@atlashub/smartstack-cli 1.13.2 → 1.14.0

package/templates/commands/ralph-loop/help.md

@@ -1,126 +0,0 @@
----
-description: "Explain Ralph Loop plugin and available commands"
----
-
-# Ralph Loop Plugin Help
-
-Please explain the following to the user:
-
-## What is Ralph Loop?
-
-Ralph Loop implements the Ralph Wiggum technique - an iterative development methodology based on continuous AI loops, pioneered by Geoffrey Huntley.
-
-**Core concept:**
-```bash
-while :; do
-  cat PROMPT.md | claude-code --continue
-done
-```
-
-The same prompt is fed to Claude repeatedly. The "self-referential" aspect comes from Claude seeing its own previous work in the files and git history, not from feeding output back as input.
-
-**Each iteration:**
-1. Claude receives the SAME prompt
-2. Works on the task, modifying files
-3. Tries to exit
-4. Stop hook intercepts and feeds the same prompt again
-5. Claude sees its previous work in the files
-6. Iteratively improves until completion
-
-The technique is described as "deterministically bad in an undeterministic world" - failures are predictable, enabling systematic improvement through prompt tuning.
-
-## Available Commands
-
-### /ralph-loop <PROMPT> [OPTIONS]
-
-Start a Ralph loop in your current session.
-
-**Usage:**
-```
-/ralph-loop "Refactor the cache layer" --max-iterations 20
-/ralph-loop "Add tests" --completion-promise "TESTS COMPLETE"
-```
-
-**Options:**
-- `--max-iterations <n>` - Max iterations before auto-stop
-- `--completion-promise <text>` - Promise phrase to signal completion
-
-**How it works:**
-1. Creates `.claude/.ralph-loop.local.md` state file
-2. You work on the task
-3. When you try to exit, stop hook intercepts
-4. Same prompt fed back
-5. You see your previous work
-6. Continues until promise detected or max iterations
-
----
-
-### /cancel-ralph
-
-Cancel an active Ralph loop (removes the loop state file).
-
-**Usage:**
-```
-/cancel-ralph
-```
-
-**How it works:**
-- Checks for active loop state file
-- Removes `.claude/.ralph-loop.local.md`
-- Reports cancellation with iteration count
-
----
-
-## Key Concepts
-
-### Completion Promises
-
-To signal completion, Claude must output a `<promise>` tag:
-
-```
-<promise>TASK COMPLETE</promise>
-```
-
-The stop hook looks for this specific tag. Without it (or `--max-iterations`), Ralph runs infinitely.
-
-### Self-Reference Mechanism
-
-The "loop" doesn't mean Claude talks to itself. It means:
-- Same prompt repeated
-- Claude's work persists in files
-- Each iteration sees previous attempts
-- Builds incrementally toward goal
-
-## Example
-
-### Interactive Bug Fix
-
-```
-/ralph-loop "Fix the token refresh logic in auth.ts. Output <promise>FIXED</promise> when all tests pass." --completion-promise "FIXED" --max-iterations 10
-```
-
-You'll see Ralph:
-- Attempt fixes
-- Run tests
-- See failures
-- Iterate on solution
-- In your current session
-
-## When to Use Ralph
-
-**Good for:**
-- Well-defined tasks with clear success criteria
-- Tasks requiring iteration and refinement
-- Iterative development with self-correction
-- Greenfield projects
-
-**Not good for:**
-- Tasks requiring human judgment or design decisions
-- One-shot operations
-- Tasks with unclear success criteria
-- Debugging production issues (use targeted debugging instead)
-
-## Learn More
-
-- Original technique: https://ghuntley.com/ralph/
-- Ralph Orchestrator: https://github.com/mikeyobrien/ralph-orchestrator

package/templates/commands/ralph-loop/ralph-loop.md

@@ -1,120 +0,0 @@
----
-description: "Start Ralph Loop in current session"
-argument-hint: "PROMPT [--max-iterations N] [--completion-promise TEXT]"
-allowed-tools: ["Bash(${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh:*)"]
-hide-from-slash-command-tool: "true"
----
-
-# Ralph Loop Command
-
-Execute the setup script to initialize the Ralph loop:
-
-```!
-"${CLAUDE_PLUGIN_ROOT}/scripts/setup-ralph-loop.sh" $ARGUMENTS
-```
-
----
-
-## RALPH WEEGUND - AUTOMATED DEVELOPMENT LOOP
-
-You are now operating in **Ralph Weegund** mode - an iterative AI development loop for SmartStack projects.
-
-### MANDATORY MCP VALIDATION
-
-**BEFORE STARTING ANY WORK**, you MUST verify MCP servers are available:
-
-1. **Check context7 MCP**: Use `mcp__plugin_context7_context7__resolve-library-id` to verify connectivity
-2. **Check smartstack MCP**: Use `mcp__smartstack__validate_conventions` with a simple check
-
-**IF ANY MCP SERVER IS UNAVAILABLE:**
-- DO NOT proceed with the task
-- Log the failure to `.ralph/logs/`
-- Output a clear error message explaining which MCP is down
-- Suggest running `smartstack check-mcp` to diagnose
-
-### STRICT MCP USAGE REQUIREMENTS
-
-Throughout your work, you MUST:
-
-1. **Use SmartStack MCP for all validations**:
-   - `mcp__smartstack__validate_conventions` - Before any commit
-   - `mcp__smartstack__check_migrations` - Before any EF Core changes
-   - `mcp__smartstack__scaffold_extension` - For code generation
-   - `mcp__smartstack__api_docs` - For API documentation
-
-2. **Use Context7 MCP for documentation**:
-   - `mcp__plugin_context7_context7__resolve-library-id` - Find library docs
-   - `mcp__plugin_context7_context7__query-docs` - Query specific documentation
-
-3. **Track all MCP calls** by logging them mentally for the final report
-
-### LOGGING PROTOCOL
-
-For each significant action, maintain an internal log:
-- MCP tool calls (which tool, parameters, success/failure)
-- Files created/modified
-- Validations performed
-- Errors encountered
-
-### ITERATION BEHAVIOR
-
-When you try to exit, the Ralph loop will feed the SAME PROMPT back to you for the next iteration. You'll see your previous work in files and git history, allowing you to iterate and improve.
-
-**CRITICAL RULE**: If a completion promise is set, you may ONLY output it when the statement is completely and unequivocally TRUE. Do not output false promises to escape the loop, even if you think you're stuck or should exit for other reasons. The loop is designed to continue until genuine completion.
-
-### COMPLETION REPORT
-
-When the task is GENUINELY COMPLETE, generate a feature report in `.ralph/reports/`:
-
-```markdown
-# Feature Report: [Feature Name]
-
-## Summary
-- **Date**: YYYY-MM-DD HH:MM
-- **Duration**: X iterations
-- **Status**: COMPLETE
-
-## MCP Usage Statistics
-| Tool | Calls | Success | Failures |
-|------|-------|---------|----------|
-| validate_conventions | X | X | 0 |
-| check_migrations | X | X | 0 |
-| scaffold_extension | X | X | 0 |
-| context7 query-docs | X | X | 0 |
-
-## Files Created
-- path/to/file1.cs
-- path/to/file2.tsx
-
-## Files Modified
-- path/to/existing1.cs
-- path/to/existing2.ts
-
-## Validations Performed
-- [ ] SmartStack conventions validated
-- [ ] EF Core migrations checked
-- [ ] No conflicts detected
-
-## Notes
-Any relevant observations about the implementation.
-```
-
-### ERROR HANDLING
-
-If you encounter an error:
-1. Log the error details
-2. Attempt recovery if possible
-3. If MCP server fails mid-task:
-   - Save current progress
-   - Log the MCP failure
-   - DO NOT continue without MCP
-   - Request manual intervention
-
-### COMMANDS AVAILABLE
-
-- `/ralph-loop:cancel-ralph` - Cancel the current loop
-- `/ralph-loop:help` - Show Ralph Loop documentation
-
----
-
-**NOW PROCEED WITH THE TASK**, ensuring you follow all MCP validation and logging requirements above.

package/templates/commands/review.md

@@ -1,106 +0,0 @@
----
-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/workflow.md

@@ -1,193 +0,0 @@
-# /workflow - Gestion Workflows SmartStack
-
-> **Synergie Skill/Commande:**
-> - **Skill** (`templates/skills/workflow/`) → Invocation automatique par Claude
-> - **Commande** (`/workflow`) → Invocation manuelle par l'utilisateur
-
----
-
-## ARGUMENTS
-
-```
-/workflow <action> [options]
-```
-
-| Action | Description |
-|--------|-------------|
-| `create` | Creer un nouveau workflow complet |
-| `trigger` | Ajouter un nouveau trigger |
-| `step` | Ajouter un step a un workflow existant |
-| `template` | Creer un email template |
-
----
-
-## WORKFLOW
-
-### /workflow create
-
-Cree un workflow complet avec trigger et steps.
-
-**Questions:**
-1. Code du workflow ? (kebab-case)
-2. Nom descriptif ?
-3. Quel trigger ? (existant ou nouveau)
-4. Quels steps ? (Email, Wait, Condition, Webhook)
-5. Systeme ? (oui/non)
-6. Priorite ? (1-100, defaut 10)
-
-**Actions:**
-1. Creer/utiliser le trigger
-2. Ajouter le workflow dans WorkflowConfiguration.cs seed
-3. Ajouter les steps dans WorkflowStepConfiguration.cs seed
-4. Creer les email templates si necessaire
-5. Creer migration EF Core
-
-### /workflow trigger
-
-Ajoute un nouveau trigger.
-
-**Questions:**
-1. Code du trigger ? (format: entity.event)
-2. Nom descriptif ?
-3. Variables disponibles ?
-
-**Actions:**
-1. Ajouter dans WorkflowTriggerConfiguration.cs seed
-2. Creer migration EF Core
-
-### /workflow step
-
-Ajoute un step a un workflow existant.
-
-**Questions:**
-1. Quel workflow ?
-2. Type de step ? (SendEmail, Wait, Condition, Webhook)
-3. Configuration specifique selon le type
-
-**Actions:**
-1. Ajouter dans WorkflowStepConfiguration.cs seed
-2. Mettre a jour l'ordre des steps
-3. Creer migration EF Core
-
-### /workflow template
-
-Cree un email template.
-
-**Questions:**
-1. Code du template ?
-2. Nom ?
-3. Categorie ? (Transactional, Marketing, System)
-4. Langues ? (fr, en, it, de)
-
-**Actions:**
-1. Ajouter dans EmailTemplateConfiguration.cs seed
-2. Ajouter les translations
-3. Creer migration EF Core
-
----
-
-## TEMPLATES
-
-### Template Trigger Seed
-
-```csharp
-new
-{
-    Id = Guid.Parse("$TRIGGER_GUID"),
-    Code = "$ENTITY.$EVENT",
-    Name = "$NAME",
-    Description = "$DESCRIPTION",
-    TriggerType = "$TRIGGER_TYPE",
-    AvailableVariablesJson = JsonSerializer.Serialize(new[]
-    {
-        new { Name = "entityId", Type = "Guid", Description = "Entity ID" },
-        new { Name = "entityName", Type = "string", Description = "Entity name" },
-        new { Name = "userEmail", Type = "string", Description = "User email" },
-    }),
-    IsActive = true,
-    CreatedAt = seedDate
-},
-```
-
-### Template Workflow Seed
-
-```csharp
-new
-{
-    Id = Guid.Parse("$WORKFLOW_GUID"),
-    Code = "$CODE",
-    Name = "$NAME",
-    Description = "$DESCRIPTION",
-    TriggerId = Guid.Parse("$TRIGGER_GUID"),
-    ApplicationId = (Guid?)null,
-    IsActive = true,
-    IsSystem = $IS_SYSTEM,
-    Priority = $PRIORITY,
-    CreatedAt = seedDate
-},
-```
-
-### Template Step Seed (Email)
-
-```csharp
-new
-{
-    Id = Guid.Parse("$STEP_GUID"),
-    WorkflowId = Guid.Parse("$WORKFLOW_GUID"),
-    Name = "$NAME",
-    StepType = WorkflowStepType.SendEmail,
-    StepOrder = $ORDER,
-    EmailTemplateId = Guid.Parse("$TEMPLATE_GUID"),
-    IsActive = true,
-    CreatedAt = seedDate
-},
-```
-
-### Template Step Seed (Wait)
-
-```csharp
-new
-{
-    Id = Guid.Parse("$STEP_GUID"),
-    WorkflowId = Guid.Parse("$WORKFLOW_GUID"),
-    Name = "$NAME",
-    StepType = WorkflowStepType.Wait,
-    StepOrder = $ORDER,
-    DelayMinutes = $DELAY_MINUTES,
-    IsActive = true,
-    CreatedAt = seedDate
-},
-```
-
-### Template Declenchement
-
-```csharp
-await _workflowService.TriggerAsync(
-    "$TRIGGER_CODE",
-    new Dictionary<string, object>
-    {
-        ["entityId"] = entity.Id,
-        ["entityName"] = entity.Name,
-        ["userEmail"] = _currentUser.Email
-    },
-    language: "fr",
-    cancellationToken: ct);
-```
-
----
-
-## FICHIERS CLES
-
-| Fichier | Role |
-|---------|------|
-| `Domain/Communications/Workflow.cs` | Entite workflow |
-| `Domain/Communications/WorkflowStep.cs` | Entite step |
-| `Domain/Communications/WorkflowTrigger.cs` | Entite trigger |
-| `Infrastructure/.../WorkflowConfiguration.cs` | Seed workflows |
-| `Infrastructure/.../WorkflowTriggerConfiguration.cs` | Seed triggers |
-| `Infrastructure/.../WorkflowStepConfiguration.cs` | Seed steps |
-| `Infrastructure/Services/Workflow/WorkflowExecutionService.cs` | Execution |
-
----
-
-User: $ARGUMENTS