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)
- Deleted the `list` command for design runs.
- Removed the `update` command and its associated documentation.
- Introduced `design-sync` command to synchronize finalized design system references to brainstorming artifacts.
- Updated command references in `COMMAND_REFERENCE.md`, `GETTING_STARTED.md`, and `GETTING_STARTED_CN.md` to reflect the new command structure.
- Ensured all related documentation and output styles are consistent with the new command naming and functionality.
Added two new scenarios for quality assurance workflows:
1. Scenario 4: Quality Assurance - Concept Clarification
- /workflow:concept-clarify command documentation
- Use before task generation to verify conceptual clarity
- Asks up to 5 targeted questions to resolve ambiguities
- Reduces planning errors and downstream rework
2. Scenario 5: Quality Assurance - Action Plan Verification
- /workflow:action-plan-verify command documentation
- Use after /workflow:plan to validate task quality
- Checks requirements coverage, dependencies, and consistency
- Generates detailed verification report with remediation plan
Benefits:
- Catches planning errors early
- Ensures requirements completeness
- Validates architectural consistency
- Integrates with TodoWrite for remediation tracking
Updated both English and Chinese versions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
/cli:mode:bug-index generates analysis documents, not task JSON.
Claude should directly execute fixes based on analysis results,
not call /workflow:execute which requires task JSON files.
Updated both English and Chinese versions to reflect correct workflow:
- Removed incorrect /workflow:execute step
- Added clarification that Claude implements fix directly after analysis
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update version badges from v4.4.0 to v4.5.0 in README files
- Add v4.5.0 release highlights:
* Enhanced agent protocols with unified execution
* Streamlined UI workflows and improved documentation
* Optimized workflow templates for better clarity
* Improved CLI commands and tool integration
* New CLI execution agent for autonomous task handling
- Update Getting Started guides to reference v4.5.0
- Add cli-execution-agent to agent list in Getting Started guides
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Removed the "Direct Gemini Wrapper Script Usage" section from Getting Started guides
as users cannot manually execute these commands in Claude Code - all tool invocations
are handled automatically by Claude through semantic understanding.
Changes:
- Removed "Gemini Wrapper 脚本直接使用" section (Chinese)
- Removed "Direct Gemini Wrapper Script Usage" section (English)
- Kept "Semantic Tool Invocation" section explaining natural language usage
- Streamlined documentation to focus on user-facing interaction patterns
Rationale:
- Users cannot run ~/.claude/scripts/gemini-wrapper commands directly in Claude Code
- These are internal implementation details handled automatically by Claude
- Documentation should focus on how users interact with the system, not internal mechanics
Files updated:
- GETTING_STARTED.md (-47 lines)
- GETTING_STARTED_CN.md (-47 lines)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixed the "Semantic Tool Invocation" concept to accurately reflect its meaning:
**Before**: "Gemini 工具语义调用" referred to direct script usage
**After**: Properly describes semantic invocation as natural language interaction
Changes:
- Added "Semantic Tool Invocation" section explaining natural language usage
- Example: User says "Use gemini to analyze architecture"
- Claude understands and automatically executes appropriate commands
- Highlighted advantages: natural interaction, intelligent understanding, auto optimization
- Renamed previous section to "Direct Gemini Wrapper Script Usage"
- Clarified this is for scenarios requiring precise control
- Maintained all existing script usage examples
Structure now clearly distinguishes:
1. Semantic invocation (natural language → Claude → tool execution)
2. Direct script usage (manual command execution)
Updated both:
- GETTING_STARTED.md (English)
- GETTING_STARTED_CN.md (Chinese)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
