mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-14 02:42:04 +08:00

Files

catlog22 89f6ac6804 feat: Implement multi-phase project analysis workflow with Mermaid diagram generation and CPCC compliance documentation

- Phase 3: Added Mermaid diagram generation for system architecture, function modules, algorithms, class diagrams, sequence diagrams, and error flows.
- Phase 4: Assembled analysis and diagrams into a structured CPCC-compliant document with section templates and figure numbering.
- Phase 5: Developed compliance review process with iterative refinement based on analysis findings and user feedback.
- Added CPCC compliance requirements and quality standards for project analysis reports.
- Established a comprehensive project analysis skill with detailed execution flow and report types.
- Enhanced error handling and recovery mechanisms throughout the analysis phases.

2025-12-26 11:44:29 +08:00

1.6 KiB

Raw Blame History

Phase 3: Deep Analysis

Execute deep analysis using Gemini CLI with exploration context.

Execution

Step 1: Prepare CLI Prompt

ccw cli -p "
PURPOSE: Generate ${type} analysis report for project
TASK: 
  • Analyze project structure and patterns from ${type} perspective
  • Focus on: ${focus_areas}
  • Depth level: ${depth}
  • Key files: ${key_files}
MODE: analysis
CONTEXT: @**/* | Exploration results
EXPECTED: 
  - Structured analysis
  - Code references (file:line format)
  - Mermaid diagram data
  - Actionable insights
RULES: $(cat ~/.claude/workflows/cli-templates/protocols/analysis-protocol.md)
" --tool gemini --mode analysis

Step 2: Parse Analysis Results

Extract structured data from CLI response:

const deepAnalysis = {
  findings: [],           // Analyzed findings with confidence scores
  patterns: [],           // Identified patterns with consistency scores
  dependencies: [],       // Dependency relationships
  recommendations: [],    // Prioritized recommendations
  sections: [],           // Report section data
  diagram_data: {}        // Data for diagram generation
};

Step 3: Validate Analysis Quality

Check analysis completeness:

const qualityChecks = {
  has_executive_summary: Boolean,
  focus_areas_covered: config.focus_areas.every(area => analysis.covers(area)),
  code_references_valid: analysis.references.every(ref => fileExists(ref)),
  insights_actionable: analysis.insights.filter(i => i.actionable).length > 0
};

Output

Save analysis results to deep-analysis.json.

1.6 KiB Raw Blame History