@atlashub/smartstack-cli 4.18.0 → 4.19.0

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

@@ -1,115 +0,0 @@
-# Cadrage: Pre-Analysis Reference
-
-> Reference for step-01-cadrage.md — silent pre-analysis to PREPARE the interactive conversation.
-> **This file does NOT replace the conversation — it prepares it.**
-
-## Purpose
-
-Before engaging the client, the AI silently analyzes the `{feature_description}` to:
-1. Understand what was said (extract explicit requirements)
-2. Detect what was NOT said (identify shadow zones to challenge)
-3. Prepare targeted questions (not generic ones)
-4. Pre-identify modules, sections, and resources
-
-**The output of this pre-analysis is INTERNAL ONLY.** It is never shown directly to the client — it feeds the reformulation (Phase 2) and challenge questions (Phase 3).
-
-## Pre-Analysis Rules
-
-### 1. Problem Type Inference
-
-Derive the problem type from `{feature_description}` keywords:
-
-```yaml
-problem_type:
-  → Keywords "remplacer", "migrer", "existant" → "replace" (existing tool to replace)
-  → Keywords "automatiser", "manuel", "processus" → "automate" (manual process to automate)
-  → Keywords "centraliser", "dispersees", "eparpillees" → "centralize" (data scattered across systems)
-  → Default (new tool) → "new_tool" (no system in place)
-```
-
-### 2. Explicit Module/Feature Extraction
-
-Extract functional areas explicitly mentioned in the description:
-
-```yaml
-detected_modules:
-  → For each distinct functional area mentioned:
-    - name: "{PascalCase module name}"
-    - description: "{what the user said about it}"
-    - detected_sections: ["{inferred sections based on description}"]
-    - detected_resources: ["{inferred resources}"]
-```
-
-### 3. Shadow Zone Detection (CRITICAL)
-
-> **Shadow zones are the most valuable output of pre-analysis.**
-> They become the challenge questions in Phase 3.
-
-For EACH detected module, check for missing information:
-
-| What to check | Shadow zone if missing | Challenge question pattern |
-|--------------|----------------------|--------------------------|
-| Stakeholders | Who uses this module? | "Who interacts with {module} daily? Only {mentioned role} or also managers, admins, external users?" |
-| Cardinality | Relationships stated as fact | "You said {A} is 1:1 with {B}. Can {A} exist without {B}? Can {B} have multiple {A}?" |
-| Granularity | Level of detail unclear | "What granularity for {feature}? Day, half-day, hour? Single entry or batch?" |
-| Reports | Mentioned but not detailed | "Which reports exactly? For whom? What format? How often?" |
-| Validation workflow | Actions without approval | "Does {action} require approval? Who validates? What happens if rejected?" |
-| Edge cases | Only happy path described | "What happens when {something goes wrong}? When data is incomplete? When two users do it simultaneously?" |
-| Non-functional | Security, performance, compliance | "Is there sensitive data (GDPR)? Expected concurrent users? Compliance requirements?" |
-| Integration | Standalone or connected | "Does {module} need to exchange data with external systems? Import? Export? API?" |
-
-### 4. Domain-Specific Anticipation Patterns
-
-When the problem domain is identified, pre-load domain-specific needs:
-
-| Domain keywords | Anticipated needs (suggest in Phase 4) |
-|----------------|---------------------------------------|
-| RH, employes, personnel | Contrats, competences, organigramme, RGPD, conges, jours feries, calendriers |
-| Temps, activites, absences | Granularite saisie, validation manageriale, soldes conges, compteurs, export paie |
-| Ventes, commandes, clients | Devis, factures, pipeline, relances, taux conversion, segments client |
-| Stock, inventaire, produits | Categories, fournisseurs, seuils reapprovisionnement, mouvements, valorisation |
-| Projets, taches, planning | Jalons, ressources, Gantt, charge, budget, risques projet |
-| Tickets, support, incidents | SLA, escalade, base connaissances, satisfaction, priorites |
-| Documents, GED | Versionning, workflows validation, templates, OCR, archivage legal |
-
-### 5. Section & Resource Pre-Identification
-
-For each detected module, anticipate sections (Level 4) and resources (Level 5) based on feature type:
-
-| Feature type | Sections (functional zones) | Resources (in list section) | Detail page tabs |
-|-------------|---------------------------|---------------------------|------------------|
-| data-centric | list | {entity}-grid, {entity}-filters, {entity}-form | Infos, {relations} |
-| workflow | list, approve | {entity}-grid, {entity}-filters, {entity}-form, approval-queue | Infos, {relations}, Historique |
-| reporting | dashboard | summary-chart, kpi-cards, export-panel | — |
-| integration | list | sync-status-grid, config-form, log-viewer | Infos, Config, Logs |
-
-> **RULE:** Sections = functional zones only (`list`, `dashboard`, `approve`, `import`, `rapport`, `planning`).
-> `create`/`edit` = separate pages with own URL routes (`/create` and `/:id/edit`). `detail` = tabbed page reached by clicking a row in `list`.
-
-**Always check:** Does the user's description imply additional functional sections? (e.g., "reports" → `dashboard`, "calendar view" → `planning`, "approval workflow" → `approve`)
-
-## Output Format (Internal Only)
-
-```yaml
-pre_analysis:
-  problem_type: "new_tool|replace|automate|centralize"
-  detected_modules:
-    - name: "ModuleName"
-      description: "What the user said"
-      detected_sections: ["list", "detail", "create"]
-      detected_resources: ["entity-grid", "entity-form"]
-  shadow_zones:
-    - topic: "Cardinality Employee-User"
-      why_it_matters: "1:1 assumption may not hold for temp workers"
-      challenge_question: "Can a user be linked to multiple employee records?"
-    - topic: "Report granularity"
-      why_it_matters: "Reports mentioned but not specified"
-      challenge_question: "Which reports exactly? For whom? What format?"
-  anticipated_suggestions:
-    - suggestion: "Leave balance management"
-      justification: "Time tracking without leave balances is incomplete"
-      module: "TimeTracking"
-    - suggestion: "GDPR compliance module"
-      justification: "HR data is personal data under GDPR"
-      module: "Employees"
-```

package/templates/skills/business-analyse/references/cadrage-shared-modules.md

@@ -1,68 +0,0 @@
-# Cross-Application Shared Module Detection
-
-Reference for detecting and extracting shared modules when `workflow_mode = "project"`.
-
-## Detection Algorithm
-
-Build module inventory per candidate application:
-
-```javascript
-// From candidateApplications (step-00) + enriched by cadrage phases 1-4
-const modulesByApp = {};
-for (const app of candidate_applications) {
-  modulesByApp[app.name] = app.modules;  // e.g., { "RH": ["Employes", "Conges", "Temps"], "Projet": ["Projets", "Temps"] }
-}
-```
-
-Detect modules appearing in 2+ applications:
-
-```javascript
-const allModules = Object.values(modulesByApp).flat();
-const moduleCounts = {};
-for (const mod of allModules) {
-  const normalized = normalizeModuleName(mod);  // "Temps", "Saisie du temps", "Time Tracking" → same concept
-  moduleCounts[normalized] = (moduleCounts[normalized] || 0) + 1;
-}
-const sharedModules = Object.entries(moduleCounts)
-  .filter(([_, count]) => count >= 2)
-  .map(([name, count]) => ({ name, appearsIn: count, applications: findAppsContaining(name) }));
-```
-
-## Extraction Logic
-
-If shared modules found, propose extraction:
-
-```javascript
-for (const shared of sharedModules) {
-  // Create new candidate application
-  candidate_applications.push({
-    name: shared.name,
-    description: `Application transversale pour ${shared.name}`,
-    modules: [shared.name],
-    isTransversal: true,
-    consumedBy: shared.applications
-  });
-
-  // Remove the shared module from original applications
-  for (const appName of shared.applications) {
-    const app = candidate_applications.find(a => a.name === appName);
-    app.modules = app.modules.filter(m => normalizeModuleName(m) !== shared.name);
-    app.dependencies = app.dependencies || [];
-    app.dependencies.push({ target: shared.name, type: "data-dependency" });
-  }
-}
-```
-
-Update `candidate_applications` in the project feature.json.
-
-## Question Template
-
-```
-question: "{language == 'fr' ? 'Souhaitez-vous extraire les modules partagés en application(s) dédiée(s) ?' : 'Do you want to extract shared modules as dedicated application(s)?'}"
-header: "Extraction"
-options:
-  - label: "{language == 'fr' ? 'Oui, extraire' : 'Yes, extract'}"
-    description: "{language == 'fr' ? 'Créer {sharedModules.length} application(s) transversale(s) supplémentaire(s)' : 'Create {sharedModules.length} additional cross-cutting application(s)'}"
-  - label: "{language == 'fr' ? 'Non, garder en l\'état' : 'No, keep as-is'}"
-    description: "{language == 'fr' ? 'Chaque application garde sa propre version du module' : 'Each application keeps its own version of the module'}"
-```

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

@@ -1,85 +0,0 @@
-# Cadrage Structure Cards
-
-> Reference for step-01-cadrage.md — exact JSON formats for cadrage section fields.
-
-## stakeholders[]
-
-```json
-{
-  "role": "Fleet Manager",
-  "function": "Manages daily fleet operations",
-  "involvement": "decision-maker",
-  "tasks": ["Monitor vehicles", "Approve repairs", "Export reports"],
-  "frequency": "Daily",
-  "painPoints": ["Manual tracking in spreadsheets", "No real-time visibility"]
-}
-```
-**MANDATORY fields:** `role`, `function`, `involvement`, `tasks`
-**involvement values:** `approver`, `decision-maker`, `consulted`, `informed`, `end-user`
-**FORBIDDEN fields:** Do NOT use `expertise`, `systemRole`, `description` (use `function` instead).
-
-## applicationRoles[]
-
-```json
-{
-  "role": "{App} Admin",
-  "description": "Full access to all modules",
-  "level": "admin",
-  "permissionPattern": "{app}.*"
-}
-```
-**MANDATORY fields:** `role`, `level`, `permissionPattern`
-**level values:** `admin`, `manager`, `contributor`, `viewer`
-**FORBIDDEN fields:** Do NOT use `permissions` (use `permissionPattern`), `isDefault`.
-
-## risks[]
-
-```json
-{
-  "id": "RISK-001",
-  "type": "business|technical|organizational",
-  "description": "CSV data may contain duplicates and errors",
-  "probability": "high|medium|low",
-  "impact": "high|medium|low",
-  "priority": "critical|medium|low",
-  "mitigation": "Data cleaning phase before import, detailed error reports"
-}
-```
-**MANDATORY fields:** `id` (pattern: RISK-NNN), `type`, `description`, `mitigation`
-**FORBIDDEN fields:** Do NOT use `risk` (name), `severity`. Use `id` + `description` + `priority`.
-
-## acceptanceCriteria[]
-
-```json
-{ "id": "AC-001", "criterion": "All must-have features delivered and tested", "validated": false }
-```
-**MANDATORY:** This section must NOT be omitted.
-
-## coverageMatrix[]
-
-```json
-{
-  "item": "User management with CRUD",
-  "category": "mustHave|shouldHave|couldHave|outOfScope|implicit",
-  "module": "Users",
-  "ucRef": "UC-UM-001",
-  "notes": "Foundation module, must be implemented first",
-  "anticipatedSections": ["list", "dashboard"],
-  "anticipatedResources": ["user-grid", "user-filters", "user-form"],
-  "detailTabs": ["Informations", "Roles", "Historique"]
-}
-```
-**MANDATORY fields:** `item`, `category`, `module`
-**OPTIONAL fields:** `ucRef`, `notes`, `anticipatedSections`, `anticipatedResources`, `detailTabs`
-**category values:** `mustHave`, `shouldHave`, `couldHave`, `outOfScope`, `implicit` (camelCase)
-**anticipatedSections:** Array of section codes (Level 4) — functional zones ONLY: `["list", "dashboard", "approve", "import", "rapport", "planning"]`. NEVER `create`, `edit`, or `detail` (those are actions/pages within `list`).
-**anticipatedResources:** Array of resource codes (Level 5) — e.g., `["user-grid", "user-filters", "user-form"]`
-**detailTabs:** Array of tab names for the detail page (reached by clicking a row in `list`) — e.g., `["Informations", "Roles", "Historique"]`
-**FORBIDDEN fields:** Do NOT use `id`, `feature`, `priority`. Use `item` + `category`.
-
-## codebaseContext
-
-Must be a string, NOT an object:
-```json
-"codebaseContext": "Greenfield project, no existing entities. SmartStack 2.1.0 with Extensions DbContext."
-```