Roo-Code/.roo/rules-docs-extractor/1_extraction_workflow.xml

361 lines
No EOL
13 KiB
XML

<extraction_workflow>
<mode_overview>
The Docs Extractor mode has two primary functions:
1. Extract technical and non-technical details about features to provide to documentation teams
2. Verify existing documentation for factual accuracy against the codebase
This mode does not generate final documentation but provides detailed analysis and verification.
</mode_overview>
<initialization_phase>
<step number="1">
<title>Parse Request</title>
<actions>
<action>Identify the feature or component in the user's request.</action>
<action>Determine if the request is for extraction or verification.</action>
<action>For extraction: Note what level of detail is needed (technical vs non-technical).</action>
<action>For verification: Identify the documentation to be verified.</action>
<action>Note any specific areas to emphasize or check.</action>
</actions>
<note>The mode branches into extraction or verification based on the request.</note>
</step>
<step number="2">
<title>Discover Feature</title>
<actions>
<action>Locate relevant code using appropriate search methods.</action>
<action>Identify entry points and components.</action>
<action>Map the high-level architecture.</action>
<action>Use any combination of tools to understand the feature.</action>
</actions>
<note>Use the most effective discovery method for the situation - file exploration, search, or direct navigation.</note>
</step>
</initialization_phase>
<analysis_phases>
<phase name="code_analysis">
<title>Code Analysis</title>
<steps>
<step>
<action>Analyze code structure</action>
<details>
- Identify classes, functions, modules
- Extract method signatures, parameters
- Document return types, data structures
- Map inheritance and composition
</details>
</step>
<step>
<action>Extract APIs</action>
<details>
- REST endpoints
- GraphQL schemas
- WebSocket events
- RPC interfaces
</details>
</step>
<step>
<action>Document configuration</action>
<details>
- Environment variables
- Config files and schemas
- Feature flags
- Runtime parameters
</details>
</step>
</steps>
</phase>
<phase name="ui_ux_analysis">
<title>UI/UX and User Experience Analysis</title>
<steps>
<step>
<action>Analyze user interface components</action>
<details>
- UI components and their interactions
- Forms, buttons, navigation elements
- Visual feedback and loading states
- Responsive design considerations
- Accessibility features
</details>
</step>
<step>
<action>Map user journeys and interactions</action>
<details>
- Step-by-step user workflows
- Click paths and navigation flows
- User decision points
- Input validation and error messaging
- Success and failure scenarios
</details>
</step>
<step>
<action>Document user experience elements</action>
<details>
- Page layouts and information architecture
- Interactive elements and their behaviors
- Tooltips, help text, and guidance
- Confirmation dialogs and warnings
- Progress indicators and status updates
</details>
</step>
<step>
<action>Capture visual and behavioral patterns</action>
<details>
- Color schemes and theming
- Animation and transitions
- Keyboard shortcuts and accessibility
- Mobile vs desktop experiences
- Browser-specific considerations
</details>
</step>
</steps>
</phase>
<phase name="business_logic_analysis">
<title>Business Logic Extraction</title>
<steps>
<step>
<action>Map workflows from user perspective</action>
<details>
- User journey through the feature
- Decision points and branching
- State transitions visible to users
- Roles and permissions affecting UI
</details>
</step>
<step>
<action>Document business rules</action>
<details>
- Validation logic and user feedback
- Formulas and algorithms
- Business process implementations
- Compliance requirements
</details>
</step>
<step>
<action>Identify use cases</action>
<details>
- Primary use cases
- Edge cases
- Error scenarios and user recovery
- Performance factors affecting UX
</details>
</step>
</steps>
</phase>
<phase name="integration_analysis">
<title>Dependency Analysis</title>
<steps>
<step>
<action>Map dependencies</action>
<details>
- Third-party libraries
- External services and APIs
- Database connections
- Message queues
</details>
</step>
<step>
<action>Document integration points</action>
<details>
- Incoming webhooks
- Outgoing API calls
- Event publishers/subscribers
- Shared data stores
</details>
</step>
<step>
<action>Analyze data flow</action>
<details>
- Data sources and formats
- Data transformations
- Output formats and destinations
- Data retention policies
</details>
</step>
</steps>
</phase>
<phase name="quality_analysis">
<title>Test Analysis</title>
<steps>
<step>
<action>Assess test coverage</action>
<details>
- Unit test coverage
- Integration test scenarios
- End-to-end test flows
- Performance test results
</details>
</step>
<step>
<action>Document error handling</action>
<details>
- Error types and codes
- Exception handling
- Fallback mechanisms
- Recovery procedures
</details>
</step>
<step>
<action>Identify quality metrics</action>
<details>
- Code complexity
- Performance benchmarks
- Security vulnerabilities
- Maintainability scores
</details>
</step>
</steps>
</phase>
<phase name="security_analysis">
<title>Security Analysis</title>
<steps>
<step>
<action>Document security</action>
<details>
- Auth mechanisms
- Access control
- Data encryption
- Security policies
</details>
</step>
<step>
<action>Identify vulnerabilities</action>
<details>
- Known security issues
- Attack vectors
- Mitigation
- Best practices
</details>
</step>
<step>
<action>Check compliance</action>
<details>
- Regulatory compliance (GDPR, etc.)
- Industry standards
- Audit trail requirements
- Data privacy
</details>
</step>
</steps>
</phase>
</analysis_phases>
<workflow_paths>
<path name="extraction">
<title>Extract Feature Details</title>
<description>Analyze and extract comprehensive details for documentation team</description>
<steps>
<step number="1">
<title>Compile Technical Details</title>
<actions>
<action>List all technical components and their relationships</action>
<action>Document APIs, data structures, and algorithms</action>
<action>Extract configuration options and their impacts</action>
<action>Identify error handling and edge cases</action>
<action>Note performance characteristics and limitations</action>
</actions>
</step>
<step number="2">
<title>Extract Non-Technical Information</title>
<actions>
<action>Describe complete user experience and workflows</action>
<action>Document UI interactions and visual elements</action>
<action>Explain business logic in plain language</action>
<action>Identify user benefits and use cases</action>
<action>Document common scenarios with UI context</action>
<action>Note prerequisites and user-facing dependencies</action>
<action>Capture error messages and user guidance</action>
</actions>
</step>
<step number="3">
<title>Create Extraction Report</title>
<actions>
<action>Organize findings into clear categories</action>
<action>Separate technical and non-technical information</action>
<action>Include code snippets and examples where helpful</action>
<action>Create `EXTRACTION-[feature].md` with findings</action>
<action>Highlight areas that need special attention in documentation</action>
</actions>
<output_format>
- Executive summary of the feature
- UI/UX analysis and user experience
- Technical details section
- Non-technical/user-facing details
- User workflows and interactions
- Configuration and setup information
- Common use cases with UI context
- Error handling and user guidance
- Potential documentation considerations
</output_format>
</step>
</steps>
</path>
<path name="verification">
<title>Verify Documentation Accuracy</title>
<description>Check existing documentation against codebase reality</description>
<steps>
<step number="1">
<title>Analyze Provided Documentation</title>
<actions>
<action>Parse the documentation to identify claims and descriptions</action>
<action>Extract technical specifications mentioned</action>
<action>Note user-facing features and workflows described</action>
<action>Identify configuration options and examples provided</action>
</actions>
</step>
<step number="2">
<title>Verify Against Codebase</title>
<actions>
<action>Check technical claims against actual implementation</action>
<action>Verify API endpoints, parameters, and responses</action>
<action>Confirm configuration options and defaults</action>
<action>Validate code examples and snippets</action>
<action>Check if described workflows match implementation</action>
</actions>
</step>
<step number="3">
<title>Create Verification Report</title>
<actions>
<action>Categorize findings by severity (Critical, Major, Minor)</action>
<action>List all inaccuracies with correct information</action>
<action>Identify missing important information</action>
<action>Note outdated or deprecated content</action>
<action>Provide specific corrections and suggestions</action>
<action>Create `VERIFICATION-[feature].md` with findings</action>
</actions>
<output_format>
- Verification summary (Accurate/Needs Updates)
- Critical inaccuracies that could mislead users
- Technical corrections needed
- Missing information that should be added
- Suggestions for clarity improvements
- Overall recommendations
</output_format>
</step>
</steps>
</path>
</workflow_paths>
<completion_criteria>
<for_extraction>
<criterion>All code paths analyzed</criterion>
<criterion>Technical details comprehensively extracted</criterion>
<criterion>Non-technical information clearly explained</criterion>
<criterion>Use cases and examples provided</criterion>
<criterion>Report organized for documentation team use</criterion>
</for_extraction>
<for_verification>
<criterion>All documentation claims verified</criterion>
<criterion>Inaccuracies identified and corrected</criterion>
<criterion>Missing information noted</criterion>
<criterion>Suggestions for improvement provided</criterion>
<criterion>Clear verification report created</criterion>
</for_verification>
</completion_criteria>
</extraction_workflow>