@atlashub/smartstack-cli 1.1.0

package/templates/commands/notification.md

@@ -0,0 +1,129 @@
+# /notification - Integration Notifications SmartStack
+
+> **Synergie Skill/Commande:**
+> - **Skill** (`templates/skills/notification/`) → Invocation automatique par Claude
+> - **Commande** (`/notification`) → Invocation manuelle par l'utilisateur
+
+---
+
+## ARGUMENTS
+
+```
+/notification <action> [options]
+```
+
+| Action | Description |
+|--------|-------------|
+| `add` | Ajouter une notification dans un service existant |
+| `type` | Creer un nouveau type de notification |
+| `hook` | Creer le hook frontend avec SignalR |
+
+---
+
+## WORKFLOW
+
+### /notification add
+
+Ajoute l'envoi de notification dans un service existant.
+
+**Questions:**
+1. Quel service modifier ? (liste des services)
+2. Quelle methode ? (Create, Update, Delete, etc.)
+3. Qui notifier ? (createur, assigne, role, liste)
+4. Quel type de notification ? (existant ou nouveau)
+
+**Actions:**
+1. Injecter `INotificationService` si pas present
+2. Ajouter l'appel `SendNotificationAsync` dans la methode
+3. Logger l'envoi de notification
+
+### /notification type
+
+Cree un nouveau type de notification.
+
+**Questions:**
+1. Nom du type ? (ex: `ProductCreated`)
+2. Categorie ? (Support, Admin, System, SLA)
+3. Description ?
+
+**Actions:**
+1. Ajouter dans `NotificationType.cs`
+2. Creer migration EF Core
+
+### /notification hook
+
+Cree le hook frontend pour recevoir les notifications en temps reel.
+
+**Questions:**
+1. Quel module ?
+2. Quel type d'entite ?
+
+**Actions:**
+1. Creer `use{Module}Notifications.ts`
+2. Integrer `useSignalR`
+3. Configurer les callbacks
+
+---
+
+## TEMPLATES
+
+### Template SendNotification
+
+```csharp
+await _notificationService.SendNotificationAsync(
+    userId: $USER_ID,
+    type: NotificationType.$TYPE,
+    title: "$TITLE",
+    message: $"$MESSAGE",
+    relatedEntityType: "$ENTITY_TYPE",
+    relatedEntityId: $ENTITY_ID,
+    actionUrl: $"/$MODULE/$ENTITY_ID",
+    cancellationToken: ct);
+
+_logger.LogInformation(
+    "Notification sent to {UserId}: {Type}",
+    $USER_ID, NotificationType.$TYPE);
+```
+
+### Template Hook
+
+```typescript
+// hooks/use{Module}Notifications.ts
+import { useSignalR } from '@/hooks/useSignalR';
+import { useQueryClient } from '@tanstack/react-query';
+import { toast } from 'sonner';
+
+export function use{Module}Notifications() {
+  const queryClient = useQueryClient();
+
+  useSignalR({
+    onNotification: (notification) => {
+      if (notification.relatedEntityType === '{Entity}') {
+        queryClient.invalidateQueries(['{module}']);
+        toast.info(notification.title, {
+          description: notification.message,
+          action: notification.actionUrl ? {
+            label: 'Voir',
+            onClick: () => window.location.href = notification.actionUrl,
+          } : undefined,
+        });
+      }
+    },
+  });
+}
+```
+
+---
+
+## FICHIERS CLES
+
+| Fichier | Role |
+|---------|------|
+| `Domain/Support/Enums/NotificationType.cs` | Types de notification |
+| `Application/Common/Interfaces/INotificationService.cs` | Interface |
+| `Infrastructure/Services/Support/NotificationService.cs` | Implementation |
+| `web/src/hooks/useSignalR.ts` | Hook SignalR |
+
+---
+
+User: $ARGUMENTS

package/templates/commands/oneshot.md

@@ -0,0 +1,57 @@
+---
+description: Ultra-fast feature implementation - Explore then Code then Test
+argument-hint: <feature-description>
+---
+
+You are a rapid implementation specialist. Implement features at maximum speed using the OneShot methodology.
+
+**You need to always ULTRA THINK.**
+
+## Workflow
+
+1. **EXPLORE**: Quick context gathering (5-10 minutes max)
+   - Launch **1-2 parallel subagents maximum** to find relevant files
+   - Prefer `explore-codebase` agent for codebase search
+   - Use `explore-docs` agent ONLY if library-specific knowledge needed
+   - Find files to use as **examples** or **edit targets**
+   - **CRITICAL**: Be surgical - know exactly what to search for
+   - **NO PLANNING PHASE** - gather context and move directly to coding
+
+2. **CODE**: Implement immediately following existing patterns
+   - Start coding as soon as you have basic context
+   - Follow existing codebase style:
+     - Prefer clear variable/method names over comments
+     - Match existing patterns and conventions
+   - **CRITICAL RULES**:
+     - Stay **STRICTLY IN SCOPE** - change only what's needed
+     - NO comments unless absolutely necessary
+     - NO refactoring beyond the feature requirements
+   - Run autoformatting scripts when done
+   - Fix reasonable linter warnings as you go
+
+3. **TEST**: Validate with ESLint and TypeScript
+   - **First check package.json** for available scripts:
+     - Look for: `lint`, `typecheck`, `format`
+     - Run: `npm run lint && npm run typecheck` (or equivalent)
+   - **CRITICAL**: Code must pass linting and type checks
+   - If checks fail: fix errors immediately and re-run
+   - **STAY IN SCOPE**: Don't run full test suite unless explicitly requested
+   - For major changes only: run relevant tests with `npm test -- <pattern>`
+
+## Execution Rules
+
+- **SPEED IS PRIORITY**: Move fast, break nothing
+- **NO PLANNING**: Trust your exploration and code directly
+- **PARALLEL AGENTS**: Max 2 agents during explore phase
+- **MINIMAL TESTS**: Lint + typecheck only (unless user requests more)
+- **STAY FOCUSED**: Implement exactly what's requested, nothing more
+- Never exceed task boundaries
+- If stuck or uncertain: ask user immediately instead of over-exploring
+
+## Priority
+
+Speed > Completeness. Ship fast, iterate later.
+
+---
+
+User: $ARGUMENTS

package/templates/commands/quick-search.md

@@ -0,0 +1,72 @@
+---
+description: Lightning-fast search to answer specific questions - optimized for speed
+argument-hint: <question>
+allowed-tools: Grep, Glob, Read
+model: haiku
+---
+
+You are a rapid search specialist. Answer questions at maximum speed using direct search tools.
+
+## Workflow
+
+1. **IDENTIFY**: Parse the question
+
+   - Extract key search terms
+   - Determine target file types or patterns
+   - **CRITICAL**: Be surgical - know exactly what to search
+
+2. **SEARCH**: Direct tool usage (NO agents)
+
+   - Use `Grep` for code content search with specific patterns
+   - Use `Glob` for file name/path patterns
+   - Launch searches **in parallel** when possible
+   - **SPEED RULE**: Max 2-3 search iterations total
+
+3. **READ**: Targeted file reading
+
+   - `Read` only the most relevant files found
+   - **CRITICAL**: Max 3-5 files - be selective
+   - Scan for the specific answer needed
+
+4. **ANSWER**: Direct response
+   - Immediate answer to the question
+   - Include file references with line numbers (`file.ts:42`)
+   - **NO**: Long explanations or architectural context
+   - **YES**: Concise answer with evidence
+
+## Execution Rules
+
+- **SPEED FIRST**: Answer in under 30 seconds
+- **NO AGENTS**: Use direct tools only (Grep, Glob, Read)
+- **PARALLEL SEARCH**: Run independent searches simultaneously
+- **MINIMAL READING**: Read only what's absolutely necessary
+- **NO DEEP ANALYSIS**: Surface-level answers with citations
+- **STOP EARLY**: Once you have the answer, respond immediately
+
+## Search Patterns
+
+**Finding implementations**:
+
+```
+Grep: pattern="class FooBar" or "function fooBar"
+```
+
+**Finding configs**:
+
+```
+Glob: pattern="**/config.{js,ts,json}"
+```
+
+**Finding imports/usage**:
+
+```
+Grep: pattern="from ['\"].*moduleName['\"]"
+```
+
+## Priority
+
+Speed > Completeness. Fast answers beat perfect answers.
+
+---
+
+User: $ARGUMENTS

package/templates/commands/review.md

@@ -0,0 +1,106 @@
+---
+description: Quick code review - review current PR changes and output directly
+allowed-tools: Bash(npm :*), Bash(git :*), Bash(gh :*), Read, Grep, Glob
+---
+
+You are a code review specialist. Conduct thorough reviews of current PR changes WITHOUT creating review files.
+
+**You need to ULTRA THINK at every step.**
+
+## Workflow
+
+1. **GET PR CONTEXT**: Understand what changed
+   - Use `gh pr view` to get PR info (title, description, number)
+   - Use `gh pr diff` to see all changes
+   - Use `git log origin/main..HEAD` to see commits
+   - Identify all modified files
+   - **CRITICAL**: Review actual changes, not entire codebase
+
+2. **FEATURE REVIEW**: Verify implementation correctness
+   - **Read changed files**: Review implementation in context
+   - **Check requirements**: Compare changes against PR description
+   - **Verify completeness**: Ensure requested features are implemented
+   - **Test coverage**: Check if tests were added for new functionality
+   - **CRITICAL**: Flag incomplete implementations
+
+3. **SECURITY REVIEW**: Deep security analysis
+   - Search for security vulnerabilities in changed code:
+     - **Credentials exposure**: Hardcoded keys, tokens, passwords
+     - **Environment variables**: Check `.env` files are gitignored
+     - **Sensitive data**: Exposed API keys, secrets, private keys
+     - **Input validation**: SQL injection, XSS vulnerabilities
+     - **Authentication**: Auth checks are correct
+     - **Authorization**: Proper permission checks
+     - **Data sanitization**: User input is escaped
+   - Use Grep on changed files:
+     - `password.*=.*['"]` (hardcoded passwords)
+     - `api[_-]?key.*=.*['"]` (hardcoded API keys)
+     - `secret.*=.*['"]` (hardcoded secrets)
+     - `token.*=.*['"]` (hardcoded tokens)
+   - **CRITICAL**: Block if critical security issues found
+
+4. **CODE QUALITY REVIEW**: Style and maintainability
+   - Check code quality in changed files:
+     - **Naming conventions**: Clear, consistent names
+     - **Code duplication**: Repeated logic
+     - **Complexity**: Overly complex functions
+     - **Comments**: Minimal, useful comments only
+     - **Patterns**: Follows existing codebase patterns
+     - **Dependencies**: No unnecessary new dependencies
+   - Note quality issues
+
+5. **AUTOMATED CHECKS**: Linting and build verification
+   - **Check `package.json`** for available scripts
+   - Run checks systematically:
+     - `npm run lint` - Code linting
+     - `npm run typecheck` - TypeScript type checking
+     - `npm run test` - Run relevant tests only
+     - `npm run build` - Build verification
+   - **CRITICAL**: All checks must pass before approval
+   - If failures: Document and request fixes
+
+6. **FINAL VERDICT**: Output review summary
+   - Compile all findings into summary
+   - Rate implementation quality (1-10)
+   - **Decision options**:
+     - **✅ APPROVED**: All checks pass, ready to merge
+     - **🔧 NEEDS FIXES**: Minor issues, list required changes
+     - **🚫 BLOCKED**: Critical issues, cannot proceed
+   - **NO FILE CREATION**: Output everything directly to chat
+
+## Security Search Patterns
+
+```bash
+# Hardcoded secrets
+gh pr diff | grep -iE "(password|api[_-]?key|secret|token)\s*=\s*['\"]"
+
+# Check .env is gitignored
+cat .gitignore | grep -E "^\.env"
+
+# Look for .env in PR
+gh pr diff | grep -E "\.env"
+```
+
+## Code Quality Anti-patterns
+
+- Large functions (>50 lines)
+- Deep nesting (>3 levels)
+- Magic numbers/strings
+- Commented-out code
+
+## Execution Rules
+
+- **ULTRA THINK** at each review phase
+- **NEVER skip security checks** - they are mandatory
+- **Focus on changed code** - don't review entire codebase
+- **Block on critical issues** - don't proceed if unsafe
+- **Stay objective** - report facts, not opinions
+- **NO FILE CREATION**: Output all results directly to chat
+
+## Priority
+
+Security > Correctness > Quality > Speed. Never compromise on security.
+
+---
+
+User: $ARGUMENTS

package/templates/commands/utils/test-web-config.md

@@ -0,0 +1,160 @@
+---
+description: Configure test-web targets from external config file
+argument-hint: [path/to/config.json]
+allowed-tools: Read, Write, AskUserQuestion, Glob
+model: haiku
+---
+
+# /test-web:config - Web test configuration
+
+Updates web test configuration from external file.
+
+> **CLAUDE INSTRUCTION:** The `AskUserQuestion({...})` blocks are instructions to use the `AskUserQuestion` tool **interactively**. You MUST execute the tool with these parameters to get user response BEFORE continuing.
+
+## Usage
+
+```
+/test-web:config                     # Ask for file interactively
+/test-web:config path/to/config.json # Load file directly
+```
+
+## Workflow
+
+### 1. Get source file
+
+**If argument provided**: Use given path
+
+**Otherwise**: Ask user
+
+```
+AskUserQuestion:
+  question: "Which configuration file do you want to load?"
+  header: "Config file"
+  options:
+    - label: "Search in project"
+      description: "Glob to find *test-web*.json files"
+    - label: "Enter path"
+      description: "Manually specify file path"
+```
+
+### 2. Validate file
+
+1. Check file exists
+2. Read JSON content
+3. Validate structure (targets, settings)
+
+**Expected structure**:
+
+```json
+{
+  "targets": [
+    {
+      "name": "string (required)",
+      "url": "string (required for fetch)",
+      "query": "string (required for search)",
+      "type": "fetch|search (required)",
+      "expects": {
+        "status": "number (optional)",
+        "contains": ["strings"] "(optional)",
+        "hasResults": "boolean (optional)"
+      }
+    }
+  ],
+  "chrome": {
+    "enabled": "boolean",
+    "targets": [...]
+  },
+  "settings": {
+    "timeout": "number",
+    "retries": "number",
+    "reportPath": "string"
+  }
+}
+```
+
+### 3. Merge or replace
+
+```
+AskUserQuestion:
+  question: "How to apply new configuration?"
+  header: "Mode"
+  options:
+    - label: "Replace"
+      description: "Completely replace existing config"
+    - label: "Merge (add)"
+      description: "Add new targets to existing"
+```
+
+### 4. Apply
+
+1. Read existing [.claude/test-web/config.json](.claude/test-web/config.json)
+2. Apply chosen mode (replace or merge)
+3. Write result
+
+### 5. Confirm
+
+```
+CONFIG UPDATED
+────────────────────────────────
+Source:  {source_file_path}
+Mode:    {replace|merge}
+Targets: {total_count}
+────────────────────────────────
+
+Test now:
+/test-web --quick
+```
+
+## Example source files
+
+### Minimal
+
+```json
+{
+  "targets": [
+    {
+      "name": "My site",
+      "url": "https://example.com",
+      "type": "fetch",
+      "expects": { "status": 200 }
+    }
+  ]
+}
+```
+
+### Complete
+
+```json
+{
+  "targets": [
+    {
+      "name": "API Health",
+      "url": "https://api.example.com/health",
+      "type": "fetch",
+      "expects": {
+        "status": 200,
+        "contains": ["healthy", "ok"]
+      }
+    },
+    {
+      "name": "SEO Check",
+      "query": "site:example.com",
+      "type": "search",
+      "expects": { "hasResults": true }
+    }
+  ],
+  "settings": {
+    "timeout": 60000,
+    "retries": 3
+  }
+}
+```
+
+## Available templates
+
+Configuration templates are available in:
+[templates/test-web/](templates/test-web/)
+
+---
+
+User: $ARGUMENTS

package/templates/commands/utils/test-web.md

@@ -0,0 +1,151 @@
+---
+description: Test web accessibility and content validation
+argument-hint: --quick|--chrome|--report|<url>
+allowed-tools: WebFetch, WebSearch, Read, Write, Bash
+model: sonnet
+---
+
+# /test-web - Web testing agent
+
+Tests accessibility and content of project web resources.
+
+## Execution Modes
+
+| Mode | Flag | Description |
+|------|------|-------------|
+| Quick | `--quick` | WebFetch only (HTTP 200 + text content) |
+| Chrome | `--chrome` | E2E tests with Claude for Chrome (requires `claude --chrome`) |
+| Report | `--report` | Generates detailed report in reports/ |
+| Full | (default) | Quick + Chrome if available |
+
+## Configuration
+
+Reads configuration from: [.claude/test-web/config.json](.claude/test-web/config.json)
+
+## Workflow
+
+### Quick Mode (--quick)
+
+1. **Load configuration**
+   ```bash
+   cat .claude/test-web/config.json
+   ```
+
+2. **For each target type "fetch"**:
+   - `WebFetch(url, "Verify that the page is accessible and contains: {expects.contains}")`
+   - Check HTTP status (200 expected)
+   - Verify expected content presence
+
+3. **For each target type "search"**:
+   - `WebSearch(query)`
+   - Verify results exist
+
+4. **Report**: Display results in console
+
+### Chrome Mode (--chrome)
+
+**Prerequisites**:
+- "Claude for Chrome" extension installed
+- Max/Pro/Team/Enterprise plan
+- Claude Code launched with: `claude --chrome`
+
+1. **Verify Chrome mode is active**
+2. **For each chrome target**:
+   - Navigate to URL
+   - Execute actions (click, verify, etc.)
+   - Capture screenshots if requested
+
+3. **Report**: Generate report with captures
+
+### Report Mode (--report)
+
+Generates markdown file in [.claude/test-web/reports/](.claude/test-web/reports/):
+
+```markdown
+# Test Web Report - YYYY-MM-DD HH:mm
+
+## Summary
+| Target | Status | Time |
+|--------|--------|------|
+| ... | PASS/FAIL | Xms |
+
+## Details
+### Target Name
+- URL: ...
+- Expected: ...
+- Result: ...
+- Screenshot: (if chrome mode)
+```
+
+## Examples
+
+### Quick test of all configured URLs
+
+```
+/test-web --quick
+```
+
+### E2E test with browser
+
+```bash
+# First launch Claude Code with Chrome
+claude --chrome
+
+# Then execute tests
+/test-web --chrome
+```
+
+### Test specific URL
+
+```
+/test-web https://github.com/SIMON-Atlashub/atlashub-claudecode-cli
+```
+
+### Generate detailed report
+
+```
+/test-web --report
+```
+
+## Output Format
+
+### Success
+
+```
+TEST WEB RESULTS
+────────────────────────────────
+✅ GitHub Repository     200 OK    "README" found
+✅ npm Package           200 OK    "claude-tools" found
+✅ Google Indexation     Results   Found in search
+
+Status: 3/3 PASS
+────────────────────────────────
+```
+
+### Failure
+
+```
+TEST WEB RESULTS
+────────────────────────────────
+✅ GitHub Repository     200 OK    "README" found
+❌ npm Package           404       Package not found
+⚠️ Google Indexation     Results   No relevant results
+
+Status: 1/3 PASS, 1 FAIL, 1 WARNING
+────────────────────────────────
+```
+
+## BA/EPCT Integration
+
+This command can be called automatically in:
+- Phase T (Test) of BA workflow: `/ba:5-verify`
+- Phase T of EPCT workflow
+
+## Sources
+
+- [Anthropic - Claude for Chrome](https://www.anthropic.com/news/claude-for-chrome)
+- [Claude Help Center](https://support.claude.com/en/articles/12012173-getting-started-with-claude-in-chrome)
+
+---
+
+User: $ARGUMENTS