Add new CLI mode for systematic technical document analysis with:
- CLI command: /cli:mode:document-analysis for Gemini/Qwen/Codex
- Comprehensive analysis template with 6-phase protocol
- Support for README, API docs, research papers, specifications, tutorials
- Evidence-based analysis with pre-planning and self-critique requirements
- Precise language constraints and structured output format
Template features:
- Pre-analysis planning phase for approach definition
- Multi-phase analysis: assessment, extraction, critical analysis, synthesis
- Self-critique requirement before final output
- Mandatory section references and evidence citations
- Output length control proportional to document size
Add comprehensive explanation of how CLI tool results can be saved and
reused as context for subsequent operations:
- Result persistence in workflow sessions (.chat/ directory)
- Using analysis results as planning basis
- Using analysis results as implementation basis
- Cross-session references
- Memory update loops with iterative optimization
- Visual memory flow diagram showing phase-to-phase context passing
- Best practices for maintaining continuity and quality
This enables intelligent workflows where Gemini/Qwen analysis informs
Codex implementation, and all results accumulate as project memory for
future decision-making. Integrates with /workflow:plan and
/workflow:lite-plan commands.
Add comprehensive section on multi-model CLI collaboration (Gemini/Qwen/Codex):
- Three execution modes: serial, parallel, and hybrid
- Semantic invocation vs command invocation patterns
- Integration examples with Lite and Full workflows
- Best practices for tool selection and execution strategies
Updates both Chinese and English versions with practical examples showing
how to leverage ultra-long context models (Gemini/Qwen) for analysis and
Codex for precise code implementation.
Add WORKFLOW_DECISION_GUIDE_EN.md with complete English translation of the workflow decision guide, including:
- Full lifecycle command selection flowchart
- Decision point explanations with examples
- Testing and review strategies
- Complete flows for typical scenarios
- Quick reference tables by knowledge level, project phase, and work mode
- Best practices and common pitfalls
Optimize the Phase 2 output filename in /memory:docs command for better clarity:
- Old: phase2-analysis.json (generic, non-descriptive)
- New: doc-planning-data.json (clear purpose, self-documenting)
The new name better reflects that this file contains comprehensive
documentation planning data including folder analysis, grouping
information, existing docs, and statistics.
Updated all references in command documentation and skill guides.
Major improvements to workflow understanding and guidance:
1. New Document: WORKFLOW_DECISION_GUIDE.md
- Comprehensive decision flowchart for full software lifecycle
- Interactive Mermaid diagram with 40+ decision points
- Clear guidance on when to use each command
- Real-world scenarios for all workflow types
- Quick reference tables by knowledge level, project stage, and mode
- Expert tips and common pitfalls
2. Clarified Brainstorm vs Plan Relationship
Core concept correction:
- Brainstorm: Use when you know WHAT to build, NOT HOW
- Plan: Use when you know both WHAT and HOW
- Plan can accept user input OR brainstorm output
3. Updated Documentation Files
- GETTING_STARTED.md: Added clear distinction and decision criteria
- GETTING_STARTED_CN.md: Chinese version with same clarifications
- FAQ.md: Enhanced brainstorm usage explanation with workflow comparison table
- README.md: Added Workflow Decision Guide link
- README_CN.md: Added Chinese link to decision guide
4. Key Improvements
When to Use Brainstorming:
- Unclear solution approach (multiple ways to solve)
- Architectural exploration needed
- Requirements clarification (high-level clear, details not)
- Multiple trade-offs to analyze
- Unfamiliar domain
When to Skip Brainstorming:
- Clear implementation approach
- Similar to existing code patterns
- Well-defined requirements
- Simple features
5. Decision Flowchart Covers:
- Ideation phase (know what to build?)
- Design phase (know how to build?)
- UI design phase (need UI design?)
- Planning phase (complexity level?)
- Testing phase (TDD, post-test, test-fix?)
- Review phase (security, architecture, quality?)
- Completion
Benefits:
- Eliminates confusion about brainstorm usage
- Provides clear decision criteria for all commands
- Visual flowchart helps users navigate workflows
- Comprehensive coverage of all development stages
- Reduces trial-and-error in workflow selection
Files modified: 5
Files added: 1 (WORKFLOW_DECISION_GUIDE.md)
Add four new comprehensive documentation files and update READMEs:
New Documentation:
- ARCHITECTURE.md: High-level system architecture overview
* Design philosophy and core principles
* System components and data flow
* Multi-agent system details
* CLI tool integration strategy
* Session and memory management
* Performance optimizations and best practices
- CONTRIBUTING.md: Contributor guidelines
* Code of conduct
* Development setup instructions
* Coding standards and best practices
* Testing guidelines
* Documentation requirements
* Pull request process
* Release process
- FAQ.md: Frequently asked questions
* General questions about CCW
* Installation and setup
* Usage and workflows
* Commands and syntax
* Sessions and tasks
* Agents and tools
* Memory system
* Troubleshooting
* Advanced topics
- EXAMPLES.md: Real-world use cases
* Quick start examples
* Web development (Express, React, e-commerce)
* API development (REST, GraphQL)
* Testing & quality assurance (TDD, test generation)
* Refactoring (monolith to microservices)
* UI/UX design (design systems, landing pages)
* Bug fixes (simple and complex)
* Documentation generation
* DevOps & automation (CI/CD, Docker)
* Complex projects (chat app, analytics dashboard)
Updated Documentation:
- README.md: Added comprehensive documentation section
* Organized docs into categories
* Links to all new documentation files
* Improved navigation structure
- README_CN.md: Added documentation section (Chinese)
* Same organization as English version
* Links to all documentation resources
Benefits:
- Provides clear entry points for new users
- Comprehensive reference for all features
- Real-world examples for practical learning
- Complete contributor onboarding
- Better project discoverability
Remove unnecessary Core Principles sections that reference task-core.md
and workflow-architecture.md from both workflow:replan and task:replan
documentation to align with execute.md style and maintain simplicity.
Removed 104 lines of version history and enhancement documentation (lines 420-523):
- TDD Workflow Enhancements section
- Key Improvements (adopted features from test-gen and plan workflows)
- Workflow Comparison table (Previous vs Current)
- Migration Notes and backward compatibility info
- Configuration examples
This content represented ~19% of the file and was historical/evolutionary
information rather than core command functionality. Focuses the documentation
on what the command does, not how it evolved.
Improves task focus and documentation clarity as identified in audit report.
- Simplify Phase 1-3: Use unified principles (Detect→Classify→Store) to avoid string concatenation and escaping
- Reduce Phase 1-3 from 70+ lines to 30 lines with clear priority chains
- Remove Phase 11 (preview generation): Delegated to generate.md command to eliminate duplication
- Update workflow from 11 phases to 10 phases
- Convert all content to English for internationalization
- Update TodoWrite pattern from 5 tasks to 4 tasks (remove preview generation task)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated output paths in various command files to reflect the new structure: `.workflow/sessions/{session_id}/` instead of `.workflow/{session_id}/`.
- Adjusted documentation and code comments to ensure consistency across all agents and commands.
- Ensured that all references to session-related files are correctly pointing to the new directory format.
Issue:
- In Bash version, new_install_manifest creates file immediately
- save_install_manifest calls remove_old_manifests_for_path
- This deletes ALL manifests for the path, including the new one
- Result: "WARNING: Failed to save installation manifest"
Solution:
- Add current_manifest_file parameter to remove_old_manifests_for_path
- Skip deletion if file matches current manifest
- Pass manifest_file to exclude it from deletion
Note: PowerShell version does not have this issue because it creates
the manifest file AFTER deleting old ones (hashtable → file conversion)
- Add Remove-OldManifestsForPath function to automatically clean old manifests
- Modify Save-InstallManifest to remove old manifests before saving new one
- Update Get-AllInstallManifests to return only latest manifest per installation path
- Apply same strategy to both Install-Claude.ps1 (PowerShell) and Install-Claude.sh (Bash)
Benefits:
- Each installation location registers only once
- Only latest version manifest is retained
- Uninstall UI shows only latest version per location
- Prevents manifest file accumulation
Restructure lite-plan.md (844→668 lines, -176) and lite-execute.md (597→569 lines, -28) following agent document patterns. Move Data Structures sections to end as reference, simplify repeated content, improve hierarchical organization. All original content preserved.
Key changes:
- Data Structures moved to end (from beginning)
- Simplified Execution Process to avoid duplication
- Improved section hierarchy and flow
- Consistent structure across both documents
Restructure cli-lite-planning-agent.md and cli-planning-agent.md following action-planning-agent.md's clear hierarchical pattern. Merge duplicate content, consolidate sections, and improve readability while preserving all original information.
Issue found by Gemini analysis:
- executionContext.planObject.tasks was incorrectly documented as string[]
- Actual runtime structure is array of structured task objects (7 fields)
- This caused documentation mismatch between lite-plan and lite-execute
Fix:
- Update executionContext definition to show full task object structure
- Add comment clarifying it's an array of structured objects (7 fields each)
- Aligns with actual implementation and lite-execute consumption logic
Impact: Documentation only (no code changes, runtime behavior was already correct)
Major changes:
- Add cli-lite-planning-agent.md for generating structured task objects
- Upgrade planObject.tasks from string[] to structured objects with 7 fields:
- title, file, action, description (what to do)
- implementation (3-7 steps on how to do it)
- reference (pattern, files, examples to follow)
- acceptance (verification criteria)
- Update lite-execute.md to format structured tasks for Agent/Codex execution
- Clean up agent files: remove "how to call me" sections (cli-planning-agent, cli-explore-agent)
- Update lite-plan.md to use cli-lite-planning-agent for Medium/High complexity tasks
Benefits:
- Execution agents receive complete "how to do" guidance instead of vague descriptions
- Each task includes specific file paths, implementation steps, and verification criteria
- Clear separation of concerns: agents only describe what they do, not how they are called
- Architecture validated by Gemini: 100% consistency, no responsibility leakage
Breaking changes: None (backward compatible via task.title || task fallback in lite-execute)
