@zeyue0329/xiaoma-cli 1.0.49 → 6.0.0-alpha.14

package/src/modules/xmb/workflows/workflow-compliance-check/steps/step-04-file-validation.md

@@ -0,0 +1,295 @@
+---
+name: 'step-04-file-validation'
+description: 'Validate file sizes, markdown formatting, and CSV data files'
+
+# Path Definitions
+workflow_path: '{project-root}/{xiaoma_folder}/xmb/workflows/workflow-compliance-check'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-04-file-validation.md'
+nextStepFile: '{workflow_path}/steps/step-05-intent-spectrum-validation.md'
+workflowFile: '{workflow_path}/workflow.md'
+complianceReportFile: '{output_folder}/workflow-compliance-report-{workflow_name}.md'
+targetWorkflowPath: '{target_workflow_path}'
+
+# Template References
+complianceReportTemplate: '{workflow_path}/templates/compliance-report.md'
+
+# Documentation References
+stepTemplate: '{project-root}/{xiaoma_folder}/xmb/docs/workflows/step-template.md'
+workflowTemplate: '{project-root}/{xiaoma_folder}/xmb/docs/workflows/workflow-template.md'
+csvStandards: '{project-root}/{xiaoma_folder}/xmb/docs/workflows/csv-data-file-standards.md'
+---
+
+# Step 4: File Size, Formatting, and Data Validation
+
+## STEP GOAL:
+
+Validate file sizes, markdown formatting standards, and CSV data file compliance to ensure optimal workflow performance and maintainability.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+
+### Role Reinforcement:
+
+- ✅ You are a compliance validator and quality assurance specialist
+- ✅ If you already have been given a name, communication_style, and persona, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring file optimization and formatting validation expertise
+- ✅ User brings their workflow files and needs performance optimization
+
+### Step-Specific Rules:
+
+- 🎯 Focus on file sizes, markdown formatting, and CSV validation
+- 🚫 FORBIDDEN to skip file size analysis or CSV validation when present
+- 💬 Approach: Systematic file analysis with optimization recommendations
+- 📋 Ensure all findings include specific recommendations for improvement
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Validate file sizes against optimal ranges (≤5K best, 5-7K good, 7-10K acceptable, 10-12K concern, >15K action required)
+- 💾 Check markdown formatting standards and conventions
+- 📖 Validate CSV files against csv-data-file-standards.md when present
+- 🚫 FORBIDDEN to overlook file optimization opportunities
+
+## CONTEXT BOUNDARIES:
+
+- Available context: Target workflow files and their sizes/formats
+- Focus: File optimization, formatting standards, and CSV data validation
+- Limits: File analysis only, holistic workflow analysis comes next
+- Dependencies: Completed step-by-step validation from previous phase
+
+## Sequence of Instructions (Do not deviate, skip, or optimize)
+
+### 1. Initialize File Validation Phase
+
+"Beginning **File Size, Formatting, and Data Validation**
+Target: `{target_workflow_name}`
+
+Analyzing workflow files for:
+
+- File size optimization (smaller is better for performance)
+- Markdown formatting standards compliance
+- CSV data file standards validation (if present)
+- Overall file maintainability and performance..."
+
+### 2. File Size Analysis
+
+**A. Step File Size Validation:**
+For each step file:
+
+"**File Size Analysis:** `{step_filename}`"
+
+- **Size:** [file size in KB]
+- **Optimization Rating:** [Optimal/Good/Acceptable/Concern/Action Required]
+- **Performance Impact:** [Minimal/Moderate/Significant/Severe]
+
+**Size Ratings:**
+
+- **≤ 5K:** ✅ Optimal - Excellent performance and maintainability
+- **5K-7K:** ✅ Good - Good balance of content and performance
+- **7K-10K:** ⚠️ Acceptable - Consider content optimization
+- **10K-12K:** ⚠️ Concern - Content should be consolidated or split
+- **> 15K:** ❌ Action Required - File must be optimized (split content, remove redundancy)
+
+**Document optimization opportunities:**
+
+- Content that could be moved to templates
+- Redundant explanations or examples
+- Overly detailed instructions that could be condensed
+- Opportunities to use references instead of inline content
+
+### 3. Markdown Formatting Validation
+
+**A. Heading Structure Analysis:**
+"**Markdown Formatting Analysis:**"
+
+For each file:
+
+- **Heading Hierarchy:** Proper H1 → H2 → H3 structure
+- **Consistent Formatting:** Consistent use of bold, italics, lists
+- **Code Blocks:** Proper markdown code block formatting
+- **Link References:** Valid internal and external links
+- **Table Formatting:** Proper table structure when used
+
+**Common formatting issues to document:**
+
+- Missing blank lines around headings
+- Inconsistent list formatting (numbered vs bullet)
+- Improper code block language specifications
+- Broken or invalid markdown links
+- Inconsistent heading levels or skipping levels
+
+### 4. CSV Data File Validation (if present)
+
+**A. Identify CSV Files:**
+"**CSV Data File Analysis:**"
+Check for CSV files in workflow directory:
+
+- Look for `.csv` files in main directory
+- Check for `data/` subdirectory containing CSV files
+- Identify any CSV references in workflow configuration
+
+**B. Validate Against Standards:**
+For each CSV file found, validate against `{csvStandards}`:
+
+**Purpose Validation:**
+
+- Does CSV contain essential data that LLMs cannot generate or web-search?
+- Is all CSV data referenced and used in the workflow?
+- Is data domain-specific and valuable?
+- Does CSV optimize context usage (knowledge base indexing, workflow routing, method selection)?
+- Does CSV reduce workflow complexity or step count significantly?
+- Does CSV enable dynamic technique selection or smart resource routing?
+
+**Structural Validation:**
+
+- Valid CSV format with proper quoting
+- Consistent column counts across all rows
+- No missing data or properly marked empty values
+- Clear, descriptive header row
+- Proper UTF-8 encoding
+
+**Content Validation:**
+
+- No LLM-generated content (generic phrases, common knowledge)
+- Specific, concrete data entries
+- Consistent data formatting
+- Verifiable and factual data
+
+**Column Standards:**
+
+- Clear, descriptive column headers
+- Consistent data types per column
+- All columns referenced in workflow
+- Appropriate column width and focus
+
+**File Size and Performance:**
+
+- Efficient structure under 1MB when possible
+- No redundant or duplicate rows
+- Optimized data representation
+- Fast loading characteristics
+
+**Documentation Standards:**
+
+- Purpose and usage documentation present
+- Column descriptions and format specifications
+- Data source documentation
+- Update procedures documented
+
+### 5. File Validation Reporting
+
+For each file with issues:
+
+```markdown
+### File Validation: {filename}
+
+**File Size Analysis:**
+
+- Size: {size}KB - Rating: {Optimal/Good/Concern/etc.}
+- Performance Impact: {assessment}
+- Optimization Recommendations: {specific suggestions}
+
+**Markdown Formatting:**
+
+- Heading Structure: {compliant/issues found}
+- Common Issues: {list of formatting problems}
+- Fix Recommendations: {specific corrections}
+
+**CSV Data Validation:**
+
+- Purpose Validation: {compliant/needs review}
+- Structural Issues: {list of problems}
+- Content Standards: {compliant/violations}
+- Recommendations: {improvement suggestions}
+```
+
+### 6. Aggregate File Analysis Summary
+
+"**File Validation Summary:**
+
+**File Size Distribution:**
+
+- Optimal (≤5K): [number] files
+- Good (5K-7K): [number] files
+- Acceptable (7K-10K): [number] files
+- Concern (10K-12K): [number] files
+- Action Required (>15K): [number] files
+
+**Markdown Formatting Issues:**
+
+- Heading Structure: [number] files with issues
+- List Formatting: [number] files with inconsistencies
+- Code Blocks: [number] files with formatting problems
+- Link References: [number] broken or invalid links
+
+**CSV Data Files:**
+
+- Total CSV files: [number]
+- Compliant with standards: [number]
+- Require attention: [number]
+- Critical issues: [number]
+
+**Performance Impact Assessment:**
+
+- Overall workflow performance: [Excellent/Good/Acceptable/Concern/Poor]
+- Most critical file size issue: {file and size}
+- Primary formatting concerns: {main issues}"
+
+### 7. Continuation Confirmation
+
+"**File Validation Complete:** Size, formatting, and CSV analysis finished
+
+**Key Findings:**
+
+- **File Optimization:** [summary of size optimization opportunities]
+- **Formatting Standards:** [summary of markdown compliance issues]
+- **Data Validation:** [summary of CSV standards compliance]
+
+**Ready for Phase 5:** Holistic workflow analysis
+
+- Flow validation and goal alignment
+- Meta-workflow failure analysis
+- Strategic recommendations and improvement planning
+
+**Select an Option:** [C] Continue to Intent Spectrum Validation [X] Exit"
+
+## Menu Handling Logic:
+
+- IF C: Save file validation findings to report, update frontmatter, then load, read entire file, then execute {nextStepFile}
+- IF X: Save current findings and end with guidance for resuming
+- IF Any other comments or queries: respond and redisplay menu
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [all file sizes analyzed, markdown formatting validated, and CSV files checked against standards], will you then load and read fully `{nextStepFile}` to execute and begin Intent Spectrum Validation phase.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- All workflow files analyzed for optimal size ranges with specific recommendations
+- Markdown formatting validated against standards with identified issues
+- CSV data files validated against csv-data-file-standards.md when present
+- Performance impact assessed with optimization opportunities identified
+- File validation findings documented with specific fix recommendations
+- User ready for holistic workflow analysis
+
+### ❌ SYSTEM FAILURE:
+
+- Skipping file size analysis or markdown formatting validation
+- Not checking CSV files against standards when present
+- Failing to provide specific optimization recommendations
+- Missing performance impact assessment
+- Overlooking critical file size violations (>15K)
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/src/modules/xmb/workflows/workflow-compliance-check/steps/step-05-intent-spectrum-validation.md

@@ -0,0 +1,264 @@
+---
+name: 'step-05-intent-spectrum-validation'
+description: 'Dedicated analysis and validation of intent vs prescriptive spectrum positioning'
+
+# Path Definitions
+workflow_path: '{project-root}/{xiaoma_folder}/xmb/workflows/workflow-compliance-check'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-05-intent-spectrum-validation.md'
+nextStepFile: '{workflow_path}/steps/step-06-web-subprocess-validation.md'
+workflowFile: '{workflow_path}/workflow.md'
+complianceReportFile: '{output_folder}/workflow-compliance-report-{workflow_name}.md'
+targetWorkflowPath: '{target_workflow_path}'
+
+# Template References
+complianceReportTemplate: '{workflow_path}/templates/compliance-report.md'
+
+# Documentation References
+stepTemplate: '{project-root}/{xiaoma_folder}/xmb/docs/workflows/step-template.md'
+workflowTemplate: '{project-root}/{xiaoma_folder}/xmb/docs/workflows/workflow-template.md'
+intentSpectrum: '{project-root}/{xiaoma_folder}/xmb/docs/workflows/intent-vs-prescriptive-spectrum.md'
+---
+
+# Step 5: Intent vs Prescriptive Spectrum Validation
+
+## STEP GOAL:
+
+Analyze the workflow's position on the intent vs prescriptive spectrum, provide expert assessment, and confirm with user whether the current positioning is appropriate or needs adjustment.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+
+### Role Reinforcement:
+
+- ✅ You are a compliance validator and design philosophy specialist
+- ✅ If you already have been given a name, communication_style, and persona, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring expertise in intent vs prescriptive design principles
+- ✅ User brings their workflow and needs guidance on spectrum positioning
+
+### Step-Specific Rules:
+
+- 🎯 Focus only on spectrum analysis and user confirmation
+- 🚫 FORBIDDEN to make spectrum decisions without user input
+- 💬 Approach: Educational, analytical, and collaborative
+- 📋 Ensure user understands spectrum implications before confirming
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Analyze workflow's current spectrum position based on all previous findings
+- 💾 Provide expert assessment with specific examples and reasoning
+- 📖 Educate user on spectrum implications for their workflow type
+- 🚫 FORBIDDEN to proceed without user confirmation of spectrum position
+
+## CONTEXT BOUNDARIES:
+
+- Available context: Complete analysis from workflow, step, and file validation phases
+- Focus: Intent vs prescriptive spectrum analysis and user confirmation
+- Limits: Spectrum analysis only, holistic workflow analysis comes next
+- Dependencies: Successful completion of file size and formatting validation
+
+## Sequence of Instructions (Do not deviate, skip, or optimize)
+
+### 1. Initialize Spectrum Analysis
+
+"Beginning **Intent vs Prescriptive Spectrum Validation**
+Target: `{target_workflow_name}`
+
+**Reference Standard:** Analysis based on `{intentSpectrum}`
+
+This step will help ensure your workflow's approach to LLM guidance is intentional and appropriate for its purpose..."
+
+### 2. Spectrum Position Analysis
+
+**A. Current Position Assessment:**
+Based on analysis of workflow.md, all step files, and implementation patterns:
+
+"**Current Spectrum Analysis:**
+Based on my review of your workflow, I assess its current position as:
+
+**[Highly Intent-Based / Balanced Middle / Highly Prescriptive]**"
+
+**B. Evidence-Based Reasoning:**
+Provide specific evidence from the workflow analysis:
+
+"**Assessment Evidence:**
+
+- **Instruction Style:** [Examples of intent-based vs prescriptive instructions found]
+- **User Interaction:** [How user conversations are structured]
+- **LLM Freedom:** [Level of creative adaptation allowed]
+- **Consistency Needs:** [Workflow requirements for consistency vs creativity]
+- **Risk Factors:** [Any compliance, safety, or regulatory considerations]"
+
+**C. Workflow Type Analysis:**
+"**Workflow Type Analysis:**
+
+- **Primary Purpose:** {workflow's main goal}
+- **User Expectations:** {What users likely expect from this workflow}
+- **Success Factors:** {What makes this workflow successful}
+- **Risk Level:** {Compliance, safety, or risk considerations}"
+
+### 3. Recommended Spectrum Position
+
+**A. Expert Recommendation:**
+"**My Professional Recommendation:**
+Based on the workflow's purpose, user needs, and implementation, I recommend positioning this workflow as:
+
+**[Highly Intent-Based / Balanced Middle / Highly Prescriptive]**"
+
+**B. Recommendation Rationale:**
+"**Reasoning for Recommendation:**
+
+- **Purpose Alignment:** {Why this position best serves the workflow's goals}
+- **User Experience:** {How this positioning enhances user interaction}
+- **Risk Management:** {How this position addresses any compliance or safety needs}
+- **Success Optimization:** {Why this approach will lead to better outcomes}"
+
+**C. Specific Examples:**
+Provide concrete examples of how the recommended position would look:
+
+"**Examples at Recommended Position:**
+**Intent-Based Example:** "Help users discover their creative potential through..."
+**Prescriptive Example:** "Ask exactly: 'Have you experienced any of the following...'"
+
+**Current State Comparison:**
+**Current Instructions Found:** [Examples from actual workflow]
+**Recommended Instructions:** [How they could be improved]"
+
+### 4. Spectrum Education and Implications
+
+**A. Explain Spectrum Implications:**
+"**Understanding Your Spectrum Choice:**
+
+**If Intent-Based:** Your workflow will be more creative, adaptive, and personalized. Users will have unique experiences, but interactions will be less predictable.
+
+**If Prescriptive:** Your workflow will be consistent, controlled, and predictable. Every user will have similar experiences, which is ideal for compliance or standardization.
+
+**If Balanced:** Your workflow will provide professional expertise with some adaptation, offering consistent quality with personalized application."
+
+**B. Context-Specific Guidance:**
+"**For Your Specific Workflow Type:**
+{Provide tailored guidance based on whether it's creative, professional, compliance, technical, etc.}"
+
+### 5. User Confirmation and Decision
+
+**A. Present Findings and Recommendation:**
+"**Spectrum Analysis Summary:**
+
+**Current Assessment:** [Current position with confidence level]
+**Expert Recommendation:** [Recommended position with reasoning]
+**Key Considerations:** [Main factors to consider]
+
+**My Analysis Indicates:** [Brief summary of why I recommend this position]
+
+**The Decision is Yours:** While I provide expert guidance, the final spectrum position should reflect your vision for the workflow."
+
+**B. User Choice Confirmation:**
+"**Where would you like to position this workflow on the Intent vs Prescriptive Spectrum?**
+
+**Options:**
+
+1. **Keep Current Position** - [Current position] - Stay with current approach
+2. **Move to Recommended** - [Recommended position] - Adopt my expert recommendation
+3. **Move Toward Intent-Based** - Increase creative freedom and adaptation
+4. **Move Toward Prescriptive** - Increase consistency and control
+5. **Custom Position** - Specify your preferred approach
+
+**Please select your preferred spectrum position (1-5):**"
+
+### 6. Document Spectrum Decision
+
+**A. Record User Decision:**
+"**Spectrum Position Decision:**
+**User Choice:** [Selected option]
+**Final Position:** [Confirmed spectrum position]
+**Rationale:** [User's reasoning, if provided]
+**Implementation Notes:** [What this means for workflow design]"
+
+**B. Update Compliance Report:**
+Append to {complianceReportFile}:
+
+```markdown
+## Intent vs Prescriptive Spectrum Analysis
+
+### Current Position Assessment
+
+**Analyzed Position:** [Current spectrum position]
+**Evidence:** [Specific examples from workflow analysis]
+**Confidence Level:** [High/Medium/Low based on clarity of patterns]
+
+### Expert Recommendation
+
+**Recommended Position:** [Professional recommendation]
+**Reasoning:** [Detailed rationale for recommendation]
+**Workflow Type Considerations:** [Specific to this workflow's purpose]
+
+### User Decision
+
+**Selected Position:** [User's confirmed choice]
+**Rationale:** [User's reasoning or preferences]
+**Implementation Guidance:** [What this means for workflow]
+
+### Spectrum Validation Results
+
+✅ Spectrum position is intentional and understood
+✅ User educated on implications of their choice
+✅ Implementation guidance provided for final position
+✅ Decision documented for future reference
+```
+
+### 7. Continuation Confirmation
+
+"**Spectrum Validation Complete:**
+
+- **Final Position:** [Confirmed spectrum position]
+- **User Understanding:** Confirmed implications and benefits
+- **Implementation Ready:** Guidance provided for maintaining position
+
+**Ready for Phase 6:** Holistic workflow analysis
+
+- Flow validation and completion paths
+- Goal alignment and optimization assessment
+- Meta-workflow failure analysis and improvement recommendations
+
+**Select an Option:** [C] Continue to Web Subprocess Validation [X] Exit"
+
+## Menu Handling Logic:
+
+- IF C: Save spectrum decision to report, update frontmatter, then load, read entire file, then execute {nextStepFile}
+- IF X: Save current spectrum findings and end with guidance for resuming
+- IF Any other comments or queries: respond and redisplay menu
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [spectrum position confirmed with user understanding], will you then load and read fully `{nextStepFile}` to execute and begin Web Subprocess Validation phase.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Comprehensive spectrum position analysis with evidence-based reasoning
+- Expert recommendation provided with specific rationale and examples
+- User educated on spectrum implications for their workflow type
+- User makes informed decision about spectrum positioning
+- Spectrum decision documented with implementation guidance
+- User understands benefits and trade-offs of their choice
+
+### ❌ SYSTEM FAILURE:
+
+- Making spectrum recommendations without analyzing actual workflow content
+- Not providing evidence-based reasoning for assessment
+- Failing to educate user on spectrum implications
+- Proceeding without user confirmation of spectrum position
+- Not documenting user decision for future reference
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.