catlog22 9e0a70150a refactor: redesign load-skill-memory to use Skill tool activation
Complete redesign from manual document reading to SKILL activation pattern:

**Before (Manual Loading)**:
- Complex level selection logic (0-3)
- Manual Read operations for each document
- Task-based auto-level selection
- ~200 lines of document loading code

**After (Skill Activation)**:
- Simple two-step: Validate → Activate
- Use Skill(command: "skill_name") tool
- System handles all documentation loading automatically
- ~100 lines simpler, more maintainable

**Key Changes**:

1. **Examples Updated**:
   - From: `/memory:load-skill-memory hydro_generator_module "分析热模型"`
   - To: `Skill(command: "hydro_generator_module")`

2. **Execution Flow Simplified**:
   - Step 1: Validate SKILL.md exists
   - Step 2: Skill(command: "skill_name")
   - System automatically handles progressive loading

3. **Removed Manual Logic**:
   - No explicit --level parameter
   - No manual document reading
   - No level selection algorithm
   - System determines context needs automatically

4. **Added SKILL Trigger Mechanism**:
   - Explains how SKILL description triggers work
   - Keyword matching (domain terms)
   - Action detection (analyzing, modifying, learning)
   - Memory gap detection
   - Path-based triggering

5. **Updated Integration Examples**:
   ```javascript
   Skill(command: "hydro_generator_module")
   SlashCommand(command: "/workflow:plan \"task\"")
   ```

**Benefits**:
- Simpler user experience (just activate SKILL)
- Automatic context optimization
- System handles complexity
- Follows Claude SKILL architecture
- Leverages built-in SKILL trigger patterns

**Philosophy Shift**:
- From: Manual control over documentation loading
- To: Trust SKILL system to load appropriate context
- Aligns with skill-memory.md description optimization

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-03 21:26:52 +08:00

🚀 Claude Code Workflow (CCW)

Version License Platform

Languages: English | 中文


Claude Code Workflow (CCW) transforms AI development from simple prompt chaining into a robust, context-first orchestration system. It solves execution uncertainty and error accumulation through structured planning, deterministic execution, and intelligent multi-model orchestration.

🎉 Version 5.2: Memory Commands Enhancement

Core Improvements:

  • Batch Processing - Single Level 1 task handles all module trees (67% fewer tasks)
  • Dual Execution Modes - Agent Mode and CLI Mode (--cli-execute) support
  • Pre-computed Analysis - Unified analysis eliminates redundant CLI calls (67% reduction)
  • Performance Boost - 67% fewer file reads, 33% fewer total tasks

See CHANGELOG.md for full details.

📚 New to CCW? Check out the Getting Started Guide for a beginner-friendly 5-minute tutorial!


Core Concepts

CCW is built on a set of core principles that differentiate it from traditional AI development approaches:

  • Context-First Architecture: Pre-defined context gathering eliminates execution uncertainty by ensuring agents have the correct information before implementation.
  • JSON-First State Management: Task states live in .task/IMPL-*.json files as the single source of truth, enabling programmatic orchestration without state drift.
  • Autonomous Multi-Phase Orchestration: Commands chain specialized sub-commands and agents to automate complex workflows with zero user intervention.
  • Multi-Model Strategy: Leverages the unique strengths of different AI models (Gemini for analysis, Codex for implementation) for superior results.
  • Hierarchical Memory System: A 4-layer documentation system provides context at the appropriate level of abstraction, preventing information overload.
  • Specialized Role-Based Agents: A suite of agents (@code-developer, @test-fix-agent, etc.) mirrors a real software team to handle diverse tasks.

⚙️ Installation

For detailed installation instructions, please refer to the INSTALL.md guide.

🚀 Quick One-Line Installation

Windows (PowerShell):

Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1" -UseBasicParsing).Content

Linux/macOS (Bash/Zsh):

bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)

Verify Installation

After installation, open Claude Code and check if the workflow commands are available by running:

/workflow:session:list

If the slash commands (e.g., /workflow:*) are recognized, the installation was successful.


🛠️ Command Reference

CCW provides a rich set of commands for managing workflows, tasks, and interacting with AI tools. For a complete list and detailed descriptions of all available commands, please see the COMMAND_REFERENCE.md file.

For a detailed technical specification of every command, see the COMMAND_SPEC.md.


🚀 Getting Started

The best way to get started is to follow the 5-minute tutorial in the Getting Started Guide.

Here is a quick example of a common development workflow:

  1. Create a Plan (automatically starts a session):
    /workflow:plan "Implement JWT-based user login and registration"
    
  2. Execute the Plan:
    /workflow:execute
    
  3. Check Status (optional):
    /workflow:status
    

🤝 Contributing & Support

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

Description
JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution
Readme MIT 35 MiB
Languages
TypeScript 34.7%
HTML 25%
Python 21.6%
JavaScript 13.2%
CSS 4%
Other 1.5%