- Renamed update-memory-full.md -> update-full.md for consistency
- Renamed update-memory-related.md -> update-related.md for consistency
- Added parallel execution support (max 4 concurrent) for both direct and agent modes
- Fixed execution strategy: <20 modules direct parallel, ≥20 modules agent batch
- Removed misleading "orchestrator agent" section that caused hierarchy confusion
- Clarified coordinator always executes, agents only for batching ≥20 modules
- Added explicit file naming rules to prevent ToolSidebar.CLAUDE.md errors
- Updated template and script with CRITICAL file naming constraints
- Removed all emoji symbols from documentation for clean text format
- Added smart filtering strategy to docs.md for auto-skip patterns
Key improvements:
- Phase 3A: Direct parallel execution (max 4 concurrent per depth)
- Phase 3B: Agent batch execution (4 modules/agent)
- Both modes use same batching strategy, differ only in agent layer
- Explicit CLAUDE.md file naming in 3 locations (script, template, checklist)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Redesign output format to be dynamic and task-adaptive
- Replace fixed template with core + optional fields structure
- Add simple and complex task examples
- Update workflow and enhancement guidelines
- Add Agent Skills section to README.md and README_CN.md
- Document Prompt Enhancer skill usage with -e/--enhance flags
- Provide skill creation best practices
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update description to follow skills.md best practices
- Explicitly state trigger condition: 'Use when user input contains -e or --enhance flag'
- Improve discoverability with clear when-to-use guidance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update description: focus on intelligent analysis and session memory
- Simplify trigger mechanism to only -e/--enhance flags
- Condense internal analysis section to single concise statement
- Remove verbose semantic analysis details for cleaner documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Simplified process from 4 steps to 3 steps
- Changed to memory-only extraction (no file reading)
- Updated confirmation options: added "Suggest optimizations"
- Removed file operation tools (Bash, Read, Glob, Grep)
- Enhanced output format with structured sections
- Improved workflow efficiency and user interaction
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Updated task JSON schema to enhance structure and artifact integration.
- Simplified agent mode execution by omitting command fields in implementation steps.
- Introduced CLI execute mode with detailed command specifications for complex tasks.
- Added comprehensive IMPL_PLAN.md template with structured sections for project analysis, context, and execution strategy.
- Enhanced documentation for artifact usage and priority guidelines.
- Improved flow control definitions for task execution and context loading.
Replace batch replan workflow with TodoWrite tracking and direct agent calls:
- concept-clarify.md: Call conceptual-planning-agent for concept gaps
- action-plan-verify.md: Call action-planning-agent for task/plan issues
Both commands now require explicit user confirmation before fixes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Refactor context-gather.md to use general-purpose agent delegation
- Change from 4-phase manual execution to 2-phase agent-driven flow
- Move project structure analysis and documentation loading to agent execution
- Add Step 0: Foundation Setup for agent to execute first
- Update agent context passing to minimal configuration
- Add MCP tools integration guidance for agent
- Fix critical path mismatch in workflow data flow
- Update plan.md Phase 2 output path from .context/ to .process/
- Align with context-gather.md output location (.process/context-package.json)
- Ensure correct data flow: context-gather → concept-enhanced
- Update concept-enhanced.md line selection (minor formatting)
Verified path consistency across all workflow commands:
- context-gather.md outputs to .process/
- concept-enhanced.md reads from .process/
- plan.md passes correct .process/ path
- All workflow tools now use consistent .process/ directory
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
🎯 Major Enhancements:
1. Concept Clarification Quality Gate (concept-clarify.md)
- Added dual-mode support: brainstorm & plan modes
- Auto-detects mode based on artifact presence (ANALYSIS_RESULTS.md vs synthesis-specification.md)
- Backward compatible with existing brainstorm workflow
- Updates appropriate artifacts based on detected mode
2. Planning Workflow Enhancement (plan.md)
- Added Phase 3.5: Concept Clarification as quality gate
- Integrated Phase 3.5 between analysis and task generation
- Enhanced with interactive Q&A to resolve ambiguities
- Updated from 4-phase to 5-phase workflow model
- Delegated Phase 3 (Intelligent Analysis) to cli-execution-agent
- Autonomous context discovery and enhanced prompt generation
3. Documentation Updates (README.md, README_CN.md)
- Added /workflow:test-cycle-execute command documentation
- Explained dynamic task generation and iterative fix cycles
- Included usage examples and key features
- Updated both English and Chinese versions
🔧 Technical Details:
- concept-clarify now supports both ANALYSIS_RESULTS.md (plan) and synthesis-specification.md (brainstorm)
- plan.md Phase 3 now uses cli-execution-agent for MCP-powered context discovery
- Maintains auto-continue mechanism with one interactive quality gate (Phase 3.5)
- All changes preserve backward compatibility
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Reorganize documentation with improved structure and clarity:
- Add comprehensive dual-mode support (session vs prompt mode)
- Enhance usage examples with clear mode comparison
- Detail task specifications for IMPL-001 and IMPL-002
- Improve phase execution flow descriptions
- Add complete artifacts and output structure
- Expand best practices and related commands sections
The restructured documentation maintains backward compatibility while
making dual-mode functionality more discoverable and easier to use.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Remove redundant container and subtask JSON schema examples from TDD task
generation documentation. The command already defaults to task merging with
subtasks only created when complexity requires (>2500 lines or >6 files),
making these detailed schemas unnecessary for standard usage.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Enable test generation for existing codebases without requiring prior
workflow session. Supports both session-based (WFS-xxx) and prompt-based
(text description or file path) inputs with automatic mode detection.
Key improvements:
- Prompt mode: Generate tests from feature description or requirements file
- Backward compatible: Existing session-based usage unchanged
- Flexible input: Accepts session ID, text description, or file path
- Use case: Testing existing APIs without workflow history
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Updated documentation to use the renamed command:
- README.md: Updated test workflow example to use /workflow:test-cycle-execute
- SKILL.md: Updated prompt-enhancer skill documentation
Changes align with test-execute → test-cycle-execute renaming for better
clarity on iterative test-fix cycle functionality.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Renamed /workflow:test-execute to /workflow:test-cycle-execute to better
communicate the iterative cycle nature of the command (test → diagnose → fix → retest).
Changes:
- Renamed test-execute.md to test-cycle-execute.md
- Updated command metadata and document title
- Updated 9 internal references within the command file
- Updated reference in test-fix-gen.md related commands section
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Deleted advanced workflows, analysis examples, context optimization, template usage, and write examples for both Gemini and Qwen to streamline documentation.
- Updated CLAUDE.md to include references to new context strategies and search commands.
- Enhanced clarity and focus on compliance, security, and performance in remaining documentation.
- Gemini: add Chinese task examples (分析代码库, 理解架构, etc.)
- Qwen: add Chinese task labels (分析, 探索, 文档任务, etc.)
- Codex: add Chinese task examples (实现功能, 修复bug, 重构代码, etc.)
- Enable auto-trigger for both English and Chinese keywords
Add comprehensive skill system and batch replan functionality:
- New skill modules for Gemini, Qwen, Codex, and context search
- Enhanced task replan command with batch mode
- Improved action plan verification
- Complete skill documentation with examples
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Enhanced layout-extract and style-extract workflows with two-phase generation
process, allowing users to preview and select preferred options before full
generation.
Key changes:
- Split generation into two agent tasks:
* Task 1: Generate concept options with previews
* Task 2: Develop selected option into complete output
- Add Phase 1.5 interactive user selection:
* Present concept options with visual previews
* Capture user selection via AskUserQuestion tool
* Save selection to user-selection.json
- Layout workflow improvements:
* Generate layout concept options with ASCII wireframes
* User selects preferred structural approach
* Generate detailed templates only for selected concepts
- Style workflow improvements:
* Generate design direction options with color/typography previews
* User selects preferred design philosophy
* Generate complete design system only for selected direction
- Better user experience:
* Avoid generating unwanted variants
* Allow informed decisions before full generation
* Reduce wasted computation on unused variants
This change improves workflow efficiency and user control over design output.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Renamed test-gen to test-fix-gen and created new test-execute command for
dynamic iterative test-fix cycles. Improved task generation flexibility and
clarified data flow between planning and execution phases.
Key changes:
- Rename test-gen.md → test-fix-gen.md to reflect task generation purpose
- Add test-execute.md for dynamic test-fix workflow execution with CLI analysis
- Enhance test-fix-gen.md:
* Emphasize code-developer's understanding and analysis responsibilities
* Support flexible task count (minimum 2, expandable based on complexity)
* Add examples for multi-module test generation scenarios
- Clarify test-execute.md data flow:
* failure_context contains raw test output and error messages
* fix_strategy generated by CLI tool (Gemini/Qwen) analysis
* IMPL-001 (test generation) executes first, then IMPL-002 (test-fix cycle)
This improves workflow clarity and enables adaptive test-fix strategies for
complex projects requiring multiple test generation tasks.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
