@atlashub/smartstack-cli 2.0.0 → 2.2.0

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

@@ -1,40 +1,36 @@
 ---
 name: business-analyse
-description: Business Analysis - Complete business analysis workflow (BABOK/IEEE 830) with progressive step loading and context refresh.
-argument-hint: "[-a] [-s] [-e] [-r <task-id>] <feature description>"
+description: Business Analysis - VibeCoding-focused workflow with JSON output, proactive suggestions, and 4 use cases (new, question, refactoring, micro).
+argument-hint: "[-a] [-e] [-q <FEAT-ID> \"question\"] [-r <FEAT-ID> \"change\"] [-m] <feature description>"
 ---
 
 <objective>
-Execute systematic business analysis workflows following BABOK v3 and IEEE 830 standards.
-This skill uses progressive step loading to minimize context usage and maintain fresh context throughout the workflow.
+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.
 </objective>
 
 <quick_start>
-**Basic usage:**
+**Four use cases:**
 
 ```bash
-/business-analyse Module de gestion des clients
-```
+# A. New feature (full workflow)
+/business-analyse Order management module
 
-**Recommended workflow (autonomous with save):**
+# B. Question about existing feature
+/business-analyse -q FEAT-001 "What permissions does the manager have?"
 
-```bash
-/business-analyse -a -s Gestion des commandes avec workflow validation
+# C. Refactoring (delta on existing)
+/business-analyse -r FEAT-001 "Add export PDF functionality"
+
+# D. Micro-feature (one-shot, minimal questions)
+/business-analyse -m Add a status field to orders
 ```
 
-**Resume a previous analysis:**
+**Recommended autonomous workflow:**
 
 ```bash
-/business-analyse -r FEAT-001
+/business-analyse -a New payment gateway integration
 ```
 
-**Flags:**
-
-- `-a` (auto): Skip confirmations
-- `-s` (save): Save outputs to `.business-analyse/`
-- `-e` (economy): No subagents, direct tool usage
-- `-r` (resume): Resume from a previous FEAT-ID
-
 See `<parameters>` for complete flag list.
 </quick_start>
 
@@ -44,37 +40,42 @@ See `<parameters>` for complete flag list.
 **Enable flags (turn ON):**
 | Short | Long | Description |
 |-------|------|-------------|
-| `-a` | `--auto` | Autonomous mode: skip confirmations, auto-approve |
-| `-s` | `--save` | Save mode: output to `.business-analyse/` (default: true) |
-| `-e` | `--economy` | Economy mode: no subagents, save tokens |
-| `-r` | `--resume` | Resume mode: continue from a previous FEAT-ID |
+| `-a` | `--auto` | Autonomous mode: skip confirmations |
+| `-e` | `--economy` | Economy mode: no subagents |
+| `-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 |
 | `-i` | `--interactive` | Interactive mode: configure flags via AskUserQuestion |
 
 **Disable flags (turn OFF):**
 | Short | Long | Description |
 |-------|------|-------------|
 | `-A` | `--no-auto` | Disable auto mode |
-| `-S` | `--no-save` | Disable save mode |
 | `-E` | `--no-economy` | Disable economy mode |
 </flags>
 
 <examples>
 ```bash
-# Basic usage
-/business-analyse Module gestion clients
+# A. New feature analysis (full workflow)
+/business-analyse Order management module
 
-# Autonomous mode (no confirmations)
-/business-analyse -a Module gestion clients
+# B. Question about existing feature
+/business-analyse -q FEAT-001 "What permissions does the manager have?"
 
-# Economy mode (save tokens)
-/business-analyse -e Module gestion clients
+# C. Refactoring (create v1.1)
+/business-analyse -r FEAT-001 "Add export PDF functionality"
 
-# Resume a previous feature
-/business-analyse -r FEAT-001
-/business-analyse -r 001  # Partial match supported
+# D. Micro-feature (minimal questions)
+/business-analyse -m Add a status field to orders
+
+# Autonomous mode
+/business-analyse -a New payment gateway
+
+# Economy mode (no subagents)
+/business-analyse -e Order management
 
 # Combined flags
-/business-analyse -a -e Module gestion clients
+/business-analyse -a -e Order management
 ```
 </examples>
 
@@ -84,77 +85,90 @@ 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. Feature ID generated as `FEAT-NNN`
+4. Use case determined by flags: question > refactor > micro > new (default)
+5. Feature ID generated as `FEAT-NNN` for new features
 </parsing_rules>
 
 </parameters>
 
 <output_structure>
-**When `{save_mode}` = true (default):**
+**All outputs saved to PROJECT directory:**
 
-All outputs saved to PROJECT directory:
 ```
-.business-analyse/business/{app}/modules/{module}/features/{FEAT-NNN}/
-├── 00-context.md              # Params, user request, timestamp, progress
-├── 1-discovery.md             # Phase 1: Discovery findings
-├── 2-business-requirements.md # Phase 2: BRD
-├── 3-functional-specification.md # Phase 3: FRD
-├── validation.json            # Phase 4: Validation gate
-├── 4-development-handoff.md   # Phase 5: Dev prompt
-└── tracking/
-    ├── changes/
-    ├── bugs/
-    └── hotfixes/
+docs/business/{app}/{module}/business-analyse/
+├── v1.0/
+│   └── feature.json    # Single JSON enriched progressively (new)
+├── v1.1/
+│   └── feature.json    # Delta version (refactoring)
+└── v2.0/
+    └── feature.json    # Major version
 ```
 
-**Ralph Loop files (generated by step-05):**
+**Ralph Loop files (generated by step-04):**
 ```
 .ralph/
-├── prd.json          # Task breakdown for /ralph-loop -r
-├── progress.txt      # Links to BA documents
-├── logs/
-└── reports/
+├── prd.json            # Task breakdown for /ralph-loop -r
+└── progress.txt        # Links to BA documents
 ```
+
+**No intermediate markdown files - all state in feature.json**
 </output_structure>
 
 <resume_workflow>
-**Resume mode (`-r {FEAT-ID}`):**
+**Question mode (`-q {FEAT-ID} "question"`):**
 
 When provided, step-00 will:
 
-1. Locate the feature folder in `.business-analyse/`
-2. Read `00-context.md` to restore state
-3. Find the last completed step
-4. Continue from the next step
+1. Locate the feature.json in `docs/business/{app}/{module}/business-analyse/v{X.Y}/`
+2. Load ba-reader agent to answer question from existing feature.json
+3. Return answer and EXIT (no further steps)
+
+**Refactoring mode (`-r {FEAT-ID} "change description"`):**
+
+When provided, step-00 will:
+
+1. Locate existing feature.json
+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
 </resume_workflow>
 
 <workflow>
-**Standard flow:**
+**Use case routing (step-00):**
+
 1. Parse flags and feature description
-2. If `-r`: Execute resume workflow
-3. Create output folder and 00-context.md
-4. Load step-01-discover.md -> elicitation with ULTRATHINK
-5. Load step-02-analyse.md -> BRD + business rules
-6. Load step-03-specify.md -> FRD + use cases
-7. Load step-04-validate.md -> validation gate
-8. Load step-05-handoff.md -> development prompt
-9. Load step-06-doc-html.md -> React documentation (optional)
+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, skip discovery/analysis → handoff
+5. If default: Full workflow (steps 01-04)
+
+**Full workflow (new features):**
+- **Step 00:** Parse flags, route use case, create feature.json (draft)
+- **Step 01:** Merged discovery + BRD, proactive suggestions (analysed)
+- **Step 02:** FRD + use cases + permissions + navigation (specified)
+- **Step 03:** Validation gate (APPROVED/REJECTED)
+- **Step 04:** Development prompt + Ralph Loop prd.json (handed-off)
+
+**Micro workflow (micro features):**
+- **Step 00:** Create minimal feature.json
+- **Step 04:** Direct handoff (skip 01-03)
 </workflow>
 
 <state_variables>
-**Persist throughout all steps:**
+**Persist throughout all steps via feature.json:**
 
 | Variable                | Type    | Description                                            |
 | ----------------------- | ------- | ------------------------------------------------------ |
-| `{feature_description}` | string  | What to analyze (flags removed)                        |
 | `{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              |
+| `{version}`             | string  | SemVer (1.0, 1.1, 2.0, etc.)                           |
 | `{application_name}`    | string  | Target application name                                |
 | `{module_name}`         | string  | Target module name                                     |
 | `{context}`             | string  | Always "business" for BA                               |
 | `{auto_mode}`           | boolean | Skip confirmations                                     |
-| `{save_mode}`           | boolean | Save outputs (default: true)                           |
 | `{economy_mode}`        | boolean | No subagents, direct tool usage only                   |
-| `{output_dir}`          | string  | Full path to feature output directory                  |
+| `{docs_dir}`            | string  | `docs/business/{app}/{module}/business-analyse/v{X.Y}/` |
 
 </state_variables>
 
@@ -169,13 +183,11 @@ When provided, step-00 will:
 
 | Step | File                         | Model  | Purpose                                              |
 | ---- | ---------------------------- | ------ | ---------------------------------------------------- |
-| 00   | `steps/step-00-init.md`      | Haiku  | Parse flags, create structure, initialize state      |
-| 01   | `steps/step-01-discover.md`  | Opus   | Elicitation with ULTRATHINK (load questionnaire)     |
-| 02   | `steps/step-02-analyse.md`   | Sonnet | BRD + business rules formalization                   |
-| 03   | `steps/step-03-specify.md`   | Sonnet | FRD + use cases + permissions                        |
-| 04   | `steps/step-04-validate.md`  | Haiku  | Validation gate (APPROVED/REJECTED)                  |
-| 05   | `steps/step-05-handoff.md`   | Opus   | Development prompt generation                        |
-| 06   | `steps/step-06-doc-html.md`  | Sonnet | React documentation (optional)                       |
+| 00   | `steps/step-00-init.md`      | Haiku  | Parse flags, route use case, create feature.json     |
+| 01   | `steps/step-01-analyse.md`   | Opus   | Merged discovery+BRD, proactive suggestions          |
+| 02   | `steps/step-02-specify.md`   | Sonnet | FRD + use cases + permissions + navigation           |
+| 03   | `steps/step-03-validate.md`  | Haiku  | Validation gate (APPROVED/REJECTED)                  |
+| 04   | `steps/step-04-handoff.md`   | Opus   | Development prompt + Ralph Loop prd.json             |
 
 </step_files>
 
@@ -184,53 +196,53 @@ When provided, step-00 will:
 
 Load ONLY relevant categories based on feature type:
 
-| Category | File                                | When to load |
-| -------- | ----------------------------------- | ------------ |
-| 01       | `questionnaire/01-context.md`       | Always       |
-| 02       | `questionnaire/02-stakeholders.md`  | Always       |
-| 03       | `questionnaire/03-scope.md`         | Always       |
-| 04       | `questionnaire/04-data.md`          | If data-centric |
-| 05       | `questionnaire/05-integrations.md`  | If integrations |
-| 06       | `questionnaire/06-security.md`      | Always (minimal) |
-| 07       | `questionnaire/07-ui.md`            | If UI-centric |
-| 08       | `questionnaire/08-performance.md`   | If performance-critical |
-| 09       | `questionnaire/09-constraints.md`   | If constraints exist |
-| 10       | `questionnaire/10-documentation.md` | If doc required |
-| 11       | `questionnaire/11-data-lifecycle.md` | If data-centric or full module |
-| 12       | `questionnaire/12-migration.md`      | Always for new modules         |
-| 13       | `questionnaire/13-cross-module.md`   | Always for new modules         |
+| Category | File                                | Questions | When to load |
+| -------- | ----------------------------------- | --------- | ------------ |
+| 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+)**
 
 </questionnaire_files>
 
 <template_files>
 **Progressive template loading:**
 
-| Template | File                          | Used in step |
-| -------- | ----------------------------- | ------------ |
-| discovery | `templates/tpl-discovery.md` | 01           |
-| brd       | `templates/tpl-brd.md`       | 02           |
-| frd       | `templates/tpl-frd.md`       | 03           |
-| handoff   | `templates/tpl-handoff.md`   | 05           |
+| Template | File                                | Used in step |
+| -------- | ----------------------------------- | ------------ |
+| schema   | `schemas/feature-schema.json`       | All steps    |
+| frd      | `templates/tpl-frd.md`              | 02           |
+| handoff  | `templates/tpl-handoff.md`          | 04           |
+| suggestions | `patterns/suggestion-catalog.md` | 01           |
 
 </template_files>
 
 <execution_rules>
 
 - **Load one step at a time** - Only load the current step file
-- **ULTRATHINK** for phases 01, 02, 03, 05 (critical thinking)
-- **Persist state variables** across all steps via 00-context.md
+- **ULTRATHINK** for steps 01, 02, 04 (critical thinking)
+- **State persisted in feature.json** (NOT markdown files)
+- **Use ba-writer agent** for all JSON writes
+- **Use ba-reader agent** for all JSON reads
 - **Follow next_step directive** at end of each step
-- **Save outputs** immediately after each phase
-- **Use parallel agents** for exploration (unless economy_mode)
 - **Context: business only** - Reject platform/personal/system contexts
+- **Use parallel agents** for exploration (unless economy_mode)
 </execution_rules>
 
 <success_criteria>
 
-- Each step loaded progressively (max 300-400 lines/step)
-- All outputs saved to feature folder
+- feature.json enriched progressively through all steps
 - Validation gate passed (APPROVED)
-- Development handoff ready for `/ralph-loop -r` (iterative) or `/feature-full` (one-shot)
-- Ralph Loop prd.json generated with atomic task breakdown
-- Clear completion summary with next steps
+- Development handoff ready for `/ralph-loop -r` or `/feature-full`
+- Ralph Loop prd.json generated
+- Proactive suggestions presented to user
+- All outputs in `docs/business/{app}/{module}/business-analyse/v{X.Y}/`
 </success_criteria>