** — REQUIRED fields: `name`, `description`, `attributes[]`, `relationships[]`
-- attributes[]: REQUIRED `name`, `description`, `required` | OPTIONAL `unique`, `validation`
+- attributes[]: REQUIRED `name`, `description`, `required` | OPTIONAL `unique`, `validation`, `type`
 - relationships[]: REQUIRED `target`, `type`, `description`
-- FORBIDDEN: `type` in attributes (use `description`), `values` (use `validation`), `rules` (use `validation`)
+- FORBIDDEN: `values` (use `validation`), `rules` (use `validation`)
+- **Two-phase `type` field:** `type` is FORBIDDEN in raw analysis input (step-03a2, before compilation). After step-03c compilation, `type` is MANDATORY (auto-inferred C# type: `string`, `int`, `decimal`, `bool`, `DateTime`, `Guid`, `enum:{Name}`, etc.). The writer ACCEPTS `type` when the value is a recognized C# type — it is only auto-removed from pre-compilation writes.
 
 **analysis.businessRules[]** — REQUIRED: `id`, `name`, `category`, `statement`, `priority`
 - OPTIONAL: `conditions[]`, `examples[]`, `testability`
@@ -502,15 +503,19 @@ Perform these structural checks before every write:
 - transitions[]: REQUIRED `{from, to, action, label, permission}` | OPTIONAL `guards[]`, `effects[]`, `confirm`
 - FORBIDDEN: flat string arrays for states (e.g., `["Active", "Inactive"]`), `terminalStates` as separate array
 
-**specification.seedDataCore** — REQUIRED 5 arrays: `navigationModules[]`, `navigationTranslations[]`, `permissions[]`, `rolePermissions[]`, `permissionConstants[]`
+**specification.seedDataCore** — REQUIRED 9 arrays: `navigationApplications[]`, `applicationRoles[]`, `navigationModules[]`, `navigationSections[]`, `navigationResources[]`, `navigationTranslations[]`, `permissions[]`, `rolePermissions[]`, `permissionConstants[]`
+- navigationApplications[]: `{code, label, icon, route, sort}`
+- applicationRoles[]: `{code, name, permissions}`
 - navigationModules[]: `{code, label, icon, route, parentCode, sort}`
-- navigationTranslations[]: `{moduleCode, language, label}` (4 languages: fr, en, nl, de)
+- navigationSections[]: `{code, label, icon, route, parentCode, permission, sort}`
+- navigationResources[]: `{code, type, entity, parentCode, permission}`
+- navigationTranslations[]: `{moduleCode, language, label}` (4 languages: fr, en, it, de)
 - permissions[]: `{path, action, description}`
 - rolePermissions[]: `{role, permissionPath}`
 - permissionConstants[]: `{constantName, path}`
 - FORBIDDEN: flat object, comma-separated strings, singular constants
 
-**specification.gherkinScenarios** — REQUIRED shape: `{feature, scenarios[]}`
+**specification.gherkinScenarios** — REQUIRED shape: `[{feature, scenarios[]}]` (array)
 - scenarios[]: `{name, tags[], given[], when[], then[]}`
 - FORBIDDEN: flat array of scenario objects without wrapping `feature`
 
@@ -525,7 +530,7 @@ Perform these structural checks before every write:
 
 **specification.navigation** — REQUIRED: `entries[]` where each: `{code, label, icon, route, parentCode, sort}`
 
-**specification.i18nKeys[]** — REQUIRED: `key`, `fr`, `en`, `nl`, `de`
+**specification.i18nKeys[]** — REQUIRED: `key`, `fr`, `en`, `it`, `de`
 
 **validation** — REQUIRED: `completenessChecks[]`, `consistencyChecks[]`, `semanticChecks[]`, `decision`
 - decision: `{approved, reason, checkedAt}`
@@ -718,7 +723,7 @@ After EVERY write, report file size status:
 
 ```
 ✓ feature.json written successfully
-  Path: docs/business/HumanResources/Projects/business-analyse/v1.0/feature.json
+  Path: docs/HumanResources/Projects/business-analyse/v1.0/feature.json
   Size: 87.3 KB (↑ 12.1 KB from previous)
   Status: ⚠ Approaching 100KB threshold
   Recommendation: Use enrichSectionIncremental for remaining modules

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

@@ -241,16 +241,16 @@ Load ONLY relevant categories based on feature type:
 | 07        | `questionnaire/07-ui.md`              | 19        | Si module oriente interface |
 | 08        | `questionnaire/08-performance.md`     | 8         | Si performance critique |
 | 09        | `questionnaire/09-constraints.md`     | 6         | Si contraintes |
-| 10        | `questionnaire/10-documentation.md`   | 7         | Si documentation requise |
+| 10        | `questionnaire/10-documentation.md`   | 7         | Toujours      |
 | 11        | `questionnaire/11-data-lifecycle.md`  | 14        | Si lifecycle requis (retention, archivage, RGPD) |
 | 12        | `questionnaire/12-migration.md`       | 14        | Si nouveau module (migration donnees existantes) |
 | 13        | `questionnaire/13-cross-module.md`    | 14        | Si nouveau module OU references autres modules |
 | 14        | `questionnaire/14-risk-assumptions.md`| 16        | Toujours      |
 | 15        | `questionnaire/15-success-metrics.md` | 17        | Toujours      |
 
-**Total noyau (toujours chargés) : 130 questions** (contexte, acteurs, périmètre, risques, métriques)
-**Total avec application : 148 questions** (+ identité application si mode multi-module)
-**Total conditionnel : 124 questions** (data, intégrations, sécurité, UI, performance, contraintes, doc, lifecycle, migration, cross-module)
+**Total noyau (toujours chargés) : 137 questions** (contexte, acteurs, périmètre, risques, métriques, documentation)
+**Total avec application : 155 questions** (+ identité application si mode multi-module)
+**Total conditionnel : 117 questions** (data, intégrations, sécurité, UI, performance, contraintes, lifecycle, migration, cross-module)
 **Total maximum possible : 272 questions** (noyau + application + tous conditionnels chargés)
 
 </questionnaire_files>

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

@@ -0,0 +1,142 @@
+# Business Analyse — Canonical Rules
+
+> **This file is the SINGLE SOURCE OF TRUTH for all rules referenced across step files.**
+> Step files MUST reference this file instead of duplicating rules.
+
+---
+
+## § ID Naming Convention
+
+All IDs MUST include a module prefix to guarantee application-wide uniqueness.
+The prefix is derived from the module code initials (2-4 chars):
+
+| Module | Prefix |
+|--------|--------|
+| UserManagement | UM |
+| VehicleManagement | VM |
+| PartsInventory | PI |
+| RepairManagement | RM |
+| MaintenanceSchedule | MS |
+| DataSync | DS |
+| Notifications | NT |
+| Dashboard | DB |
+| Orders | OR |
+| Customers | CU |
+
+**Patterns:**
+
+| ID Type | Pattern | Example |
+|---------|---------|---------|
+| Use Case | `UC-{PREFIX}-{NNN}` | UC-RM-001, UC-PI-003 |
+| Business Rule | `BR-{CAT}-{PREFIX}-{NNN}` | BR-VAL-RM-001, BR-CALC-PI-002 |
+| Functional Req | `FR-{PREFIX}-{NNN}` | FR-RM-001 |
+| Objective | `OBJ-{PREFIX}-{NNN}` | OBJ-RM-001 |
+| Acceptance Crit | `AC-{PREFIX}-{NNN}` | AC-RM-001 |
+| Risk | `RISK-{PREFIX}-{NNN}` | RISK-RM-001 |
+
+**NEVER use bare IDs** (UC-001, BR-VAL-001) in multi-module mode.
+
+---
+
+## § Schema Conformity
+
+ALL data MUST fit within the defined `feature-schema.json` structure.
+
+- NEVER create custom top-level fields (KPIDefinitions, ChartConfigurations, etc.)
+- Dashboard modules MUST use `specification.dashboards[]` (it exists in the schema).
+- If truly needed, use `specification.extensions: {}` (additionalProperties: true).
+
+---
+
+## § Auto-Fix: Wireframe Field Names
+
+Before writing wireframes to feature.json, normalize field names to canonical form.
+
+| Source field | Canonical field | Action |
+|---|---|---|
+| `title` | `screen` | Rename if `screen` absent |
+| `name` | `screen` | Rename if `screen` absent |
+| `ascii` | `mockup` | Rename if `mockup` absent |
+| `content` | `mockup` | Rename if `mockup` absent |
+
+After renaming, store wireframes under the canonical key `specification.uiWireframes`.
+
+---
+
+## § Auto-Fix: Entity Attribute Type Inference
+
+When an entity attribute is missing a `type` field, infer it from the attribute name pattern.
+
+| Pattern (attribute name) | Inferred type |
+|---|---|
+| `*name`, `*title`, `*code`, `*description`, `*label`, `*email`, `*phone`, `*address` | `string` |
+| `*Id` (suffix) | `Guid` |
+| `*date*`, `*At` (suffix) | `DateTime` |
+| `is*`, `has*`, `*active`, `*enabled` | `bool` |
+| `*amount`, `*salary`, `*rate`, `*price`, `*total` | `decimal` |
+| `*count`, `*number`, `*order`, `*sort`, `*index` | `int` |
+| (no match — default) | `string` |
+
+**Additional normalization:**
+- If `validation` contains `max {N}`, extract and set `maxLength = N`.
+- If `required` is undefined, default to `true`.
+
+---
+
+## § Minimum Counts (Authoritative)
+
+> **These are the AUTHORITATIVE minimums used across step-03d validation and robustness checks.**
+> When in doubt, use these values. They are the strictest (most correct) across all sources.
+
+| Section | Minimum | Blocking | Notes |
+|---|---|---|---|
+| `analysis.entities` | ≥ 2 | YES | Single-entity modules are rare and likely incomplete |
+| Entity attributes (each) | ≥ 3 | YES | Entities with < 3 attributes are incomplete |
+| `analysis.businessRules` | ≥ 4 | YES | Mix of VAL/CALC/WF/SEC/DATA |
+| BR categories | ≥ 2 | YES | Single-category modules likely incomplete |
+| `specification.useCases` | ≥ 6 | YES | CRUD (5) + 1 business-specific minimum |
+| `specification.functionalRequirements` | ≥ 4 | YES | FRs must cover key functionality |
+| UC-FR linkage | Every UC has ≥ 1 FR | YES | Orphan UCs indicate incomplete requirements |
+| `specification.actors` | ≥ 2 | YES | At least 2 roles with permissions |
+| `specification.permissionMatrix.permissions` | ≥ 5 | YES | CRUD (4) + 1 business action |
+| `specification.permissionMatrix.roleAssignments` | ≥ 2 | YES | All roles must have ≥ 1 permission |
+| `specification.sections` | ≥ 2 | YES | list + detail/form minimum |
+| Wireframes | 1 per section | YES | EVERY section MUST have a wireframe |
+| `specification.navigation.entries` | ≥ 1 | YES | Module must be accessible in menu |
+| `specification.seedDataCore` | All 9 arrays present | YES | Missing CORE data breaks deployment |
+| `specification.messages` | ≥ 4 | YES | 1 success, 1 error, 1 warning, 1 info |
+| `specification.validations` | ≥ 1 | YES | Modules need field validation rules |
+| `specification.apiEndpoints` | ≥ 5 | YES | CRUD (5) minimum |
+| `specification.i18nKeys` leaf count | ≥ 42 | YES | Entities, fields, messages, validation, navigation |
+| i18n languages per leaf | 4 (fr, en, it, de) | YES | Missing translations break multi-language |
+| `specification.gherkinScenarios` | ≥ 1 entry (array) | YES | Must be array, not single object |
+| Gherkin scenario count | ≥ 2 | NO (WARNING) | Enables automated testing |
+| `analysis.dataLifecycle` | present | YES | Missing causes BLOCKING errors downstream |
+
+**seedDataCore arrays (9 total):**
+1. `navigationApplications` — required for 1st module, can be `[]` for subsequent
+2. `applicationRoles` — required for 1st module, can be `[]` for subsequent
+3. `navigationModules` — min 1
+4. `navigationSections` — min 1
+5. `navigationResources` — min 1
+6. `navigationTranslations` — min 2 (fr + en)
+7. `permissions` — min 1
+8. `rolePermissions` — min 1
+9. `permissionConstants` — min 1
+
+---
+
+## § Format Checks
+
+These format rules apply to ALL modules (including the first). They validate canonical schema compliance.
+
+| Check | Rule | Auto-fix |
+|---|---|---|
+| Gherkin format | `gherkinScenarios` MUST be an **array** `[{feature, scenarios}]`, not a single object | Wrap single object in array |
+| Validation rules | `validations[].rules` MUST be an **array**, not a singular `rule` string | Convert string to `[string]`; rename `rule` → `rules` |
+| Message field | `messages[]` MUST have a `message` field (not only `description`) | Copy `description` → `message` if `message` absent |
+| Wireframe fields | Wireframes MUST use canonical field names (`screen`, `mockup`) | Apply § "Auto-Fix: Wireframe Field Names" table above |
+| Entity attributes | Entities MUST use `attributes[]` (not `fields[]`), no `tableName` or `primaryKey` | Structural error — must be fixed manually |
+| Entity attribute types | ALL attributes MUST have a `type` field | Apply § "Auto-Fix: Entity Attribute Type Inference" table above |
+| Navigation routes | FORBIDDEN: `/module/list` (use `/module`), `/module/detail/:id` (use `/module/:id`) | Rewrite route |
+| Permission paths | Dot-separated lowercase: module-level `{app}.{module}.{action}` (3 segments) or section-level `{app}.{module}.{section}.{action}` (4 segments) | — |

package/templates/skills/business-analyse/questionnaire/10-documentation.md

@@ -1,7 +1,7 @@
 # Category 10: Documentation & Support
 
 > **Usage:** Documentation and support needs
-> **When to load:** If documentation explicitly required
+> **When to load:** Toujours (chargé en step-01 §4g — every application requires documentation decisions)
 
 ---
 
@@ -9,10 +9,10 @@
 
 | # | Question | Answer Type |
 |---|----------|-------------|
-| Q10.1 | User documentation needed? | Yes/No + type |
-| Q10.2 | Technical documentation needed? | Yes/No + type |
-| Q10.3 | User training planned? | Plan |
-| Q10.4 | Knowledge base to create? | Scope |
+| Q10.1 | User documentation needed? (tooltips intégrés, guide pas-à-pas, FAQ, vidéo tutoriel) | Yes/No + format |
+| Q10.2 | Technical documentation needed? (API Swagger, ERD schéma données, guide développeur) | Yes/No + type |
+| Q10.3 | Who is responsible for maintaining documentation after delivery? | Person/Role |
+| Q10.4 | Knowledge base or training planned? (onboarding, wiki, release notes) | Scope + timeline |
 
 ---
 
@@ -20,12 +20,26 @@
 
 | Type | Generated by | Format |
 |------|-------------|--------|
-| Documentation module | `/documentation` (auto step-08) | React page intégrée via doc-data.ts + DocRenderer |
+| Documentation module | `/documentation` skill (après `/ralph-loop`) | React page intégrée via doc-data.ts + DocRenderer |
 | Swagger API | Automatic (Swashbuckle) | OpenAPI 3.0 |
 | User guide | Manual or AI | Markdown / PDF |
 | Release notes | `/gitflow finish` | Changelog automatique |
 | ERD (schéma données) | `/documentation` skill | Mermaid diagram |
 
+## Génération automatique
+
+| Livrable | Quand | Comment |
+|----------|-------|---------|
+| Swagger API | Automatique (ASP.NET Core + Swashbuckle) | Disponible à `/swagger` dès le déploiement |
+| ERD (schéma données) | Après `/ralph-loop` | Skill `/documentation` type ERD |
+| Module documentation | Après `/ralph-loop` | Skill `/documentation` type user-module |
+| Release notes | À chaque release | Skill `/gitflow finish` |
+| Tooltips in-app (doc-data.ts) | Pendant `/ralph-loop` | Catégorie `documentation` du PRD |
+
+> **Flux recommandé :** `/business-analyse` capture les besoins → `/ralph-loop` génère les fichiers de base (doc-data.ts) → `/documentation` génère ERD + guides complets → `/gitflow finish` génère release notes.
+
+---
+
 ## Elicitation Guide
 
 ### Follow-ups by Question
@@ -40,4 +54,5 @@
 
 | Signal | Anti-pattern | Action |
 |--------|-------------|--------|
-| "La doc se fera après" | **Documentation en dette** | Le feature.json EST la doc. `/documentation` la génère automatiquement au step-08. |
+| "La doc se fera après" | **Documentation en dette** | Le feature.json EST la doc. `/documentation` la génère automatiquement après `/ralph-loop`. |
+| "On n'a pas besoin de doc" | **Documentation inexistante** | Même sans guide utilisateur, Swagger + ERD sont générés automatiquement. Le skill `/documentation` ne coûte rien à lancer. |

package/templates/skills/business-analyse/references/acceptance-criteria.md

@@ -16,7 +16,7 @@ All previous checks were **pseudocode interpreted by the model**. The model can
 
 | # | Criterion | Minimum | Field Path | Blocking | Category |
 |---|-----------|---------|------------|----------|----------|
-| AC-01 | Entities present | 1 | `analysis.entities[]` | YES | Data Model |
+| AC-01 | Entities present | 2 | `analysis.entities[]` | YES | Data Model |
 | AC-02 | Entity attributes have `type` field | ALL | `analysis.entities[].attributes[].type` | YES | Data Model |
 | AC-03 | Use cases present | 2 | `specification.useCases[]` | YES | Requirements |
 | AC-04 | Functional requirements present | 4 | `specification.functionalRequirements[]` | YES | Requirements |
@@ -24,7 +24,7 @@ All previous checks were **pseudocode interpreted by the model**. The model can
 | AC-06 | Wireframes >= sections | count match | wireframes.length >= sections.length | YES | UI |
 | AC-07 | Wireframe content non-empty | ALL | `wireframe.mockup \|\| wireframe.ascii \|\| wireframe.content` | YES | UI |
 | AC-08 | Sections present | 1 | `specification.sections[]` | YES | UI |
-| AC-09 | SeedDataCore 7 arrays non-empty | 7/7 | `specification.seedDataCore.*` | YES | Seed Data |
+| AC-09 | SeedDataCore 9 arrays non-empty | 9/9 | `specification.seedDataCore.*` | YES | Seed Data |
 | AC-10 | Gherkin scenarios is array | `Array.isArray` | `specification.gherkinScenarios` | YES | Format |
 | AC-11 | API endpoints present | 1 | `specification.apiEndpoints[]` | YES | API |
 | AC-12 | Messages present | 4 | `specification.messages[]` | YES | Messages |
@@ -53,13 +53,13 @@ const sections = spec.sections || [];
 const sdc = spec.seedDataCore || {};
 
 const checks = [
-  ['AC-01: entities >= 1',          (analysis.entities||[]).length,               1],
+  ['AC-01: entities >= 2',          (analysis.entities||[]).length,               2],
   ['AC-03: useCases >= 2',          (spec.useCases||[]).length,                   2],
   ['AC-04: FRs >= 4',               (spec.functionalRequirements||[]).length,     4],
   ['AC-05: wireframes >= 1',        wf.length,                                    1],
   ['AC-06: wireframes >= sections', wf.length,                                    sections.length],
   ['AC-08: sections >= 1',          sections.length,                               1],
-  ['AC-09: seedDataCore 7 arrays',  Object.keys(sdc).filter(k => Array.isArray(sdc[k]) && sdc[k].length > 0).length, 7],
+  ['AC-09: seedDataCore 9 arrays',  Object.keys(sdc).filter(k => Array.isArray(sdc[k]) && sdc[k].length > 0).length, 9],
   ['AC-10: gherkin is array',       Array.isArray(spec.gherkinScenarios) ? 1 : 0,  1],
   ['AC-11: apiEndpoints >= 1',      (spec.apiEndpoints||[]).length,                1],
   ['AC-12: messages >= 4',          (spec.messages||[]).length,                    4],

package/templates/skills/business-analyse/references/agent-module-prompt.md

@@ -81,7 +81,7 @@ Reference their entities for FK relationships:
 Execute these steps IN ORDER. Each step is a separate file to load:
 
 ### Step 1: Setup (step-03a1-setup.md)
-Load: `templates/skills/business-analyse/steps/step-03a1-setup.md`
+Load: `~/.claude/skills/business-analyse/steps/step-03a1-setup.md`
 
 Execute sections 1-8 (skip AskUserQuestion calls — decide autonomously):
 - Determine current module from workflow state
@@ -99,7 +99,7 @@ Execute sections 1-8 (skip AskUserQuestion calls — decide autonomously):
 - Questionnaires: Skip (no user to ask) — use ULTRATHINK to cover key concerns
 
 ### Step 2: Analysis (step-03a2-analysis.md)
-Load: `templates/skills/business-analyse/steps/step-03a2-analysis.md`
+Load: `~/.claude/skills/business-analyse/steps/step-03a2-analysis.md`
 
 Execute sections for objectives, entities, business rules, process flow:
 - Define 2-4 objectives per module
@@ -120,7 +120,7 @@ Execute sections for objectives, entities, business rules, process flow:
   - reporting: configure → generate → view → export
 
 ### Step 3: UI Specification (step-03b-ui.md)
-Load: `templates/skills/business-analyse/steps/step-03b-ui.md`
+Load: `~/.claude/skills/business-analyse/steps/step-03b-ui.md`
 
 Execute: state machines, wireframes, layouts:
 - Define lifecycle state machine (if entity has status)
@@ -140,14 +140,14 @@ Execute: state machines, wireframes, layouts:
 - Layouts: Always use standard SmartStack responsive grid
 
 ### Step 4: Compile (step-03c-compile.md)
-Load: `templates/skills/business-analyse/steps/step-03c-compile.md`
+Load: `~/.claude/skills/business-analyse/steps/step-03c-compile.md`
 
 Execute ALL compilation sections:
 - Actors (2+ per module)
 - Use Cases with Gherkin scenarios
 - Functional Requirements
 - Permission matrix (CRUD per entity + module admin)
-- Navigation seed data (7 arrays — CRITICAL)
+- Navigation seed data (9 arrays — CRITICAL)
 - i18n keys (4 languages: fr, en, it, de)
 - API endpoints summary
 
@@ -163,14 +163,18 @@ Execute ALL compilation sections:
 9. permissionConstants (C# constant names)
 
 ### Step 5: Validate & Propose (step-03d-validate.md)
-Load: `templates/skills/business-analyse/steps/step-03d-validate.md`
+Load: `~/.claude/skills/business-analyse/steps/step-03d-validate.md`
 
 Execute validation checks, write to feature.json, then send proposal:
 1. Run ALL completeness checks from step-03d section 9
 2. Fix any FAIL checks before proceeding
 3. Write module feature.json via ba-writer
-4. Build structured summary (see Communication Protocol below)
-5. Send PROPOSAL_READY to team lead
+4. Run POST-CHECK verifications (sections 11-POST-CHECK and 11-POST-CHECK-BASH)
+5. Build structured summary (see Communication Protocol below)
+6. Send PROPOSAL_READY to team lead
+
+> **Note:** Section 11-bis (incremental HTML deployment) is handled by the **team lead** after module approval.
+> You do NOT need to deploy the HTML — focus on validation, writing feature.json, and sending the proposal.
 
 ## Communication Protocol
 
@@ -349,7 +353,7 @@ NEVER use bare IDs (UC-001, BR-VAL-001) — always prefixed.
 - [ ] All FK fields are Guid type with navigation property
 - [ ] All sections have at least 1 resource
 - [ ] All sections have a wireframe (+ create/edit wireframes for data-centric sections)
-- [ ] seedDataCore has all 7 arrays with content
+- [ ] seedDataCore has all 9 arrays with content
 - [ ] Permissions follow {app}.{module}.{entity}.{action} pattern
 - [ ] i18n has all keys in **4 languages (fr, en, it, de)** — not just fr/en
 - [ ] At least 2 actors, 2 use cases, 4 functional requirements

package/templates/skills/business-analyse/references/consolidation-structural-checks.md

@@ -19,9 +19,9 @@
 | `specification.sections[]` | YES | Must have >=1 section with resources |
 | `specification.uiWireframes[]` | YES | Must have >=1 wireframe with `layout` object |
 | `specification.lifeCycles[]` | IF entities have status | States must be objects (NOT strings) |
-| `specification.seedDataCore` | YES | Must have 7 arrays: navigationModules, navigationSections, navigationResources, navigationTranslations, permissions, rolePermissions, permissionConstants |
+| `specification.seedDataCore` | YES | Must have 9 arrays: navigationApplications, applicationRoles, navigationModules, navigationSections, navigationResources, navigationTranslations, permissions, rolePermissions, permissionConstants |
 | `specification.seedDataBusiness` | NO (WARNING) | Business seed data is generated during implementation (ralph-loop), not during BA. If present, validates format. |
-| `specification.gherkinScenarios` | YES | Must be `{feature, scenarios[]}` (NOT flat array) |
+| `specification.gherkinScenarios` | YES | Must be `[{feature, scenarios[]}]` (array of objects, NOT single object or flat array) |
 | `specification.navigation` | YES | Must have entries[] |
 | `specification.i18nKeys[]` | YES | Must have >=1 key with fr, en, it, de |
 | `validation` | YES | Must have completenessChecks, consistencyChecks, semanticChecks, decision |

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

@@ -1,6 +1,7 @@
 # FEATURE_DATA & EMBEDDED_ARTIFACTS Build Reference
 
 > Reference for step-05b-deploy.md — complete mapping specification for the interactive HTML.
+> **Canonical field mapping reference:** See also `html-data-mapping.md` for the authoritative field name mapping between feature.json and HTML data objects.
 
 ## FEATURE_DATA Object
 
@@ -84,12 +85,12 @@ const FEATURE_DATA = {
           : (ent.fields || []).filter(f => f.foreignKey)
               .map(f => `${f.foreignKey.table} (N:1) - ${f.description || f.name}`)
       })),
-      permissions: module.specification.permissions || [],
+      permissions: module.specification.permissionMatrix?.permissions || [],
       apiEndpoints: module.specification.apiEndpoints || []
     }
   },
   consolidation: {
-    integrations: master.consolidation.integrations || [],
+    integrations: master.consolidation.crossModuleInteractions || [],
     sharedEntities: master.consolidation.sharedEntities || [],
     sequenceDiagrams: master.consolidation.e2eFlows || []
   },

package/templates/skills/business-analyse/references/prd-generation.md

@@ -52,7 +52,8 @@ Fix: Re-run ss derive-prd with latest version
       "api": [...],
       "frontend": [...],
       "seedData": [...],
-      "tests": [...]
+      "tests": [...],
+      "documentation": [...]
     }
   }
 }
@@ -79,9 +80,9 @@ ss derive-prd --feature {path} --output .ralph/prd-{moduleCode}.json
 
 ---
 
-### 3. Seven Categories (MANDATORY)
+### 3. Eight Categories (MANDATORY)
 
-All PRD files MUST include these 7 categories under `implementation.filesToCreate`:
+All PRD files MUST include these 8 categories under `implementation.filesToCreate`:
 
 | Category | Description | Examples |
 |----------|-------------|----------|
@@ -92,10 +93,13 @@ All PRD files MUST include these 7 categories under `implementation.filesToCreat
 | **frontend** | React pages, components, hooks | `ProjectsPage.tsx`, `useProjects.ts` |
 | **seedData** | Seed data classes | `ProjectSeedData.cs` |
 | **tests** | Unit tests, integration tests | `ProjectServiceTests.cs`, `ProjectsControllerTests.cs` |
+| **documentation** | Technical docs, user guides, API specs | `doc-data.ts`, `UserGuide.md`, `api-spec.yaml` |
+
+> **Note `documentation`:** Cette catégorie peut contenir des fichiers générés par le skill `/documentation` après `/ralph-loop`. Elle est obligatoire dans la structure PRD (peut être un tableau vide `[]` si aucune doc n'est prévue, mais DOIT être présente).
 
 **Validation:**
 ```javascript
-const categories = ['domain', 'application', 'infrastructure', 'api', 'frontend', 'seedData', 'tests'];
+const categories = ['domain', 'application', 'infrastructure', 'api', 'frontend', 'seedData', 'tests', 'documentation'];
 const missingCategories = categories.filter(cat => !prd.implementation.filesToCreate[cat]);
 
 if (missingCategories.length > 0) {
@@ -106,7 +110,8 @@ if (missingCategories.length > 0) {
 **Common Errors:**
 - Missing `tests` category → often forgotten
 - Missing `seedData` category → sometimes omitted for modules without seed data
-- Empty arrays allowed (e.g., `"seedData": []`) if genuinely no files needed
+- Missing `documentation` category → must be present even if empty
+- Empty arrays allowed (e.g., `"seedData": []`, `"documentation": []`) if genuinely no files needed
 
 ---
 
@@ -116,7 +121,7 @@ if (missingCategories.length > 0) {
 
 ```javascript
 const featureHandoff = moduleFeature.handoff.filesToCreate;
-const categories = ['domain', 'application', 'infrastructure', 'api', 'frontend', 'seedData', 'tests'];
+const categories = ['domain', 'application', 'infrastructure', 'api', 'frontend', 'seedData', 'tests', 'documentation'];
 
 for (const cat of categories) {
   const prdCount = prd.implementation.filesToCreate[cat]?.length ?? 0;
@@ -170,7 +175,7 @@ Use this checklist when validating PRD files:
 |-------|-----------|--------|
 | **Version** | `$version === "3.0.0"` | PASS/FAIL |
 | **Structure** | `implementation.filesToCreate` exists (not root) | PASS/FAIL |
-| **Categories** | All 7 categories present | PASS/FAIL |
+| **Categories** | All 8 categories present | PASS/FAIL |
 | **File Counts** | PRD counts match feature.json handoff | PASS/FAIL |
 | **File Schemas** | All files have path, type, module | PASS/FAIL |
 
@@ -194,12 +199,12 @@ BLOCKING_ERROR: filesToCreate is at ROOT level (wrong structure)
 
 ### Error 3: Missing Categories
 ```
-BLOCKING_ERROR: Missing categories: seedData, tests
+BLOCKING_ERROR: Missing categories: seedData, tests, documentation
 ```
 **Fix:**
-- Check feature.json handoff.filesToCreate has all 7 categories
+- Check feature.json handoff.filesToCreate has all 8 categories
 - Re-derive PRD after fixing feature.json
-- If genuinely no files needed, use empty array: `"seedData": []`
+- If genuinely no files needed, use empty array: `"seedData": []`, `"documentation": []`
 
 ### Error 4: File Count Mismatch
 ```

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

@@ -1,5 +1,6 @@
 # Robustness Checks for Business Analysis
 
+> **Authoritative minimums:** See `_rules.md` § "Minimum Counts" for the single source of truth on all minimum thresholds.
 > **Objective:** Prevent incomplete specifications and broken references from reaching development.
 
 ## Overview
@@ -74,17 +75,19 @@ Ensures each module has ALL required components before being marked as "specifie
 
 | # | Check | Minimum | Blocking | Rationale |
 |---|-------|---------|----------|-----------|
-| 7.1 | CORE seed data sections | All 7 sections present | YES | Missing CORE data breaks deployment |
+| 7.1 | CORE seed data arrays | All 9 arrays present (per `_rules.md` § "Minimum Counts") | YES | Missing CORE data breaks deployment |
 | 7.2 | Business seed data | Template defined | NO (WARNING) | Helps with testing |
 
-**CORE sections required:**
-1. `navigationModules`
-2. `navigationSections`
-3. `navigationResources`
-4. `navigationTranslations`
-5. `permissions`
-6. `rolePermissions`
-7. `permissionConstants`
+**CORE arrays required (9 total — see `_rules.md` § "seedDataCore arrays"):**
+1. `navigationApplications` — required for 1st module, can be `[]` for subsequent
+2. `applicationRoles` — required for 1st module, can be `[]` for subsequent
+3. `navigationModules`
+4. `navigationSections`
+5. `navigationResources`
+6. `navigationTranslations`
+7. `permissions`
+8. `rolePermissions`
+9. `permissionConstants`
 
 #### SECTION 8: API Endpoints (2 checks)