nemonix-cli 1.0.0

package/src/config/claude-code-config/skills/meta-skill-workflow-creator/SKILL.md

@@ -0,0 +1,390 @@
+---
+name: skill-workflow-creator
+description: Create multi-step workflow skills with progressive step loading, state management, and interactive decisions. Use when building complex skills like APEX that need structured phases.
+argument-hint: <workflow name> [description]
+---
+
+<objective>
+Guide the creation of professional multi-step workflow skills. These skills use progressive step loading to minimize context, maintain state across steps, and provide interactive decision points.
+</objective>
+
+<when_to_use>
+**Use this skill when building:**
+
+- Multi-phase workflows (3+ distinct steps)
+- Skills that need state persistence across steps
+- Interactive workflows with user decision points
+- Skills with optional/conditional steps
+- Workflows that save outputs for review
+
+**Don't use for:**
+
+- Simple single-action skills
+- Skills that complete in one step
+- Pure research/exploration skills
+  </when_to_use>
+
+<workflow_creation_process>
+
+## Phase 1: Design the Workflow
+
+<step_1_define_structure>
+**1.1 Identify Workflow Steps**
+
+Ask yourself:
+
+- What are the distinct phases of this workflow?
+- What must complete before the next step can start?
+- Which steps are optional or conditional?
+- Where do users need to make decisions?
+
+**1.2 Map Dependencies**
+
+```
+Step 1 ──► Step 2 ──► Step 3 ──┬──► Step 4a (if condition)
+                               └──► Step 4b (else)
+```
+
+**1.3 Define State Variables**
+
+What data needs to persist across steps?
+
+```yaml
+state_variables:
+  - task_description: string # What to do
+  - task_id: string # Unique identifier
+  - auto_mode: boolean # Skip confirmations
+  - results: object # Accumulated results
+```
+
+</step_1_define_structure>
+
+<step_2_create_structure>
+**2.1 Create Folder Structure**
+
+```
+skills/{skill-name}/
+├── SKILL.md                    # Main entry point
+├── steps/
+│   ├── step-00-init.md         # Initialization (parse flags, setup)
+│   ├── step-01-{name}.md       # First step
+│   ├── step-02-{name}.md       # Second step
+│   └── ...
+└── references/                 # Optional: templates, patterns
+    └── ...
+```
+
+**2.2 Naming Conventions**
+
+- Steps: `step-NN-{descriptive-name}.md`
+- NN = two-digit number (00, 01, 02...)
+- Use kebab-case for names
+- Keep names short but descriptive
+  </step_2_create_structure>
+
+</workflow_creation_process>
+
+<templates>
+**Load templates from references:**
+
+- [Step Template](references/step-template.md) - Base structure for any step
+- [Ask Patterns](references/ask-patterns.md) - AskUserQuestion patterns
+- [State Management](references/state-management.md) - Persisting data across steps
+- [Workflow Patterns](references/workflow-patterns.md) - Common workflow designs
+- [Prompt Engineering](references/prompt-engineering.md) - Best practices for prompts
+  </templates>
+
+<execution_flow>
+
+## Phase 2: Build the Skill
+
+**Step 1: Create SKILL.md**
+
+Use this structure:
+
+```markdown
+---
+name: { skill-name }
+description: { what it does }
+argument-hint: { flags and args }
+---
+
+<objective>
+{Clear goal statement}
+</objective>
+
+<parameters>
+{Flags and arguments}
+</parameters>
+
+<state_variables>
+{Data that persists across steps}
+</state_variables>
+
+<entry_point>
+Load `steps/step-00-init.md`
+</entry_point>
+
+<step_files>
+{Table of all steps}
+</step_files>
+```
+
+**Step 2: Create step-00-init.md**
+
+Always start with an init step that:
+
+- Parses flags and arguments
+- Sets up state variables
+- Creates output folders (if needed)
+- Loads the first "real" step
+
+**Step 3: Create Each Step File**
+
+Use the step template from [references/step-template.md](references/step-template.md)
+
+**Step 4: Test the Workflow**
+
+Run through the workflow to ensure:
+
+- State persists correctly
+- Transitions work
+- Conditional steps trigger properly
+- Error handling works
+
+</execution_flow>
+
+<critical_patterns>
+
+## Critical Patterns to Follow (BMAD-Inspired)
+
+### 1. Micro-File Architecture
+
+```
+ALWAYS: Each step is a self-contained file with embedded rules
+ALWAYS: Load one step at a time (progressive loading)
+NEVER: Load all steps upfront
+NEVER: Assume knowledge from future steps
+
+Why: Saves context, disciplined execution, clear boundaries
+```
+
+### 2. Mandatory Execution Rules Section
+
+Every step MUST start with this:
+
+```markdown
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+- 🛑 NEVER {critical forbidden action}
+- ✅ ALWAYS {critical required action}
+- 📋 YOU ARE A {role}, not a {anti-role}
+- 💬 FOCUS on {this step's scope} only
+- 🚫 FORBIDDEN to {boundary violation}
+```
+
+### 3. Execution Protocols Section
+
+```markdown
+## EXECUTION PROTOCOLS:
+
+- 🎯 Show your analysis before taking any action
+- 💾 Update document/frontmatter after each phase
+- 📖 Complete this step fully before loading next
+- 🚫 FORBIDDEN to load next step until {criteria}
+```
+
+### 4. Context Boundaries Section
+
+```markdown
+## CONTEXT BOUNDARIES:
+
+- Variables from previous steps are available in memory
+- Previous context = what's in output document + frontmatter
+- Don't assume knowledge from future steps
+- {Resource} loaded on-demand when needed
+```
+
+### 5. Your Task Statement
+
+One clear sentence describing the step's purpose:
+
+```markdown
+## YOUR TASK:
+
+Initialize the workflow by parsing flags and setting up state.
+```
+
+### 6. User Decisions with AskUserQuestion
+
+**CRITICAL: NEVER use plain text "[C] Continue" prompts. ALWAYS use AskUserQuestion.**
+
+````markdown
+**If `{auto_mode}` = true:**
+→ Use recommended option automatically
+
+**If `{auto_mode}` = false:**
+Use AskUserQuestion:
+
+```yaml
+questions:
+  - header: "Continue"
+    question: "Ready to proceed to the next step?"
+    options:
+      - label: "Continue (Recommended)"
+        description: "Proceed to next phase"
+      - label: "Review first"
+        description: "I want to review before continuing"
+      - label: "Go back"
+        description: "Return to previous step"
+    multiSelect: false
+```
+````
+
+````
+
+### 7. Success Metrics & Failure Modes
+```markdown
+## SUCCESS METRICS:
+
+✅ {Criterion 1}
+✅ {Criterion 2}
+✅ Frontmatter properly updated
+
+## FAILURE MODES:
+
+❌ {Failure 1}
+❌ {Failure 2}
+❌ **CRITICAL**: Not using AskUserQuestion for user input
+````
+
+### 8. Frontmatter State Tracking
+
+Track progress in document frontmatter:
+
+```yaml
+---
+stepsCompleted: [1, 2, 3]
+task_description: "Add auth middleware"
+selected_approach: "jwt"
+---
+```
+
+### 9. Critical Tags
+
+Use `<critical>` tags for essential reminders:
+
+```markdown
+<critical>
+Remember: This step is ONLY about analysis - don't plan or implement!
+</critical>
+```
+
+### 10. Next Step Routing
+
+```markdown
+## NEXT STEP:
+
+After user confirms via AskUserQuestion, load `./step-02-plan.md`
+
+<critical>
+Remember: {Important boundary reminder}
+</critical>
+```
+
+</critical_patterns>
+
+<common_mistakes>
+
+## Common Mistakes to Avoid
+
+❌ **Loading all steps at once**
+→ Use micro-file architecture, one step at a time
+
+❌ **Plain text prompts like "[C] Continue"**
+→ ALWAYS use AskUserQuestion tool for ANY user input
+
+❌ **Missing MANDATORY EXECUTION RULES section**
+→ Every step MUST start with rules using 🛑✅📋💬🚫 emojis
+
+❌ **No CONTEXT BOUNDARIES section**
+→ Always define what's in scope and what's not
+
+❌ **Vague YOUR TASK statement**
+→ Must be ONE clear sentence describing step's purpose
+
+❌ **Forgetting state handoff**
+→ Each step must document available variables from previous steps
+
+❌ **Missing SUCCESS METRICS / FAILURE MODES**
+→ Every step needs ✅ success criteria and ❌ failure modes
+
+❌ **Not handling auto_mode**
+→ Check auto_mode before ANY AskUserQuestion call
+
+❌ **No frontmatter state tracking**
+→ Track `stepsCompleted` array in document frontmatter
+
+❌ **Missing `<critical>` reminders**
+→ End each step with critical boundary reminder
+
+❌ **Hardcoding paths**
+→ Use relative paths and state variables
+
+</common_mistakes>
+
+<success_criteria>
+**A well-designed workflow skill (BMAD-style):**
+
+**Structure:**
+
+- [ ] Micro-file architecture - each step self-contained
+- [ ] Clear step progression with dependencies
+- [ ] State variables documented and persisted in frontmatter
+
+**Each Step Has:**
+
+- [ ] MANDATORY EXECUTION RULES section with emojis
+- [ ] EXECUTION PROTOCOLS section
+- [ ] CONTEXT BOUNDARIES section
+- [ ] YOUR TASK - one clear sentence
+- [ ] Numbered EXECUTION SEQUENCE
+- [ ] SUCCESS METRICS with ✅ checkmarks
+- [ ] FAILURE MODES with ❌ marks
+- [ ] NEXT STEP routing section
+- [ ] `<critical>` reminder at the end
+
+**User Interaction:**
+
+- [ ] ALL user decisions use AskUserQuestion (never plain text)
+- [ ] Auto mode skips AskUserQuestion calls
+- [ ] Save mode outputs to files with frontmatter
+
+**State Management:**
+
+- [ ] `stepsCompleted` array tracked in frontmatter
+- [ ] Resume detection checks existing documents
+- [ ] State variables passed between steps
+      </success_criteria>
+
+<quick_start>
+
+## Quick Start
+
+**To create a new workflow skill:**
+
+1. Define your steps and their dependencies
+2. Create the folder structure
+3. Copy and customize SKILL.md template
+4. Create step-00-init.md for initialization
+5. Create each step using the step template
+6. Test the workflow end-to-end
+
+**Reference files to consult:**
+
+- `references/step-template.md` - Step file structure
+- `references/ask-patterns.md` - User interaction patterns
+- `references/state-management.md` - State persistence
+- `references/workflow-patterns.md` - Common workflows
+- `references/prompt-engineering.md` - Prompt best practices
+  </quick_start>

package/src/config/claude-code-config/skills/meta-skill-workflow-creator/references/ask-patterns.md

@@ -0,0 +1,225 @@
+# Ask Patterns
+
+Patterns for using AskUserQuestion tool effectively in workflow steps.
+
+---
+
+## Critical Rule
+
+**NEVER use plain text prompts like:**
+```
+Choose an option:
+1. Option A
+2. Option B
+
+Enter 1 or 2: _
+```
+
+**ALWAYS use AskUserQuestion tool.**
+
+---
+
+## Basic Pattern
+
+```yaml
+questions:
+  - header: "Header"           # Max 12 chars, shown as chip/tag
+    question: "Full question?" # End with question mark
+    options:
+      - label: "Option A (Recommended)"  # Add "(Recommended)" to preferred
+        description: "What this option does"
+      - label: "Option B"
+        description: "What this option does"
+    multiSelect: false         # true for checkboxes, false for radio
+```
+
+---
+
+## Common Patterns
+
+### 1. Proceed/Cancel Pattern
+
+```yaml
+questions:
+  - header: "Proceed"
+    question: "Ready to continue with the next step?"
+    options:
+      - label: "Continue (Recommended)"
+        description: "Proceed to the next phase"
+      - label: "Review first"
+        description: "I want to review before continuing"
+      - label: "Cancel"
+        description: "Stop the workflow"
+    multiSelect: false
+```
+
+### 2. Approach Selection Pattern
+
+```yaml
+questions:
+  - header: "Approach"
+    question: "Which approach should we use?"
+    options:
+      - label: "Approach A (Recommended)"
+        description: "Description of approach A and tradeoffs"
+      - label: "Approach B"
+        description: "Description of approach B and tradeoffs"
+      - label: "Approach C"
+        description: "Description of approach C and tradeoffs"
+    multiSelect: false
+```
+
+### 3. Scope Selection Pattern
+
+```yaml
+questions:
+  - header: "Scope"
+    question: "How comprehensive should this be?"
+    options:
+      - label: "Minimal"
+        description: "Only essential changes, fast"
+      - label: "Balanced (Recommended)"
+        description: "Standard approach, good coverage"
+      - label: "Comprehensive"
+        description: "Thorough coverage, takes longer"
+    multiSelect: false
+```
+
+### 4. Yes/No Confirmation Pattern
+
+```yaml
+questions:
+  - header: "Confirm"
+    question: "Are you sure you want to proceed?"
+    options:
+      - label: "Yes, proceed"
+        description: "Continue with the action"
+      - label: "No, go back"
+        description: "Return to previous step"
+    multiSelect: false
+```
+
+### 5. Multi-Select Features Pattern
+
+```yaml
+questions:
+  - header: "Features"
+    question: "Which features do you want to include?"
+    options:
+      - label: "Feature A"
+        description: "Description of feature A"
+      - label: "Feature B"
+        description: "Description of feature B"
+      - label: "Feature C"
+        description: "Description of feature C"
+      - label: "Feature D"
+        description: "Description of feature D"
+    multiSelect: true  # User can select multiple
+```
+
+### 6. Error Recovery Pattern
+
+```yaml
+questions:
+  - header: "Error"
+    question: "An error occurred. How should we handle it?"
+    options:
+      - label: "Retry"
+        description: "Try the operation again"
+      - label: "Skip this step"
+        description: "Continue without completing this step"
+      - label: "Debug manually"
+        description: "I'll investigate the issue"
+      - label: "Abort workflow"
+        description: "Stop the entire workflow"
+    multiSelect: false
+```
+
+### 7. Resolution Options Pattern
+
+```yaml
+questions:
+  - header: "Resolution"
+    question: "How would you like to handle these findings?"
+    options:
+      - label: "Auto-fix all (Recommended)"
+        description: "Automatically fix all identified issues"
+      - label: "Walk through each"
+        description: "Review and decide on each finding individually"
+      - label: "Fix critical only"
+        description: "Only fix high-severity issues"
+      - label: "Skip all"
+        description: "Acknowledge but don't make changes"
+    multiSelect: false
+```
+
+### 8. Next Step Pattern
+
+```yaml
+questions:
+  - header: "Next"
+    question: "What would you like to do next?"
+    options:
+      - label: "Continue to step X"
+        description: "Proceed with the next phase"
+      - label: "Run optional step Y"
+        description: "Include optional step before continuing"
+      - label: "Complete workflow"
+        description: "Finish here, skip remaining steps"
+    multiSelect: false
+```
+
+---
+
+## Auto Mode Handling
+
+Always check auto_mode before asking:
+
+```markdown
+**If `{auto_mode}` = true:**
+→ Use first/recommended option automatically
+
+**If `{auto_mode}` = false:**
+Use AskUserQuestion:
+```yaml
+questions:
+  - header: "Choice"
+    question: "..."
+    options:
+      - label: "Option A (Recommended)"  # This is used in auto mode
+        description: "..."
+```
+
+---
+
+## Response Handling Pattern
+
+After receiving user response:
+
+```markdown
+**Handle responses:**
+
+**If "Option A":**
+1. Do action A
+2. Proceed to step X
+
+**If "Option B":**
+1. Do action B
+2. Return to previous state
+
+**If "Other" (user typed custom):**
+1. Parse user input
+2. Handle accordingly
+```
+
+---
+
+## Guidelines
+
+1. **Header**: Max 12 characters, appears as chip/tag
+2. **Question**: Clear, specific, ends with "?"
+3. **Options**: 2-4 options maximum
+4. **Recommended**: Mark preferred option with "(Recommended)"
+5. **Descriptions**: Brief but informative
+6. **MultiSelect**: Only true when options aren't mutually exclusive
+7. **Other**: Users can always select "Other" for custom input