@atlashub/smartstack-cli 4.80.0 → 5.0.0

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

@@ -1,304 +0,0 @@
----
-name: step-01-apply
-description: Apply review corrections from ba-review.json, create new version, regenerate all artifacts
-model: opus
----
-
-> **Context files:** `references/review-data-mapping.md`
-
-# Step 01: Apply Review Corrections
-
-Apply corrections exported from the interactive HTML review (`ba-review.json`) to create a new version of the business analysis with all downstream artifacts regenerated.
-
-## Prerequisites
-
-- `workflow_type = "review"` (set by step-00)
-- `review_json_path` points to a valid `ba-review.json` file
-- `application_name` and `docs_dir` are set
-
-## Flow
-
-1. Read and validate ba-review.json
-2. Read existing master index.json and version directory
-3. Create new version
-4. Apply cadrage corrections (reverse mapping)
-5. Apply module corrections
-6. Apply consolidation corrections
-7. Preserve review comments
-8. Regenerate HTML
-9. Update manifest
-10. Display completion summary
-
----
-
-## Step 1: Read and Validate ba-review.json
-
-```
-1. Read file at {review_json_path}
-2. Parse JSON
-3. Validate required structure:
-   - _reviewMeta: { sourceVersion, sourceApplicationId, exportedAt }
-   - metadata: { applicationId, version }
-   - cadrage: { ... }
-   - modules: [ ... ]
-   - moduleSpecifications: { ... }
-4. If validation fails → display error with missing fields, STOP
-5. Display: "Review file valid: {_reviewMeta.changeSummary}"
-```
-
-**Store:**
-```yaml
-review_data: parsed ba-review.json object
-source_version: _reviewMeta.sourceVersion
-change_summary: _reviewMeta.changeSummary
-```
-
-## Step 2: Read Existing Master Index.json
-
-```
-1. Locate master index.json from docs_dir (ba-006: docs/{projectSlug}/v{X.Y}/index.json, legacy: docs/{app}/business-analyse/v{X.Y}/index.json)
-2. Read and parse
-3. Verify metadata.applicationId matches _reviewMeta.sourceApplicationId
-4. Store as existing_master_index
-5. Read all thematic files referenced in index.json (cadrage.json, entities.json, rules.json, etc.)
-```
-
-## Step 3: Create New Version
-
-Determine version bump based on changes:
-
-```
-IF change_summary.modulesAdded.length > 0 OR change_summary.modulesRemoved.length > 0:
-  version_type = "major"  (v1.0 → v2.0)
-ELSE:
-  version_type = "minor"  (v1.0 → v1.1)
-
-Call ba-writer.createVersion(existing_master.id, "Review corrections applied from v{source_version}")
-```
-
-**Store:**
-```yaml
-new_version: string (e.g., "1.1" or "2.0")
-new_docs_dir: path to new version directory
-new_version_dir: path to new version directory (contains index.json + thematic files)
-```
-
-## Step 4: Apply Cadrage Corrections
-
-> **Reference:** `references/review-data-mapping.md` for exact field mapping
-
-Read the new version's cadrage.json and apply reverse mapping from review data:
-
-```
-1. Scope mapping (review → cadrage.json):
-   - cadrage.scope.inscope[] → cadrage.globalScope.inScope[]
-   - cadrage.scope.outofscope[] → cadrage.globalScope.outOfScope[]
-   (Extract name from {name, description} objects)
-
-2. Stakeholders mapping:
-   - For each review stakeholder:
-     - role → role (preserved)
-     - function → function
-     - tasks → tasks
-     - access → involvement (reverse: admin→decision-maker, manager→consulted, contributor→end-user, viewer→informed)
-     - frequency → frequency (reverse: daily→Quotidien, weekly→Hebdomadaire, monthly→Mensuel, occasional→Occasionnel)
-     - frustrations → painPoints (split by newline)
-
-3. Problem/Vision mapping:
-   - cadrage.problem.description → cadrage.problem
-   - cadrage.problem.trigger → cadrage.trigger
-   - cadrage.vision.changes → cadrage.toBe
-   - cadrage.current.tools → cadrage.asIs
-
-4. Risks mapping:
-   - For each review risk → cadrage.risks[] (direct mapping, generate RISK-NNN IDs if missing)
-
-5. Acceptance criteria:
-   - cadrage.success.definition → cadrage.acceptanceCriteria[] (split by newline, generate AC-NNN IDs)
-
-Update cadrage.json with corrected data and update its hash in index.json
-```
-
-## Step 5: Apply Module Corrections
-
-```
-FOR EACH moduleCode in review_data.moduleSpecifications:
-  1. Check if module exists in current index.json.modules[]
-     - If NEW module (in change_summary.modulesAdded):
-       a. Add to index.json.modules[] with metadata from review
-       b. Create module directory and entities.json, rules.json, usecases.json, etc. via ba-writer
-     - If REMOVED module (in change_summary.modulesRemoved):
-       a. Mark module status as "removed" in index.json (do NOT delete files)
-     - If EXISTING module:
-       a. Update module's thematic files
-
-  2. Reverse-map module specification data:
-     - review.useCases[] → usecases.json.useCases[]
-       (name→name, actor→primaryActor, steps→mainScenario (split by \n), alternative→alternativeScenarios)
-     - review.businessRules[] → rules.json.businessRules[]
-       (name→name, category→category, statement→statement, example→examples[])
-     - review.entities[] → entities.json.entities[]
-       (name→name, description→description, attributes→attributes, relationships→relationships)
-     - review.permissions[] → permissions.json.permissionMatrix
-       (reverse "Role|Action" format → {permissions[], roleAssignments[]})
-
-  3. Update each module's thematic files via ba-writer.enrichSection()
-  4. Update hashes in index.json for modified files
-```
-
-## Step 6: Apply Consolidation Corrections
-
-```
-IF review_data.consolidation exists:
-  1. Reverse-map interactions:
-     - consolidation.interactions[] → consolidation.json.crossModuleInteractions[]
-       (from→fromModule, to→toModule, description→description)
-
-  2. Reverse-map E2E flows:
-     - consolidation.e2eFlows[] → consolidation.json.e2eFlows[]
-       (name→name, steps→steps, actors preserved)
-
-  3. Update consolidation.json and update hash in index.json
-```
-
-## Step 7: Preserve Review Comments
-
-Store all review feedback in a new review.json file:
-
-```
-review_section = {
-  appliedAt: new Date().toISOString(),
-  sourceVersion: source_version,
-  comments: review_data.comments || [],          // inline structured comments
-  specComments: review_data.specComments || {},   // textarea comments per spec item
-  wireframeComments: review_data.wireframeComments || {},  // wireframe feedback
-  changeSummary: change_summary
-}
-
-Create review.json with review_section and update hash in index.json
-```
-
-> `review.json` is an AUDIT artifact — it preserves the review trail for traceability. No downstream skill consumes it.
-
-## Step 8: Determine Correction Routing
-
-Analyze the corrections applied to determine which phase needs re-execution:
-
-```
-analysis_changes = false
-ui_changes = false
-
-FOR EACH module in corrected_modules:
-  IF entities, rules, usecases, or permissions were modified:
-    analysis_changes = true
-  IF screens, wireframes, or navigation were modified:
-    ui_changes = true
-
-IF analysis_changes AND ui_changes:
-  route = "both"
-ELSE IF analysis_changes:
-  route = "analysis"
-ELSE IF ui_changes:
-  route = "ui"
-ELSE:
-  route = "html-only"
-```
-
-## Step 9: Regenerate Interactive HTML
-
-Delegate HTML generation to `/business-analyse-html` skill:
-
-```
-1. Load skill: /business-analyse-html with feature_id
-2. The skill handles: collect → build → render → verify
-3. Output: {new_version_dir}/ba-interactive.html
-```
-
-## Step 10: Update Project Index
-
-```
-1. Read {docs_dir}/index.json (project master index)
-2. Update version, lastModified, status
-3. Write {docs_dir}/index.json
-4. Legacy: if docs/index.json global manifest exists, also update it
-```
-
-## Step 10b: Update Status
-
-```javascript
-ba-writer.updateStatus({feature_id}, "reviewed")
-```
-
-## Step 11: Display Completion Summary
-
-```
-=====================================================================
-  REVIEW CORRECTIONS APPLIED SUCCESSFULLY
-=====================================================================
-
-| Field                | Value                                |
-|----------------------|--------------------------------------|
-| Application          | {application_name}                   |
-| Previous version     | v{source_version}                    |
-| New version          | v{new_version}                       |
-| Version type         | {major/minor}                        |
-
-Changes applied:
-| Change               | Count                                |
-|----------------------|--------------------------------------|
-| Cadrage modified     | {yes/no}                             |
-| Modules added        | {count} ({list})                     |
-| Modules removed      | {count} ({list})                     |
-| Modules modified     | {count} ({list})                     |
-| Comments preserved   | {count}                              |
-
-Artifacts regenerated:
-| Artifact             | Path                                 |
-|----------------------|--------------------------------------|
-| Master index.json    | {new_version_dir}/index.json         |
-| ba-interactive.html  | {new_version_dir}/ba-interactive.html|
-| Thematic files       | {new_version_dir}/*.json             |
-| Manifest             | docs/index.json                      |
-
-NEXT STEPS (based on correction routing: {route}):
-```
-
-Display next steps based on `route`:
-
-```
-IF route == "analysis":
-  "1. Run /business-analyse step-03 for modules: {corrected_module_list}"
-  "2. Then run /business-analyse-design to update UI specs"
-  "3. Then run /business-analyse-html to regenerate documentation"
-
-IF route == "ui":
-  "1. Run /business-analyse-design for modules: {corrected_module_list}"
-  "2. Then run /business-analyse-html to regenerate documentation"
-
-IF route == "both":
-  "1. Run /business-analyse step-03 for modules: {analysis_corrected_modules}"
-  "2. Then run /business-analyse-design for modules: {ui_corrected_modules}"
-  "3. Then run /business-analyse-html to regenerate documentation"
-
-IF route == "html-only":
-  "HTML has been regenerated. Review the updated document."
-  "If satisfied, run /business-analyse-handoff to generate PRD files."
-
-IF no corrections (client approves):
-  "No corrections needed. Run /business-analyse-handoff to generate PRD files."
-  "Then run /business-analyse-develop to start development."
-```
-
-```
-=====================================================================
-```
-
-## Error Handling
-
-| Error | Action |
-|-------|--------|
-| ba-review.json malformed | Display structure errors, STOP |
-| Source version mismatch | Warn but continue (corrections may still apply) |
-| Module not found for update | Skip module, warn user |
-| HTML generation fails | Warn but continue (can be re-run manually) |
-| Manifest update fails | Warn but continue |

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

@@ -1,136 +0,0 @@
----
-name: business-analyse-status
-description: Display the current state of business analysis cycle, show progress per module, and recommend next steps.
-user-invocable: true
----
-
-# /business-analyse-status
-
-Display the current state of the business analysis cycle for the active feature.
-
-## Trigger
-
-- Explicit: `/business-analyse-status` or `/business-analyse-status <feature-id>`
-- When the user asks "where are we?", "what's the status?", "what's left to do?"
-
-## Execution
-
-### Step 1 — Locate project(s)
-
-1. Glob `docs/*/v*/index.json` to discover all projects (ba-006 format)
-2. Also check legacy paths: `docs/business-analyse/v*/index.json`, `docs/*/business-analyse/v*/index.json`
-3. If `<feature-id>` is provided, filter to matching project
-4. If 0 projects found, display:
-   ```
-   Aucune analyse métier trouvée dans docs/.
-   → Lancez /business-analyse pour démarrer.
-   ```
-5. If 1 project → auto-select
-6. If N projects → list ALL projects with their status:
-   ```
-   Projets disponibles :
-   | # | Projet        | Version | Apps | Modules | Status       |
-   |---|---------------|---------|------|---------|--------------|
-   | 1 | projet-rh     | v1.0    | 2    | 6       | consolidated |
-   | 2 | commande-repas| v1.0    | 1    | 3       | specified    |
-   ```
-   Then ask which project to display details for.
-
-### Step 2 — Read state
-
-Read the following files (all optional — missing = not done):
-
-| File | What it tells us |
-|------|-----------------|
-| `index.json` | Feature exists, metadata, status, module list |
-| `cadrage.json` | Cadrage done |
-| Per module: `entities.json` | Entities specified |
-| Per module: `rules.json` | Business rules specified |
-| Per module: `usecases.json` | Use cases specified |
-| Per module: `permissions.json` | Permissions defined |
-| Per module: `screens.json` | UI design done |
-| Per module: `navigation.json` | Navigation tree done |
-| Per module: `handoff.json` | Handoff/PRD generated |
-| `ba-interactive.html` (in `{docs_dir}/`) | HTML document generated |
-| `ba-review.json` (in project root or `{docs_dir}/`) | Client review pending |
-
-### Step 3 — Compute progress
-
-For each module, determine completion of each phase:
-
-| Phase | Required files | Skill |
-|-------|---------------|-------|
-| Cadrage | status >= `"framed"` AND `cadrage.json` has context/stakeholders/scope | `/business-analyse` |
-| Structure | status >= `"decomposed"` AND modules[] non-empty with anticipatedSections | `/business-analyse` |
-| Specification | status >= `"specified"` (per module) AND entities/rules/usecases/permissions non-empty | `/business-analyse` |
-| Consolidation | status >= `"consolidated"` AND consolidation.json exists | `/business-analyse` |
-| Design | status >= `"designed"` AND `screens.json` non-empty per module | `/business-analyse-design` |
-| HTML | `ba-interactive.html` exists and > 100KB | `/business-analyse-html` |
-| Review | status >= `"reviewed"` OR `ba-review.json` exists (pending) | `/business-analyse-review` |
-| Handoff | status >= `"handed-off"` AND `.ralph/prd-*.json` exists | `/business-analyse-handoff` |
-
-### Step 4 — Display
-
-Use this exact format:
-
-```
-══════════════════════════════════════════════════
-  Business Analyse — {projectSlug}
-  Version {version} · {lastModified}
-══════════════════════════════════════════════════
-
-  {checkmark} Cadrage              {status}
-  {checkmark} Spécification        {X}/{Y} modules
-  {checkmark} Design UI            {X}/{Y} modules
-  {checkmark} Document HTML        {status}
-  {checkmark} Review client        {status}
-  {checkmark} Handoff              {status}
-
-  Détail par module :
-  ┌──────────────────┬──────┬────────┬────────┬──────────┐
-  │ Module           │ Spec │ Design │ Review │ Handoff  │
-  ├──────────────────┼──────┼────────┼────────┼──────────┤
-  │ {moduleName}     │  ✓   │  ✓     │  ○     │  ·       │
-  │ {moduleName}     │  ✓   │  ○     │  ·     │  ·       │
-  └──────────────────┴──────┴────────┴────────┴──────────┘
-
-  Prochaine étape recommandée :
-  → {recommendation}
-
-══════════════════════════════════════════════════
-```
-
-Legend:
-- `✓` = done (green if terminal supports it)
-- `○` = in progress / partial
-- `·` = not started
-
-### Step 5 — Recommend next step
-
-Based on the current state, recommend ONE next action:
-
-| State | Recommendation |
-|-------|---------------|
-| No cadrage | `Lancez /business-analyse pour démarrer l'analyse.` |
-| Cadrage done, spec incomplete | `Continuez /business-analyse pour spécifier les modules restants.` |
-| All modules specified, no design | `Lancez /business-analyse-design <feature-id> pour concevoir les interfaces.` |
-| Design done, no HTML | `Lancez /business-analyse-html <feature-id> pour générer le document client.` |
-| HTML generated, no review | `Envoyez ba-interactive.html au client pour review.` |
-| ba-review.json exists | `Lancez /business-analyse-review pour appliquer les corrections client.` |
-| Review done / approved | `Lancez /business-analyse-handoff pour générer les PRD.` |
-| Handoff done | `Analyse complète ! Lancez /business-analyse-develop pour démarrer le développement.` |
-
-## Rules
-
-- This skill is READ-ONLY — it never modifies any file
-- Use the `ba-reader` agent to read JSON files if available
-- Keep output concise — the user wants a quick overview, not a full report
-- If a module has partial data (e.g., entities but no rules), show it as `○` (in progress)
-
-<success_criteria>
-- Projet(s) decouverts via structure docs/ (format ba-006 + legacy)
-- Progression calculee par module pour chaque phase
-- Tableau de statut genere avec symboles corrects
-- Recommandation d'etape suivante fournie
-- Aucun fichier modifie (lecture seule)
-</success_criteria>

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

@@ -1,129 +0,0 @@
----
-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>

package/templates/skills/cc-agent/references/agent-behavior-patterns.md

@@ -1,95 +0,0 @@
-# Agent Behavior Pattern Templates
-
-> Referenced from `steps/step-02-generate.md` — System prompt templates for each agent behavior pattern.
-
----
-
-## Explorer Pattern
-
-```markdown
-You are a specialized exploration agent for {purpose}.
-
-## Workflow
-
-1. **Search**: Use Grep and Glob to find relevant files
-2. **Read**: Load and analyze discovered files
-3. **Analyze**: Identify patterns, dependencies, and relationships
-4. **Report**: Present findings in structured format
-
-## Execution Rules
-
-- Run independent searches in parallel
-- Always cite file paths and line numbers
-- Focus only on what's relevant to the request
-- Present findings as tables or structured lists
-
-## Output Format
-
-List findings with file references:
-```
-- path/to/file.ext:line - Description of finding
-```
-```
-
----
-
-## Modifier Pattern
-
-```markdown
-You are a code modification specialist for {purpose}.
-
-## Workflow
-
-1. **Read**: Load all specified files with Read tool
-2. **Analyze**: Understand current structure and patterns
-3. **Edit**: Apply requested changes using Edit tool
-4. **Validate**: Verify changes are correct
-5. **Report**: List what was modified
-
-## Execution Rules
-
-- Follow existing code style exactly
-- Preserve all formatting and indentation
-- Make minimal changes to achieve the goal
-- Never add comments unless requested
-
-## Output Format
-
-```
-- path/to/file.ext: [Description of change]
-```
-```
-
----
-
-## Validator Pattern
-
-```markdown
-You are a validation specialist for {purpose}.
-
-## Workflow
-
-1. **Scan**: Find all files to validate
-2. **Check**: Apply validation rules to each file
-3. **Report**: Present issues with severity and recommendations
-
-## Execution Rules
-
-- Check ALL files in scope, not just a sample
-- Every issue must have a clear recommendation
-- Use severity levels: ERROR, WARN, INFO
-- Present results as tables
-
-## Output Format
-
-| File | Severity | Issue | Recommendation |
-|------|----------|-------|----------------|
-| path | ERROR | ... | ... |
-```
-
----
-
-## Custom Pattern
-
-Use the user's description from Step 1 to generate appropriate sections.
-Include Workflow, Execution Rules, and Output Format sections tailored to the specific purpose.