@atlashub/smartstack-cli 2.9.0 → 3.0.0

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

@@ -1,15 +1,15 @@
 ---
 name: business-analyse
-description: Business Analysis v4.0 - Iterative multi-module workflow with 5-level navigation hierarchy, client checkpoints, and integrated documentation.
-argument-hint: "[-a] [-e] [-q <FEAT-ID> \"question\"] [-r <FEAT-ID> \"change\"] [-m] <feature description>"
+description: Business Analysis v5.0 - Iterative multi-module workflow with 5-level navigation hierarchy, client checkpoints, interactive HTML documentation, and extraction pipeline.
+argument-hint: "[-a] [-e] [-q <FEAT-ID> \"question\"] [-r <FEAT-ID> \"change\"] [-m] [-x <json-path>] <feature description>"
 ---
 
 <objective>
-Execute VibeCoding-focused business analysis workflows. This skill produces a single feature.json progressively enriched at each step, published to docs/business/ for web app rendering. Supports 4 use cases: new feature analysis, questions about existing features, feature refactoring, and one-shot micro-features.
+Execute VibeCoding-focused business analysis workflows. This skill produces a single feature.json progressively enriched at each step, published to docs/business/ for web app rendering. Supports 5 use cases: new feature analysis, questions about existing features, feature refactoring, one-shot micro-features, and extraction from interactive HTML documentation.
 </objective>
 
 <quick_start>
-**Four use cases:**
+**Five use cases:**
 
 ```bash
 # A. New feature (full workflow)
@@ -23,6 +23,9 @@ Execute VibeCoding-focused business analysis workflows. This skill produces a si
 
 # D. Micro-feature (one-shot, minimal questions)
 /business-analyse -m Add a status field to orders
+
+# E. Extract from interactive HTML export
+/business-analyse -x ./docs/business/MyApp/ba-export.json
 ```
 
 **Recommended autonomous workflow:**
@@ -45,6 +48,7 @@ See `<parameters>` for complete flag list.
 | `-q` | `--question` | Question mode: query an existing feature (requires FEAT-ID + question) |
 | `-r` | `--refactor` | Refactoring mode: delta changes on existing feature (requires FEAT-ID + change description) |
 | `-m` | `--micro` | Micro-feature mode: minimal questions, direct handoff |
+| `-x` | `--extract` | Extract mode: import from interactive HTML export JSON (requires json-path) |
 | `-app` | `--application` | Application mode: multi-module analysis with module decomposition |
 | `-i` | `--interactive` | Interactive mode: configure flags via AskUserQuestion |
 
@@ -72,6 +76,9 @@ See `<parameters>` for complete flag list.
 # E. Micro-feature (minimal questions)
 /business-analyse -m Add a status field to orders
 
+# F. Extract from interactive HTML export
+/business-analyse -x ./docs/business/MyApp/ba-export.json
+
 # Autonomous application mode
 /business-analyse -app -a New HR management system
 
@@ -86,7 +93,7 @@ See `<parameters>` for complete flag list.
 1. Defaults loaded from `steps/step-00-init.md` `<defaults>` section
 2. Command-line flags override defaults
 3. Flags removed from input, remainder becomes `{feature_description}`
-4. Use case determined by flags: question > refactor > micro > new (default)
+4. Use case determined by flags: question > refactor > extract > micro > new (default)
 5. Feature ID generated as `FEAT-NNN` for new features
 </parsing_rules>
 
@@ -96,10 +103,13 @@ See `<parameters>` for complete flag list.
 **All outputs saved to PROJECT directory:**
 
 ```
-docs/business/{app}/business-analyse/v{X.Y}/
-    feature.json              # APPLICATION-level master (modules, dependencies, roles)
-docs/business/{app}/{module}/business-analyse/v{X.Y}/
-    feature.json              # MODULE-level detail (entities, UC, FR, permissions, mockups)
+docs/business/
+    index.json                    # BA manifest (auto-updated at handoff, consumed by web app viewer)
+    {app}/business-analyse/v{X.Y}/
+        feature.json              # APPLICATION-level master (modules, dependencies, roles)
+        ba-interactive.html       # Client-facing interactive review document (deployed at handoff)
+    {app}/{module}/business-analyse/v{X.Y}/
+        feature.json              # MODULE-level detail (entities, UC, FR, permissions, mockups)
 ```
 
 **Ralph Loop files (generated by step-05):**
@@ -133,6 +143,15 @@ When provided, step-00 will:
 2. Create new version folder (v1.1 from v1.0, etc.)
 3. Load existing feature context
 4. Continue through steps 01-04 with delta focus
+
+**Extract mode (`-x <json-path>`):**
+
+When provided, step-00 will:
+
+1. Validate the JSON file at `<json-path>` exists and is valid JSON
+2. Pass parsed content to step-06-extract.md
+3. Step-06 maps ALL client data to feature.json format (zero information loss)
+4. Post-extraction: choice to enrich, handoff, or terminate
 </resume_workflow>
 
 <workflow>
@@ -141,9 +160,10 @@ When provided, step-00 will:
 1. Parse flags and feature description
 2. If `-q`: Load ba-reader, answer question → EXIT
 3. If `-r`: Load existing feature.json, create new version
-4. If `-m`: Create minimal feature.json → simplified handoff
-5. If `-app` or auto-detected multi-module: Full application workflow
-6. Default: Single module workflow (same phases, decomposition is trivial)
+4. If `-x`: Load JSON export, extract to feature.json → step-06
+5. If `-m`: Create minimal feature.json → simplified handoff
+6. If `-app` or auto-detected multi-module: Full application workflow
+7. Default: Single module workflow (same phases, decomposition is trivial)
 
 **Application workflow (multi-module):**
 - **Step 00:** Parse flags, create master feature.json (draft)
@@ -170,6 +190,11 @@ When provided, step-00 will:
 **Micro workflow:**
 - **Step 00:** Create minimal feature.json
 - **Step 05:** Direct handoff (skip 01-04)
+
+**Extract workflow (from interactive HTML):**
+- **Step 00:** Parse `-x` flag, validate JSON file
+- **Step 06:** Map HTML export to feature.json (cadrage, modules, specs, consolidation)
+- Post-extraction choice: enrich with questionnaire (step-01), go to handoff (step-05), or terminate
 </workflow>
 
 <state_variables>
@@ -179,7 +204,7 @@ When provided, step-00 will:
 | ----------------------- | ------- | ------------------------------------------------------ |
 | `{feature_id}`          | string  | Unique identifier (e.g., `FEAT-001`)                   |
 | `{feature_description}` | string  | What to analyze (flags removed)                        |
-| `{use_case}`            | string  | One of: new, question, refactoring, micro              |
+| `{use_case}`            | string  | One of: new, question, refactoring, micro, extract     |
 | `{version}`             | string  | SemVer (1.0, 1.1, 2.0, etc.)                           |
 | `{application_name}`    | string  | Target application name                                |
 | `{module_name}`         | string  | Target module name                                     |
@@ -208,6 +233,7 @@ When provided, step-00 will:
 | 03   | `steps/step-03-specify.md`        | Opus   | Iterative per-module specification + validation |
 | 04   | `steps/step-04-consolidation.md`  | Sonnet | Cross-module validation, E2E flows, permissions coherence |
 | 05   | `steps/step-05-handoff.md`        | Opus   | Development prompt + Ralph Loop prd.json |
+| 06   | `steps/step-06-extract.md`        | Sonnet | Extract interactive HTML export → feature.json |
 
 </step_files>
 
@@ -216,21 +242,23 @@ When provided, step-00 will:
 
 Load ONLY relevant categories based on feature type:
 
-| Category | File                                | Questions | When to load |
-| -------- | ----------------------------------- | --------- | ------------ |
-| 00       | `questionnaire/00-application.md` | 8         | If application mode |
-| 01       | `questionnaire/01-context.md`       | 4         | Always       |
-| 02       | `questionnaire/02-stakeholders.md`  | 6         | Always       |
-| 03       | `questionnaire/03-scope.md`         | 6         | Always       |
-| 04       | `questionnaire/04-data.md`          | 6         | If data-centric |
-| 05       | `questionnaire/05-integrations.md`  | 6         | If integrations |
-| 06       | `questionnaire/06-security.md`      | 4         | Always (minimal) |
-| 07       | `questionnaire/07-ui.md`            | 6         | If UI-centric |
-| 08       | `questionnaire/08-performance.md`   | 4         | If performance-critical |
-| 09       | `questionnaire/09-constraints.md`   | 4         | If constraints exist |
-| 10       | `questionnaire/10-documentation.md` | 4         | If doc required |
-
-**Total: ~60 questions (trimmed from 100+)**
+| Categorie | Fichier                               | Questions | Quand charger |
+| --------- | ------------------------------------- | --------- | ------------- |
+| 00        | `questionnaire/00-application.md`     | 8         | Si mode application |
+| 01        | `questionnaire/01-context.md`         | 12        | Toujours      |
+| 02        | `questionnaire/02-stakeholders.md`    | 14        | Toujours      |
+| 03        | `questionnaire/03-scope.md`           | 12        | Toujours      |
+| 04        | `questionnaire/04-data.md`            | 8         | Si module oriente donnees |
+| 05        | `questionnaire/05-integrations.md`    | 8         | Si integrations |
+| 06        | `questionnaire/06-security.md`        | 8         | Si securite mentionnee |
+| 07        | `questionnaire/07-ui.md`              | 12        | Si module oriente interface |
+| 08        | `questionnaire/08-performance.md`     | 4         | Si performance critique |
+| 09        | `questionnaire/09-constraints.md`     | 4         | Si contraintes |
+| 10        | `questionnaire/10-documentation.md`   | 4         | Si documentation requise |
+| 14        | `questionnaire/14-risk-assumptions.md`| 8         | Toujours      |
+| 15        | `questionnaire/15-success-metrics.md` | 8         | Toujours      |
+
+**Total noyau : ~86 questions (en profondeur, langage business)**
 
 </questionnaire_files>
 
@@ -243,6 +271,7 @@ Load ONLY relevant categories based on feature type:
 | spec     | `templates/tpl-frd.md`              | 02           |
 | handoff  | `templates/tpl-handoff.md`          | 04           |
 | suggestions | `patterns/suggestion-catalog.md` | 01           |
+| interactive | `html/ba-interactive.html`        | 05 (deploy)  |
 
 </template_files>
 

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

@@ -473,70 +473,101 @@ AskUserQuestion({
 
 ---
 
-## Elicitation Techniques
+## Techniques d'elicitation
 
-> **Loaded by:** step-01-analyse (Opus ULTRATHINK)
-> **Purpose:** Guide HOW to question, not just WHAT to ask.
+> **Charge par :** step-01-cadrage (Opus ULTRATHINK)
+> **Objectif :** Guider COMMENT questionner, pas seulement QUOI demander.
+> **Principe :** Chaque technique doit etre appliquee naturellement dans le flux de la conversation,
+> pas comme un outil supplementaire. L'analyste choisit la technique adaptee a la situation.
 
-### Technique 1: Solution → Problem Reframing
+### Technique 1 : Reformulation du besoin
 
-If the user describes a **solution** (button, field, screen, API), reframe as a **need**:
+Quand le client decrit une **solution** (bouton, ecran, champ, outil), reformuler en **besoin** :
 
-| User says | BA agent asks |
-|-----------|---------------|
-| "I need a Role dropdown on the User form" | "What problem are you trying to solve with different user access levels?" |
-| "We need an export button" | "What do you do with the exported data? Who needs it and why?" |
-| "Add a status field" | "What lifecycle does this entity go through? What triggers each transition?" |
+| Le client dit | L'analyste demande |
+|---------------|-------------------|
+| "Il me faut un menu deroulant pour les roles" | "Quel probleme rencontrez-vous aujourd'hui avec la gestion des acces ? Pourquoi certaines personnes doivent-elles avoir des acces differents ?" |
+| "On a besoin d'un bouton d'export" | "Que faites-vous avec les donnees une fois exportees ? Qui en a besoin et pourquoi ?" |
+| "Ajoutez un champ statut" | "Quel parcours suit cet element du debut a la fin ? Quels evenements declenchent un changement d'etat ?" |
 
-### Technique 2: 5 Whys (Root Cause)
+### Technique 2 : Chaine des pourquoi
 
-When the need seems superficial, chain up to 5 "Why?":
+Quand le besoin semble superficiel, enchainez jusqu'a 5 "Pourquoi ?" pour trouver la cause racine :
 
 ```
-User: "We need to track user activity"
-→ Why? "To know who modified what"
-→ Why? "Because we had data integrity issues"
-→ Why? "Because multiple people edit the same records"
-→ ROOT CAUSE: Concurrent editing conflict → Need audit trail + optimistic locking
+Client : "On a besoin de suivre l'activite des utilisateurs"
+→ Pourquoi ? "Pour savoir qui a modifie quoi"
+→ Pourquoi ? "Parce qu'on a eu des problemes de donnees incorrectes"
+→ Pourquoi ? "Parce que plusieurs personnes modifient les memes fiches"
+→ CAUSE RACINE : Conflit d'edition simultanee → Besoin de journal d'activite + protection des modifications
 ```
 
-### Technique 3: Concrete Scenario Extraction
+### Technique 3 : Extraction de scenario concret
 
-Never accept abstract descriptions. Always ask for **a real day-in-the-life scenario**:
+Ne jamais accepter de descriptions abstraites. Toujours demander un **scenario de vie reelle** :
 
 ```
-"Walk me through a typical day: you arrive at the office,
- you open the application — what is the FIRST thing you need to do?
- Then what? What information do you look at? What decisions do you make?"
+"Racontez-moi une journee type : vous arrivez au bureau, vous ouvrez l'application.
+ Quelle est la PREMIERE chose que vous devez faire ?
+ Puis ensuite ? Quelles informations consultez-vous ? Quelles decisions prenez-vous ?"
 ```
 
-### Technique 4: Absence Test
+### Technique 4 : Test d'absence
 
-Validate necessity by asking what happens WITHOUT:
+Valider la necessite en demandant ce qui se passe SANS :
 
 ```
-"If this feature did NOT exist, what would you do instead?
- How much time/money does the current workaround cost?"
+"Si cette fonctionnalite N'EXISTAIT PAS, que feriez-vous a la place ?
+ Combien de temps ou d'argent le contournement actuel coute-t-il ?"
 ```
 
-### Technique 5: Completeness Probing
+### Technique 5 : Verification de completude
 
-For every list answer, challenge completeness:
+Pour chaque reponse sous forme de liste, verifier qu'il ne manque rien :
 
-| Answer type | Probe |
-|-------------|-------|
-| "There are 3 user types" | "Are there external actors? Auditors? System admins? Automated processes?" |
-| "The main flow is A→B→C" | "What if the user cancels at step B? What if step C fails? What if they go back to A?" |
-| "Required fields: name, email" | "What uniqueness constraints? What format? What happens on duplicate?" |
+| Type de reponse | Relance |
+|-----------------|---------|
+| "Il y a 3 types d'utilisateurs" | "Y a-t-il des acteurs externes ? Des auditeurs ? Des administrateurs systeme ? Des processus automatiques ?" |
+| "Le flux principal est A puis B puis C" | "Que se passe-t-il si l'utilisateur annule a l'etape B ? Si l'etape C echoue ? S'il veut revenir a A ?" |
+| "Champs obligatoires : nom et email" | "Quelles contraintes d'unicite ? Quel format ? Que se passe-t-il en cas de doublon ?" |
 
-### Answer Quality Indicators
+### Technique 6 : Projection dans le futur
 
-| Quality | Signal | Action |
+Demander au client de se projeter pour decouvrir des besoins non exprimes :
+
+```
+"Imaginons que nous sommes 2 ans dans le futur et que l'application fonctionne parfaitement.
+ Qu'est-ce qui a change dans votre facon de travailler ?
+ Quels nouveaux besoins sont apparus auxquels vous ne pensez pas aujourd'hui ?"
+```
+
+### Technique 7 : Test de contradiction
+
+Quand deux reponses semblent contradictoires, les confronter pour clarifier :
+
+```
+"Vous avez mentionne que [affirmation A], mais vous dites aussi que [affirmation B].
+ Ces deux elements semblent en tension. Pouvez-vous m'aider a comprendre
+ comment ils coexistent dans la realite ?"
+```
+
+### Technique 8 : Escalade d'impact
+
+Augmenter progressivement l'echelle pour tester les limites :
+
+```
+"Aujourd'hui vous avez 50 fiches. Que se passe-t-il avec 500 ? Avec 5000 ?
+ Est-ce que le processus reste le meme ou faudrait-il faire differemment ?"
+```
+
+### Indicateurs de qualite des reponses
+
+| Qualite | Signal | Action |
 |---------|--------|--------|
-| **Insufficient** | < 1 sentence, "I don't know", vague adjective | Apply technique 1-5, ask for concrete example |
-| **Solution-oriented** | Contains UI/tech terms (button, field, API, database) | Apply technique 1 (reframe to problem) |
-| **Sufficient** | Contains WHO, WHAT, WHY, concrete example | Proceed, note confidence level |
-| **Excellent** | Includes edge cases, constraints, measurable criteria | Proceed, mark as "Confirmed" |
+| **Insuffisante** | Moins d'une phrase, "je ne sais pas", adjectif vague | Appliquer les techniques 1 a 8, demander un exemple concret |
+| **Orientee solution** | Contient des termes d'interface ou techniques (bouton, champ, base de donnees) | Appliquer la technique 1 (reformuler en besoin) |
+| **Suffisante** | Contient QUI, QUOI, POURQUOI et un exemple concret | Continuer, noter le niveau de confiance |
+| **Excellente** | Inclut les cas limites, les contraintes et des criteres mesurables | Continuer, marquer comme "Confirme" |
 
 ---