@atlashub/smartstack-cli 1.36.0 → 2.0.0

package/templates/skills/business-analyse/questionnaire/11-data-lifecycle.md

@@ -25,9 +25,9 @@
 
 ---
 
-## SmartStack Lifecycle Patterns
+## Lifecycle Patterns
 
-| Need | SmartStack Pattern | Impact |
+| Need | Platform Pattern | Impact |
 |------|-------------------|--------|
 | Soft delete | `SoftDeletableEntity` | IsDeleted, DeletedBy, DeletedDate auto-managed |
 | Audit trail | `AuditableEntity` | CreatedBy/Date, ModifiedBy/Date auto-managed |

package/templates/skills/business-analyse/questionnaire/12-migration.md

@@ -25,7 +25,7 @@
 
 ---
 
-## SmartStack Migration Patterns
+## Migration Patterns
 
 | Need | Pattern | Tool |
 |------|---------|------|

package/templates/skills/business-analyse/questionnaire/13-cross-module.md

@@ -25,7 +25,7 @@
 
 ---
 
-## SmartStack Cross-Module Patterns
+## Cross-Module Patterns
 
 | Need | Pattern | Example |
 |------|---------|---------|
@@ -56,7 +56,7 @@
 | Module totalement isolé | **Silo de données** | Rare qu'un module métier n'ait aucune connexion. Vérifier avec le codebase context. |
 | Duplication d'entité existante | **Entité dupliquée** | Si `Client` existe déjà, ne pas créer `Customer`. Référencer l'existant. |
 | Modification d'entité d'un autre module | **Couplage fort** | Utiliser des événements (MediatR) plutôt que des modifications directes. |
-| Aucune mention de navigation | **Module orphelin dans l'UI** | Le module doit apparaître dans le menu SmartStack (NavRoute). |
+| Aucune mention de navigation | **Module orphelin dans l'UI** | Le module doit apparaître dans le menu de l'application (NavRoute). |
 
 ### Using Pre-Research Context
 

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

@@ -40,6 +40,11 @@ Read `{output_dir}/digest-00.md` for compressed context from step-00.
 > doit être dans `{language}`. Les exemples ci-dessous sont en français — adapter si `{language}` ≠ `fr`.
 > Voir `_shared.md` → "Configuration Langue de Communication" pour les règles complètes.
 
+> **⚠️ BRANDING :** Ne JAMAIS utiliser le mot "SmartStack" dans les communications utilisateur
+> (questions, résumés, reformulations, synthèses). Utiliser "la plateforme", "l'application",
+> ou "le système" à la place. SmartStack est le nom interne du framework — le projet client
+> a son propre nom. Les références techniques internes (paths, MCP calls) restent inchangées.
+
 ---
 
 ### 2. Determine Feature Type
@@ -245,21 +250,21 @@ AskUserQuestion([
       { label: "Revenus", description: "Impact direct sur le chiffre d'affaires" },
       { label: "Qualitatif", description: "Satisfaction, conformité, image — non chiffrable" }
     ], multiSelect: true },
-  { question: "Que se passe-t-il si ce module n'est PAS développé ?",
-    header: "Sans module",
+  { question: "Quel est le déclencheur de ce besoin ?",
+    header: "Déclencheur",
     options: [
-      { label: "Bloquant", description: "Impossible de continuer sans (réglementaire, technique)" },
-      { label: "Dégradé", description: "On continue avec l'existant mais avec des inefficacités" },
-      { label: "Risque", description: "Risque croissant (erreurs, perte de données, non-conformité)" },
-      { label: "Confort", description: "Pas d'impact critique, amélioration de confort" }
+      { label: "Urgence opérationnelle", description: "Processus bloqué ou inefficace au quotidien" },
+      { label: "Obligation réglementaire", description: "Conformité imposée par une deadline externe" },
+      { label: "Évolution planifiée", description: "Amélioration prévue dans la roadmap" },
+      { label: "Opportunité", description: "Gain identifié, pas de contrainte immédiate" }
     ], multiSelect: false },
-  { question: "Priorité par rapport aux autres besoins ?",
-    header: "Priorité",
+  { question: "Quel est le délai souhaité de mise en production ?",
+    header: "Délai",
     options: [
-      { label: "Critique", description: "Doit être livré en premier, bloque d'autres projets" },
-      { label: "Haute", description: "Important mais pas bloquant" },
-      { label: "Moyenne", description: "Souhaité mais peut attendre" },
-      { label: "Basse", description: "Nice-to-have" }
+      { label: "Urgent (< 1 mois)", description: "Besoin immédiat, bloquant des opérations" },
+      { label: "Court terme (1-3 mois)", description: "Planifié pour le prochain cycle" },
+      { label: "Moyen terme (3-6 mois)", description: "Important mais pas immédiat" },
+      { label: "Flexible", description: "Pas de contrainte de délai définie" }
     ], multiSelect: false }
 ])
 ```
@@ -301,7 +306,7 @@ AskUserQuestion([
 
 **ULTRATHINK checkpoint:**
 - If only 1-2 user types → probe with Technique 5: "Et les auditeurs, le support, les processus automatisés ?"
-- If no "Admin" → SmartStack requires admin role, clarify
+- If no "Admin" → The platform requires an admin role, clarify
 - If "Externe" → follow-up: portal, API, or shared access?
 
 **Batch 2 — Needs per role (Q2.5-Q2.8):**
@@ -361,20 +366,20 @@ AskUserQuestion([
       { label: "Historique/Audit", description: "Historique détaillé des modifications" },
       { label: "Intégrations", description: "Connexion avec d'autres modules/systèmes" }
     ], multiSelect: true },
-  { question: "Qu'est-ce qui est EXCLU du périmètre ?",
-    header: "Exclusions",
+  { question: "Y a-t-il des limites connues pour la v1 ?",
+    header: "Limites v1",
     options: [
-      { label: "Mobile", description: "Pas d'accès mobile pour la v1" },
-      { label: "Reporting avancé", description: "Pas de rapports complexes ou BI" },
-      { label: "Multi-langue contenu", description: "UI i18n, mais pas le contenu métier" },
-      { label: "Rien d'exclu", description: "Pas d'exclusion explicite" }
+      { label: "Pas de limite identifiée", description: "Le périmètre sera défini par les Must-Have et Should-Have" },
+      { label: "Budget/temps limité", description: "Contrainte qui pourrait réduire le périmètre" },
+      { label: "Dépendance externe", description: "Certaines fonctions dépendent d'un autre système pas encore prêt" },
+      { label: "Complexité technique", description: "Certaines fonctions nécessitent une phase de R&D" }
     ], multiSelect: true }
 ])
 ```
 
 **ULTRATHINK checkpoint:**
-- If "Rien d'exclu" → anti-pattern "Scope illimité" → probe exclusions
-- If > 5 Must-Have → "Sans cette fonctionnalité, le module a ZÉRO valeur ?"
+- If > 5 Must-Have → "Parmi ces fonctionnalités, lesquelles apportent le plus de valeur pour la v1 ?"
+- If "Pas de limite identifiée" → accept as valid, scope will be naturally bounded by Must-Have/Should-Have
 
 **Batch 2 — Process flow (Q3.5-Q3.8):**
 
@@ -426,14 +431,28 @@ Document each response with:
 #### 5.5 Reformulation Loop (AFTER EACH CATEGORY)
 
 > **RULE: After each category, reformulate understanding and validate with user.**
+> **IMPORTANT: The `question` field of `AskUserQuestion` does NOT support markdown or line breaks.**
+> **NEVER put long summaries in the `question` field — it becomes an unreadable wall of text.**
+
+After completing a category's batches:
+
+**Step 1: Display the summary as regular text output** (supports markdown formatting):
+
+```
+Output text directly to the user:
 
-After completing a category's batches, display a concise summary and ask for validation:
+## Synthèse - {category_name}
+
+- **Point 1:** {résumé}
+- **Point 2:** {résumé}
+- **Point 3:** {résumé}
+```
+
+**Step 2: Ask for validation with a SHORT question** (no summary in the question field):
 
 ```
 AskUserQuestion([
-  { question: "Voici ce que j'ai compris pour {category_name}:
-    {bullet_point_summary}
-    Est-ce correct ?",
+  { question: "Cette synthèse est-elle correcte ?",
     header: "Validation",
     options: [
       { label: "Correct", description: "La compréhension est fidèle, on continue" },
@@ -443,6 +462,12 @@ AskUserQuestion([
 ])
 ```
 
+> **⚠️ FORMATTING RULE for `AskUserQuestion`:**
+> Le champ `question` ne supporte PAS le markdown ni les retours à la ligne.
+> Une question simple reste lisible meme longue. Mais ne JAMAIS mettre de contenu
+> structuré (listes à puces, résumés multi-points, tableaux) dans le champ `question`.
+> Pour du contenu structuré → afficher en **texte direct** AVANT l'appel (voir `_shared.md`).
+
 - If **"Correct"** → proceed to next category
 - If **"Partiellement"** → ask: "Quelles corrections ou nuances souhaitez-vous apporter ?" (free text follow-up)
 - If **"Incorrect"** → re-ask the category with refined questions based on feedback

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

@@ -359,56 +359,125 @@ mkdir -p .ralph/reports
 
 **ULTRATHINK about task decomposition:**
 - Each task must be atomic (implementable in one Ralph iteration)
-- Tasks follow the SmartStack layer order: Domain → Application → Infrastructure → API → Frontend → Tests → Validation
+- Tasks follow the SmartStack layer order: Domain → Application → Infrastructure → API → Frontend → i18n → Tests → Validation
 - Conditionally include tasks based on feature scope (skip layers not present in the handoff document)
+- Each task MUST include `category`, `dependencies`, and `acceptance_criteria` (schema v2)
 
-**Conditional Task Generation Rules:**
+**Granularity Rules:**
+- 1 task per entity (domain, EF config, unit tests)
+- 1 task per entity for CQRS (commands + queries + DTOs grouped per entity)
+- 1 task per controller (API)
+- 1 task per page (frontend)
+- Max 1 entity per task — do NOT group multiple entities into a single task
+- Enums and shared value objects can be grouped in 1 task if they belong to the same module
+
+**Conditional Task Generation Rules (v2 schema):**
 
 For each layer, generate tasks ONLY if the handoff document contains specifications for that layer.
+Each task must have: `id`, `description`, `status: "pending"`, `category`, `dependencies`, `acceptance_criteria`.
 
 ```
 LAYER 1 - DOMAIN (if entities defined in handoff section 3/4):
-  Task: "Create {Entity} entity in SmartStack.Domain/Entities/Business/ with properties: {property_list}"
-  Task: "Create {Entity}Status enum if status workflow defined"
-  (One task per entity)
+  Task per entity:
+    description: "Create {Entity} entity in Domain/Entities/Business/ with properties: {property_list}"
+    category: "domain"
+    dependencies: []
+    acceptance_criteria: "Entity compiles, properties match handoff spec, correct base class (SoftDeletableEntity/AuditableEntity)"
+  Task (if enums needed):
+    description: "Create domain enums for {Module}: {EnumList} in Domain/Enums/{Module}/"
+    category: "domain"
+    dependencies: []
+    acceptance_criteria: "Enums compile, values match handoff spec"
 
 LAYER 2 - APPLICATION (if CQRS handlers defined in handoff section 3/4):
-  Task: "Create CQRS Commands for {Entity}: {Create/Update/Delete}Command + Handler + Validator"
-  Task: "Create CQRS Queries for {Entity}: GetAll{Entity}Query, Get{Entity}ByIdQuery + Handlers"
-  Task: "Create DTOs for {Entity}: {Entity}Dto, Create{Entity}Request, Update{Entity}Request"
-  Task: "Register permissions in Permissions.cs and PermissionConfiguration.cs for business.{app}.{module}"
+  Task per entity:
+    description: "Create CQRS for {Entity}: Commands ({Create/Update/Delete}Command + Handlers), Queries (GetAll/GetById + Handlers), DTOs ({Entity}Dto, Create/UpdateRequest), Validator"
+    category: "application"
+    dependencies: [ID of corresponding DOMAIN task for this entity]
+    acceptance_criteria: "Handlers compile, validators defined with business rules, DTOs match handoff properties"
+  Task (once per module):
+    description: "Register permissions in Permissions.cs and PermissionConfiguration.cs for business.{app}.{module}"
+    category: "application"
+    dependencies: [IDs of ALL application tasks for this module]
+    acceptance_criteria: "Permissions compile, HasData seed includes all permissions from handoff"
 
 LAYER 3 - INFRASTRUCTURE (if EF Core config or services in handoff):
-  Task: "Create EF Core configuration for {Entity} with HasData seed and migration"
-  Task: "Register {Entity} DbSet in ApplicationDbContext"
-  Task: "Create {Entity}Service implementing I{Entity}Service with DI registration" (if services needed)
+  Task per entity:
+    description: "Create EF Core configuration for {Entity} with indexes, relationships, and schema"
+    category: "infrastructure"
+    dependencies: [ID of corresponding DOMAIN task for this entity]
+    acceptance_criteria: "Configuration compiles, DbSet registered in DbContext, indexes match handoff"
+  Task (once per module):
+    description: "Create EF Core migration for {Module} entities"
+    category: "infrastructure"
+    dependencies: [IDs of ALL EF Core configuration tasks]
+    acceptance_criteria: "Migration applies without errors, 3 files present (Migration.cs, Designer.cs, ModelSnapshot.cs)"
+  Task per service (if services needed):
+    description: "Create {Service} implementing I{Service} with DI registration"
+    category: "infrastructure"
+    dependencies: [IDs of relevant DOMAIN + APPLICATION tasks]
+    acceptance_criteria: "Service compiles, registered in DI, follows existing patterns"
 
 LAYER 4 - API (if endpoints defined in handoff section 8):
-  Task: "Create {Module}Controller with CRUD endpoints: GET, POST, GET/{id}, PUT/{id}, DELETE/{id}"
+  Task per controller:
+    description: "Create {Entity}Controller with endpoints: {endpoint list} and [NavRoute] + [Authorize] attributes"
+    category: "api"
+    dependencies: [IDs of APPLICATION tasks for this entity + INFRASTRUCTURE migration task]
+    acceptance_criteria: "Controller compiles, endpoints respond, Swagger displays all routes"
 
 LAYER 5 - FRONTEND (if frontend files in handoff section 5):
-  Task: "Create {module}Api.ts API service with Axios calls"
-  Task: "Create use{Module}.ts hook with React Query + SignalR"
-  Task: "Create {Module}Page.tsx list page with EntityCard"
-  Task: "Create {Module}Form.tsx create/edit form"
-  Task: "Add routes in App.tsx for business/{app}/{module}"
+  Task (API service):
+    description: "Create {module}Api.ts API service with Axios calls for all endpoints"
+    category: "frontend"
+    dependencies: [IDs of ALL API controller tasks]
+    acceptance_criteria: "API service compiles, all endpoints covered, types match DTOs"
+  Task per page:
+    description: "Create {PageName}.tsx with {description of page content}"
+    category: "frontend"
+    dependencies: [ID of frontend API service task]
+    acceptance_criteria: "Page renders, API calls work, navigation functional"
+  Task (routes):
+    description: "Add routes in App.tsx for business/{app}/{module} and register in navigation"
+    category: "frontend"
+    dependencies: [IDs of ALL frontend page tasks]
+    acceptance_criteria: "Routes resolve, navigation links appear in menu"
 
 LAYER 6 - I18N (if i18n keys in handoff section 10):
-  Task: "Create i18n translation files for {module} in 4 languages (fr, en, it, de)"
+  Task:
+    description: "Create i18n translation files for {module} in 4 languages (fr, en, it, de)"
+    category: "i18n"
+    dependencies: [IDs of frontend page tasks]
+    acceptance_criteria: "4 language files created, all keys from handoff present, no missing translations"
 
 LAYER 7 - TESTS (always included):
-  Task: "Create unit tests: {Entity}ValidatorTests + {Entity}Tests"
-  Task: "Create integration tests: {Module}ControllerTests with 200, 201, 400, 403, 404 scenarios"
+  Task per entity:
+    description: "Create unit tests for {Entity}: {Entity}ValidatorTests + {Entity}Tests (entity methods)"
+    category: "test"
+    dependencies: [ID of APPLICATION task for this entity]
+    acceptance_criteria: "Tests pass, validator rules covered, entity methods tested"
+  Task per controller:
+    description: "Create integration tests for {Entity}Controller: 200, 201, 400, 403, 404 scenarios"
+    category: "test"
+    dependencies: [ID of API task for this controller]
+    acceptance_criteria: "Tests pass, all status codes covered, permission denial tested"
 
 LAYER 8 - VALIDATION (always included):
-  Task: "Run dotnet build, pnpm build, dotnet test - fix any failures"
-  Task: "Run MCP validate_conventions to verify all naming conventions"
+  Task 1:
+    description: "Run dotnet build + dotnet test - fix any build errors or test failures"
+    category: "validation"
+    dependencies: [IDs of ALL test tasks]
+    acceptance_criteria: "Build succeeds, all tests pass"
+  Task 2:
+    description: "Run MCP validate_conventions to verify all naming and structural conventions"
+    category: "validation"
+    dependencies: [ID of validation task 1]
+    acceptance_criteria: "MCP validation clean, no convention violations"
 ```
 
 **Sizing rules:**
-- Simple feature (1 entity, CRUD only): ~8-12 tasks
-- Medium feature (2-3 entities, business rules): ~15-20 tasks
-- Complex feature (multiple entities, integrations): ~20-30 tasks
+- Simple feature (1 entity, CRUD only): ~10-15 tasks
+- Medium feature (2-3 entities, business rules): ~18-25 tasks
+- Complex feature (multiple entities, integrations): ~25-35 tasks
 
 #### 12bis.3 Write prd.json
 
@@ -416,20 +485,50 @@ Write to: `.ralph/prd.json`
 
 ```json
 {
+  "$version": "2.0.0",
   "feature": "{feature_id} - {feature_description}",
+  "status": "pending",
   "created": "{ISO 8601 timestamp}",
-  "max_iterations": 30,
-  "completion_promise": "IMPLEMENTATION COMPLETE",
-  "current_iteration": 1,
-  "source": "{output_dir}/4-development-handoff.md",
+  "updated_at": "{ISO 8601 timestamp}",
+  "metadata": {
+    "cli_version": "{version from package.json}",
+    "branch": "{current git branch}",
+    "project_path": "{cwd}",
+    "mcp_servers": { "smartstack": true, "context7": true }
+  },
+  "config": {
+    "max_iterations": 30,
+    "completion_promise": "IMPLEMENTATION COMPLETE",
+    "current_iteration": 1
+  },
+  "source": {
+    "type": "ba-handoff",
+    "handoff_path": "{output_dir}/4-development-handoff.md",
+    "frd_path": "{output_dir}/3-functional-specification.md",
+    "brd_path": "{output_dir}/2-business-requirements.md"
+  },
   "tasks": [
-    { "id": 1, "description": "...", "passes": false },
-    { "id": 2, "description": "...", "passes": false }
-  ]
+    {
+      "id": 1,
+      "description": "Create {Entity} entity in Domain layer with properties: {list}",
+      "status": "pending",
+      "category": "domain",
+      "dependencies": [],
+      "acceptance_criteria": "Entity compiles, properties match handoff spec",
+      "started_at": null,
+      "completed_at": null,
+      "iteration": null,
+      "commit_hash": null,
+      "files_changed": { "created": [], "modified": [] },
+      "validation": null,
+      "error": null
+    }
+  ],
+  "history": []
 }
 ```
 
-> **Note:** The `source` field links back to the handoff document for reference. It is not read by Ralph's execution engine and is backward-compatible.
+> **Schema v2.0.0** — Compatible avec ralph-loop step-01 sans migration. Chaque tache inclut `category`, `dependencies` et `acceptance_criteria` pour un pilotage precis de l'execution.
 
 #### 12bis.4 Initialize progress.txt
 

package/templates/skills/cc-agent/SKILL.md

@@ -0,0 +1,129 @@
+---
+name: cc-agent
+description: |
+  Create or update Claude Code agents (subagents) based on official documentation.
+  Use this skill when:
+  - Creating a new specialized agent
+  - Updating an agent's tools, model, or permissions
+  - Adding skills to an agent
+argument-hint: "<create|update> [name] [--scope project|global|templates]"
+disable-model-invocation: true
+---
+
+<objective>
+Create or update Claude Code agents (subagents) following official conventions. Guides the user through agent design, generates properly structured .md files, and validates the result.
+</objective>
+
+<quick_start>
+
+```bash
+# Create a new agent
+/cc-agent create my-agent
+/cc-agent create my-agent --scope project
+/cc-agent create my-agent --scope global
+/cc-agent create my-agent --scope templates
+
+# Update an existing agent
+/cc-agent update my-agent
+/cc-agent update my-agent --scope global
+```
+
+</quick_start>
+
+<parameters>
+
+<subcommands>
+| Command | Description | Workflow |
+|---------|-------------|----------|
+| `create` | Create a new agent from scratch | init → design → generate → validate |
+| `update` | Update an existing agent | init → analyze → apply → validate |
+</subcommands>
+
+<flags>
+| Flag | Description |
+|------|-------------|
+| `--scope project` | Target `.claude/agents/` (default) |
+| `--scope global` | Target `~/.claude/agents/` |
+| `--scope templates` | Target `templates/agents/` (SmartStack CLI) |
+| `--category <name>` | Place in subdirectory (e.g., efcore, gitflow) |
+</flags>
+
+<examples>
+```bash
+# Create a standalone agent
+/cc-agent create test-runner
+
+# Create a categorized agent
+/cc-agent create migration --category efcore --scope templates
+
+# Update an existing agent
+/cc-agent update code-reviewer
+
+# Create agent for SmartStack templates
+/cc-agent create my-validator --scope templates
+```
+</examples>
+
+</parameters>
+
+<workflow>
+**Create flow:**
+1. Parse subcommand, name, scope, category
+2. Design agent (model, tools, permissions, skills)
+3. Generate agent .md file
+4. Validate structure and conventions
+
+**Update flow:**
+1. Parse subcommand, name, scope
+2. Read and analyze existing agent
+3. Apply requested changes
+4. Validate structure and conventions
+</workflow>
+
+<state_variables>
+| Variable | Type | Description |
+|----------|------|-------------|
+| `{subcommand}` | string | create or update |
+| `{agent_name}` | string | Agent name (unique identifier) |
+| `{scope}` | string | project, global, or templates |
+| `{target_dir}` | string | Resolved target directory |
+| `{category}` | string | Subdirectory (null for standalone) |
+| `{description}` | string | Agent description |
+| `{model}` | string | haiku, sonnet, opus, or inherit |
+| `{tools}` | string | Comma-separated tool list |
+| `{disallowed_tools}` | string | Blocked tools |
+| `{permission_mode}` | string | Permission handling mode |
+| `{preloaded_skills}` | string[] | Skills to inject at startup |
+| `{system_prompt}` | string | Agent's system prompt content |
+</state_variables>
+
+<entry_point>
+
+**FIRST ACTION:** Load `steps/step-00-init.md`
+
+</entry_point>
+
+<step_files>
+| Step | File | Purpose |
+|------|------|---------|
+| 00 | `steps/step-00-init.md` | Parse subcommand, name, scope, resolve target |
+| 01 | `steps/step-01-design.md` | Design agent (model, tools, permissions, skills) |
+| 02 | `steps/step-02-generate.md` | Generate agent .md file from template |
+| 03 | `steps/step-03-validate.md` | Validate format and display summary |
+</step_files>
+
+<execution_rules>
+- **Load one step at a time** - Progressive loading
+- **Ask before generating** - Confirm design choices with user
+- **Use templates** - Load from `templates/` directory for generation
+- **Follow official conventions** - Based on Claude Code documentation
+- **Validate at the end** - Check generated file
+</execution_rules>
+
+<success_criteria>
+- Agent .md file created with valid frontmatter
+- Description is clear enough for Claude to decide when to delegate
+- Tools are appropriate for the agent's purpose
+- Permission mode matches the agent's risk level
+- Agent follows official Claude Code conventions
+</success_criteria>