@atlashub/smartstack-cli 4.19.0 → 4.21.0

package/templates/skills/business-analyse/steps/step-00-init.md

@@ -101,7 +101,7 @@ Execute workflow detection algorithm:
    - Continue to application name determination.
 
 **Key decision points:**
-1. IF review mode → load ba-review.json, skip to step-06-review.md
+1. IF review mode → inform user to use `/ba-review` skill instead
 2. IF no existing apps → workflow_type = "new"
 3. IF existing apps → analyze similarity → prompt user
 
@@ -496,13 +496,9 @@ If initialization was interrupted:
 
    **Status-based resume routing (check in this order):**
 
-   - If status = `"handed-off"`:
-     → Resume at `step-06-review.md`
-     → Display: "Handoff complete — proceeding to review..."
-
-   - If status = `"consolidated"`:
-     → Resume directly at `step-05-deploy.md`
-     → Display: "Resuming from consolidation — proceeding to deployment..."
+   - If status = `"handed-off"` or `"consolidated"`:
+     → Display: "BA workflow complete. Use /ba-generate-html to generate HTML, /ba-review for corrections."
+     → STOP
 
    - If status = `"specified"` AND `metadata.workflow.allModulesSpecified === true`:
      → Resume at `step-04-consolidate.md`
@@ -531,4 +527,5 @@ If a project-level index.json is found (scope = "project"):
      → All applications specified → Resume at `step-04-consolidate.md`
 
    - If status = `"consolidated"`:
-     → Resume at `step-05-deploy.md`
+     → Display: "BA workflow complete. Use /ba-generate-html to generate HTML."
+     → STOP

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

@@ -209,13 +209,11 @@ options:
 #### 4a. Business Context (ALWAYS — from `questionnaire/01-context.md`)
 
 > Load the full questionnaire reference for elicitation guides and alert signals.
+> The questionnaire contains 3 targeted questions: Q1.1 (business process), Q1.4 (friction points), Q1.8 (vision).
 
-Select the most relevant questions from Q1.1-Q1.12.
-**Mandatory minimum:** Q1.1 (problem), Q1.4 (current tools), Q1.8 (vision), Q1.11 (trigger).
+Ask all 3 questions in 1 batch via AskUserQuestion.
 
-Ask in 1-2 batches via AskUserQuestion (max 4 questions per batch).
-
-Apply ULTRATHINK after each batch:
+Apply ULTRATHINK after the batch:
 - If answer is vague → probe deeper using the elicitation guide from 01-context.md
 - If answer is solution-oriented → apply Technique 1 (reformulate as need)
 - If answer is superficial → apply Technique 2 (chain of whys)
@@ -223,7 +221,9 @@ Apply ULTRATHINK after each batch:
 
 #### 4b. Stakeholders (ALWAYS — from `questionnaire/02-stakeholders-scope.md`)
 
-**Mandatory minimum:** Q2.1 (users), Q2.5 (tasks per profile), Q2.9 (access levels).
+> The questionnaire contains 10 targeted questions covering profiles, tasks, access levels, scope, and user journey.
+
+**Mandatory minimum:** Q2.1 (users), Q2.5 (tasks per profile), Q2.9-Q2.11 (access levels).
 
 Ask in 1-2 batches. After each batch:
 - If only 1 user type mentioned → probe: "Who else interacts? Managers? Admins? External users?"
@@ -232,7 +232,7 @@ Ask in 1-2 batches. After each batch:
 
 #### 4c. Functional Scope (ALWAYS — from `questionnaire/02-stakeholders-scope.md`)
 
-**Mandatory minimum:** Q3.2 (must-have), Q3.4 (exclusions), Q3.5 (main journey).
+**Mandatory minimum:** Q2.13 (must-have), Q2.15 (exclusions), Q2.16 (main journey).
 
 Ask in 1-2 batches. After each batch:
 - If everything is "must-have" → **BLOCKING**: apply MoSCoW prioritization question
@@ -441,15 +441,7 @@ options:
 
 > **CRITICAL:** The intelligence of this step is in the ULTRATHINK analysis. The AI must REASON about domain coherence, score the entity, and recommend — not just present 4 neutral options. The client can always override the recommendation, but they should benefit from expert architectural guidance.
 
-#### 4e. Risks & Success Criteria (ALWAYS — from `questionnaire/04-risks-metrics.md`)
-
-Select the most pertinent questions:
-- **04-risks-metrics.md:** Risk identification, assumptions validation
-- **04-risks-metrics.md:** Success definition, measurable objectives
-
-Ask in 1 batch via AskUserQuestion.
-
-#### 4f. Conditional Deep-Dives
+#### 4e. Conditional Deep-Dives
 
 Based on brief analysis, load additional materials if relevant:
 
@@ -460,33 +452,6 @@ Based on brief analysis, load additional materials if relevant:
 | Performance requirements | Additional probing on non-functional needs |
 | Technical constraints | Additional probing on platform constraints |
 
-#### 4g. Documentation Needs (ALWAYS — from `questionnaire/03-data-ui.md`)
-
-> **Every application requires documentation decisions made upfront, not as an afterthought.**
-> Load relevant documentation section from questionnaire/03-data-ui.md
-
-Ask in 1 batch via AskUserQuestion (max 3 questions):
-- Will users need documentation (guide, FAQ, in-app tooltips)?
-- Is technical documentation required (API docs, ERD, developer guide)?
-- Who is responsible for maintaining documentation after delivery?
-
-After the batch:
-- If "Non" to both → probe: "Pas même les docs API ou un guide d'accueil pour les nouveaux utilisateurs ?"
-- If "Oui" without detail → ask format: "Tooltips intégrés ? Guide PDF ? Wiki ? Portail dédié ?"
-- If "La doc se fera après" → challenge: "La documentation est planifiée maintenant et générée par `/documentation` après `/ralph-loop`. Quel niveau souhaitez-vous ?"
-
-**Store in `cadrage.documentation`:**
-```json
-{
-  "userDocumentation": { "needed": true, "format": "tooltips|guide|wiki|pdf|portal", "audience": "..." },
-  "technicalDocumentation": { "needed": true, "format": "swagger|erd|developer-guide", "generated": true },
-  "owner": "who maintains it",
-  "skill": "/documentation — runs after /ralph-loop"
-}
-```
-
-This feeds directly into handoff step-05 category `documentation` in `filesToCreate`.
-
 ---
 
 ## PHASE 4: ANTICIPATION (Suggest Unexpressed Needs)
@@ -677,20 +642,16 @@ ba-writer.enrichSection({
     problem: {from Phase 3, section 4a — Q1.1 answer or refined problem},
     asIs: {from Phase 3, section 4a — Q1.4 answer},
     toBe: {from Phase 3, section 4a — Q1.8 answer},
-    trigger: {from Phase 3, section 4a — Q1.11 answer},
     stakeholders: [{from Phase 3, section 4b}],
     globalScope: {
       mustHave: [{from Phase 3, section 4c + Phase 4 accepted suggestions}],
       shouldHave: [{from coverage matrix}],
       couldHave: [{from coverage matrix}],
-      outOfScope: [{from Phase 3, section 4c — Q3.4 exclusions}]
+      outOfScope: [{from Phase 3, section 4c — Q2.15 exclusions}]
     },
     applicationRoles: [{from Phase 5, section 6}],
     errorFlows: [{from Phase 3, section 4c}],
-    risks: [{from Phase 3, section 4e}],
-    acceptanceCriteria: [{from Phase 3, section 4e}],
     coverageMatrix: [{from Phase 5, section 7 — with anticipatedSections and anticipatedResources}],
-    documentation: {from Phase 3, section 4g},
     codebaseContext: "{string summary of codebase findings}"
   }
 })
@@ -708,7 +669,6 @@ ba-writer.updateStatus({feature_id}, "framed")
 | Stakeholders | {count} |
 | Must-have scope items | {count} |
 | Application roles | {count} |
-| Risks identified | {count} |
 | Suggestions accepted | {count} |
 | Anticipated sections | {total across all modules} |
 

package/templates/skills/business-analyse/steps/step-04-consolidate.md

@@ -2,7 +2,7 @@
 name: step-04-consolidate
 description: Cross-module validation - data model, permissions, E2E flows, approval
 model: opus
-next_step: steps/step-05-deploy.md
+next_step: none
 ---
 
 > **Context files:** `_shared.md`
@@ -34,8 +34,8 @@ ba-reader.readApplicationContext({feature_id})
 → cadrage.applicationRoles, modules[], dependencyGraph
 
 IF status already "consolidated":
-  Display: "Consolidation already completed. Loading step-05-deploy."
-  Load: steps/step-05-deploy.md
+  Display: "Consolidation already completed. BA workflow finished."
+  Display: "Next: invoke /ba-generate-html then /ba-review for client cycle."
   STOP
 ```
 
@@ -443,7 +443,11 @@ Display final summary:
 ✓ All validations passed
 ✓ Client approval obtained
 ✓ Status: consolidated
-→ Proceeding to step-05-deploy.md
+
+BA workflow complete. Next steps:
+→ Invoke /ba-generate-html to generate the interactive HTML
+→ Invoke /ba-review to apply client corrections
+→ Invoke /derive-prd → /ralph-loop for implementation
 ```
 
 ---
@@ -473,6 +477,9 @@ Display final summary:
 
 ---
 
-## NEXT STEP
+## NEXT STEPS
 
-Load: `./step-05-deploy.md`
+BA workflow ends here. After consolidation:
+1. Invoke `/ba-generate-html` to generate the interactive HTML document
+2. Invoke `/ba-review` to apply client corrections (if needed)
+3. Invoke `/derive-prd` then `/ralph-loop` for implementation

package/templates/skills/business-analyse/templates/tpl-handoff.md

@@ -1,6 +1,6 @@
 # Template Development Handoff
 
-> **Usage:** Template for step-05-deploy.md
+> **Usage:** Template for /derive-prd
 > **Data source:** index.json (sections: metadata, analysis, specification, handoff)
 
 ---

package/templates/skills/business-analyse/templates/tpl-launch-displays.md

@@ -1,6 +1,6 @@
 # Skill Launch Display Templates (templates/tpl-launch-displays.md)
 
-> **Used by:** step-05-deploy (Completion Summary)
+> **Used by:** /ba-generate-html (Completion Summary)
 > **Purpose:** User-facing display templates for BA completion
 > **Note:** No emojis - uses text markers per Claude Code conventions
 

package/templates/skills/documentation/SKILL.md

@@ -22,10 +22,17 @@ Works in synergy with the `/documentation module` command.
 <quick_start>
 ## WHEN THIS SKILL ACTIVATES
 
+### PREREQUISITE — ONLY post-implementation
+This skill requires the feature page to already exist (generated by /ralph-loop).
+It reads real TSX pages, controllers, and entities. Without them, nothing to document.
+
+→ For reviewing/editing the analysis BEFORE implementation: use ba-interactive.html (/business-analyse step-05)
+
 Claude automatically invokes this skill when it detects:
 
 | Trigger | Example |
 |---------|---------|
+| ❌ NEVER during BA | Before /ralph-loop — feature page does not exist yet |
 | Explicit request | "Document the SLA module" |
 | Documentation mention | "We should create the doc for..." |
 | After implementation | "The feature is done, generate the doc" |

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

@@ -1,220 +0,0 @@
----
-name: step-05-deploy
-description: Deploy interactive HTML document from analysis data
-model: sonnet
-next_step: steps/step-06-review.md
----
-
-> **Context files:** `_shared.md` | `references/html-data-mapping.md`
-
-# Step 5: Deploy - Interactive HTML Document
-
-## MANDATORY EXECUTION RULES
-
-- **ALWAYS** verify PRD exists before proceeding (`.ralph/prd-{module}.json`)
-- **ALWAYS** pre-populate HTML with FEATURE_DATA + EMBEDDED_ARTIFACTS (no empty templates)
-- **FEATURE_DATA.moduleSpecs** must have ONE entry per module (empty = BROKEN)
-- **FEATURE_DATA.cadrage.scope** uses HTML keys (vital/important/optional/excluded)
-- **ALWAYS** deploy SINGLE interactive HTML (multi-app or single-app per config)
-
-## YOUR TASK
-
-Deploy the single interactive HTML document pre-populated with all analysis data across all modules and applications. PRD and handoff data must already exist (generated by `/derive-prd`).
-
----
-
-## EXECUTION SEQUENCE
-
-### 1. Verify PRD Exists
-
-For each module, verify PRD file 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
-```
-
-Verify consolidation status:
-
-```
-IF workflow.mode === "project":
-  projectFeature = ba-reader.findProjectFeature()
-  FOR each app in projectFeature.applications:
-    appFeature = ba-reader.findFeature(app.featureJsonPath)
-    IF appFeature.status !== "consolidated":
-      BLOCKING ERROR: "Application {app.code} not consolidated"
-ELSE:
-  feature = ba-reader.findFeature({feature_id})
-  IF feature.status !== "consolidated":
-    BLOCKING ERROR: "Feature status: {feature.status}, expected consolidated"
-```
-
-Display:
-```
-PRD verified: {module_count} modules
-  .ralph/prd-{module1}.json ({size} bytes)
-  .ralph/prd-{module2}.json ({size} bytes)
-→ Proceeding to HTML generation...
-```
-
----
-
-### 2. Build FEATURE_DATA Object
-
-Read from index.json (master module JSON files):
-
-For EACH module:
-- Read complete index.json for each module
-- Map to FEATURE_DATA structure per `references/html-data-mapping.md`
-
-**FEATURE_DATA structure:**
-- metadata (analysisMode="interactive", workflowMode, versions, timestamps)
-- cadrage (scope using HTML keys: vital/important/optional/excluded; objectives, constraints, assumptions)
-- modules[] (all modules with all fields from index.json)
-- moduleSpecs{} (one entry PER module with analysis, specification sections from index.json)
-- consolidation (cross-module interactions)
-- handoff (complexity, filesToCreate summary, totalFiles, totalTasks)
-
-**Critical requirements:**
-- moduleSpecs MUST have ONE entry per module (empty = BUG)
-- cadrage.scope converts: mustHave->vital, shouldHave->important, couldHave->optional, outOfScope->excluded
-- metadata.analysisMode from master.metadata.analysisMode (always "interactive")
-- PROJECT MODE: include applications[], consolidation.crossApplicationInteractions
-
----
-
-### 3. Build EMBEDDED_ARTIFACTS Object
-
-Collect from FEATURE_DATA:
-- **wireframes**: Per-module ASCII + SVG (if generated) — fields: format, content, svgContent
-- **e2eFlows**: E2E diagrams from consolidated.e2eFlows
-- **dependencyGraph**: From dependencyGraph section
-
-**Field name mapping (CRITICAL):**
-- wireframes use: `format`, `content`, `svgContent` (NOT mockupFormat/mockup)
-
----
-
-### 4. Generate SVG Wireframes (Parallel, Optional)
-
-> **After EMBEDDED_ARTIFACTS built but BEFORE HTML write.**
-> This step is NEVER blocking — ASCII-only wireframes acceptable.
-> **Reference:** Read `references/wireframe-svg-style-guide.md` for full agent prompt template
-
-1. Collect all wireframes where `mockup` exists and `svgContent` is null
-2. Spawn parallel Task(sonnet) agents — ONE per wireframe
-3. Validate results: strip markdown fences, verify SVG syntax
-4. Inject valid SVGs into `EMBEDDED_ARTIFACTS.wireframes[moduleCode][index].svgContent`
-5. Display: "SVG wireframe generation: {successCount}/{total} generated, {failCount} fallback (ASCII)"
-
----
-
-### 5. Replace Placeholders & Write HTML
-
-1. Read HTML template from skill: `html/ba-interactive.html`
-2. Serialize FEATURE_DATA and EMBEDDED_ARTIFACTS as JSON (2-space indent)
-3. Replace 8 placeholders:
-   - `{{FEATURE_DATA}}` — Full FEATURE_DATA JSON object
-   - `{{EMBEDDED_ARTIFACTS}}` — Wireframes, E2E, dependency graph
-   - `{{APPLICATION_NAME}}` — From master.metadata.application
-   - Others per template
-
-4. **Output path:**
-   - Multi-app (project mode): `docs/business-analyse/v{version}/ba-interactive.html`
-   - Single-app: `docs/{app}/business-analyse/v{version}/ba-interactive.html`
-
-5. Write to file
-
----
-
-### 6. Verify Deployment
-
-**POST-CHECK (BLOCKING):**
-
-1. **File size > 100KB** (indicates pre-populated)
-   ```
-   if [ $(stat --format=%s ba-interactive.html) -lt 100000 ]; then
-     BLOCKING_ERROR("ba-interactive.html not pre-populated")
-   fi
-   ```
-
-2. **moduleSpecs present in HTML** (must be serialized)
-   ```
-   if ! grep -q '"moduleSpecs"' ba-interactive.html; then
-     BLOCKING_ERROR("moduleSpecs not found — FEATURE_DATA not serialized")
-   fi
-   ```
-
-3. **cadrage.scope uses HTML keys** (vital/important/optional/excluded)
-   ```
-   if grep -q '"mustHave"' ba-interactive.html; then
-     BLOCKING_ERROR("cadrage.scope still has JSON keys")
-   fi
-   ```
-
-4. **Wireframe field names correct** (format/content, NOT mockupFormat/mockup)
-   ```
-   if grep -q '"mockupFormat"' ba-interactive.html; then
-     BLOCKING_ERROR("Wireframes use 'mockupFormat' — must be 'format'")
-   fi
-   ```
-
-5. **All modules have specs AND wireframes**
-   ```
-   FOR each module in FEATURE_DATA.modules:
-     IF FEATURE_DATA.moduleSpecs[module.code] undefined:
-       BLOCKING_ERROR("Module not in moduleSpecs")
-     IF EMBEDDED_ARTIFACTS.wireframes[module.code] undefined:
-       BLOCKING_ERROR("Module not in wireframes")
-   ```
-
----
-
-### 7. Display Completion Summary
-
-```
-══════════════════════════════════════════════════════════════
-  [OK] HTML DEPLOY COMPLETE — {application_name}
-══════════════════════════════════════════════════════════════
-
-Modules: {count} ({names})
-
-[DIR] Artifact generated:
-  ba-interactive.html — Interactive document
-     Path: {output_path}
-     Pre-populated: {module_count} modules, {total_uc} use cases,
-       {total_br} business rules, {total_wireframes} wireframes
-
-[NEXT] Review & Validation:
-  1. Open ba-interactive.html in browser
-  2. Review all modules, use cases, business rules
-  3. Validate wireframes and permissions
-  4. If OK: /derive-prd then /ralph-loop to begin development
-  5. If changes needed: /business-analyse to iterate
-
-══════════════════════════════════════════════════════════════
-```
-
----
-
-## SELF-VERIFICATION (BEFORE COMPLETION)
-
-1. `ba-interactive.html` exists and >100KB
-2. FEATURE_DATA.moduleSpecs has entries for ALL modules
-3. cadrage.scope uses HTML keys (vital/important/optional/excluded)
-4. Wireframes use format/content fields (not mockupFormat/mockup)
-5. POST-CHECK verification all passed
-
-**IF any check fails -> generate missing artifact before completing.**
-
----
-
-## NEXT STEP
-
-Load: `steps/step-06-review.md`