catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-05 01:50:27 +08:00
Code Issues Packages Projects Releases Wiki Activity
535 Commits 20 Branches 102 Tags
0404a7eb7ca854fdbabbc5e63462f48f51cb3241
Commit Graph

535 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
catlog22
0404a7eb7c docs: 增强 conflict-resolution 核心规则，禁止使用 bash 命令输出 
添加核心职责规则：直接文本输出，禁止使用 bash echo/printf 命令

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 12:07:45 +08:00
catlog22
b98d28df3d docs(command-guide): add Pattern 0 brainstorming workflow for 0-to-1 development 
- Add Pattern 0: 头脑风暴 (Brainstorming) as first workflow pattern
- Distinguish FROM-ZERO-TO-ONE vs FEATURE-ADDITION scenarios
- Update decision tree to require brainstorming for new projects
- Enhance SKILL.md Mode 4 with project stage identification
- Remove duplicate Pattern 7 UI design workflow
- Add warning in best practices about not skipping brainstorming

Fixes issue where system incorrectly guided users to start with /workflow:plan
for new projects instead of /workflow:brainstorm:artifacts
 2025-11-06 22:14:14 +08:00
catlog22
1e67f5780d feat: 增强 command-guide skill，新增 UI 设计工作流指南和自动同步功能 
## 主要更新

### 1. 新增 UI 设计工作流完整指南
- 新增 `ui-design-workflow-guide.md` (12KB)
- 使用 Gemini 分析 11 个 UI 设计命令文件
- 提供 4 种工作流模式详细指导：
  - 探索式设计（新概念）
  - 设计复制（模仿现有网站）
  - 代码优先导入
  - 批量生成（高容量）
- 包含架构最佳实践、性能优化和故障排查

### 2. 更新工作流模式指南
- 在 `workflow-patterns.md` 中新增 Pattern 7: UI设计工作流
- 提供三种子模式的中文示例
- 添加 UI 设计指南的交叉引用

### 3. 增强索引构建脚本
- 更新 `analyze_commands.py` 支持自动同步 reference 目录
- 新增 `sync_reference_directory()` 函数：
  - 自动删除旧的 reference 文件
  - 从 `.claude/agents` 和 `.claude/commands` 复制最新文件
  - 确保索引构建前 reference 目录为最新
- 增强统计输出，显示 reference 目录同步状态

### 4. 更新索引文件
- 重建所有索引文件（all-commands.json, by-category.json 等）
- 优化命令元数据和分类
- 同步最新的 UI 设计命令（包括新增的 import-from-code.md）

## 技术细节

**命令分类体系**:
- Orchestrators: explore-auto, imitate-auto, batch-generate
- Core Extractors: style-extract, layout-extract, animation-extract
- Input & Capture: capture, explore-layers, import-from-code
- Assemblers: generate, update

**架构原则**:
- 关注点分离：Style、Structure、Motion 独立
- Token-First CSS：使用 CSS 变量而非硬编码
- 并行执行：支持最多 6 个并发任务

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.5.1 		2025-11-06 21:37:19 +08:00
catlog22
581b46b494 feat: 更新 UI 设计工作流，增强设计完整性检查并生成详细报告 2025-11-06 21:20:19 +08:00
catlog22
eeffa8a9e8 Enhance UI Design Workflows with Intelligent Path Detection and Source Selection 
- Updated explore-auto.md to include a new phase for intelligent path detection and source selection, allowing the system to identify existing file paths from prompts and images.
- Introduced conditional code import and completeness assessment based on detected design sources (code only, visual only, hybrid).
- Modified phase execution flow to accommodate new checks for style, animation, and layout completeness based on the design source.
- Added error handling for missing design elements and user prompts for visual supplementation.
- Enhanced imitate-auto.md with intelligent path detection and a new phase for code import and completeness assessment, ensuring a hybrid approach when applicable.
- Implemented detailed reporting for each phase, including missing elements and recommendations for improvement.
- Created a comprehensive import-from-code.md file outlining the workflow for importing design systems from code files, detailing the execution process and error handling.
 2025-11-06 21:00:49 +08:00
catlog22
096621eee7 docs: 强调 SKILL 智能整合原则，避免模板直接复制 
核心修改：
1. 新增"Core Principle: Intelligent Integration"部分
   - 明确 SKILL 提供参考材料用于智能整合，而非直接复制模板
   - 定义响应策略：分析上下文 → 提取相关信息 → 合成定制化 → 交付目标响应
   - 列出禁止事项和必须遵守的原则

2. 更新所有 6 个 Mode 的 Process 描述：
   - Mode 1 (Command Search): 强调智能过滤和排序，而非 JSON 数据转储
   - Mode 2 (Smart Recommendations): 分析工作流上下文并评估推荐优先级
   - Mode 3 (Full Documentation): 提取用户相关部分，渐进式披露
   - Mode 4 (Beginner Onboarding): 评估用户背景，设计个性化学习路径
   - Mode 5 (Issue Reporting): 智能引导信息收集，适应模板部分
   - Mode 6 (Deep Command Analysis): 合成聚焦解释，处理并整合 CLI 分析

3. 更新示例说明：
   - 每个 Mode 的示例都强调"NOT: [直接返回模板]"
   - 展示如何根据上下文定制响应

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 16:56:34 +08:00
catlog22
e8a5980c88 docs: 修正 CLI 工具语义调用概念并精简文档 
核心修改：
1. 修正语义调用触发方式：用户必须明确说"使用 gemini"、"用 qwen"、"让 codex"
2. 区分两种调用方式：
   - CLI 工具语义调用：用户明确指定工具 → Claude 生成 CLI 命令
   - Slash 命令调用：用户输入 /workflow:* 或 /cli:* → 执行预定义流程
3. 精简文档结构：
   - 删除过多的重复示例和详细步骤
   - 简化能力特性清单
   - 删除进阶技巧和避免做法部分
   - 添加常用工作流程指南
4. 更新所有使用场景示例，确保触发方式正确

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 16:52:31 +08:00
catlog22
38b070551c fix: 使用绝对路径确保 skill 在全局安装时正常工作 
问题
- 原有代码使用相对路径 (cd reference &&)
- skill 安装在 ~/.claude/skills/ 后相对路径会失效

修复
- 所有文件操作使用绝对路径: ~/.claude/skills/command-guide/reference/
- CLI 命令改用 --include-directories 参数指向绝对路径
- 更新示例输出中的路径为绝对路径

影响
- handleSimpleQuery: basePath 使用绝对路径
- locateCommandFile: 使用 basePath 参数
- executeCLIAnalysis: 使用 --include-directories 替代 cd
- resolveEntityPath: glob 使用绝对路径
- buildCLIPrompt: CONTEXT 使用 @**/* + --include-directories

版本更新
- v1.3.0 → v1.3.1

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 16:37:21 +08:00
catlog22
1897ba4e82 feat: 增强 command-guide skill 支持深度命令分析和 CLI 辅助查询 
新增 Mode 6: 深度命令分析
- 创建 reference 备份目录（80个文档：11 agents + 69 commands）
- 支持简单查询（直接文件查找）和复杂查询（CLI 辅助分析）
- 集成 gemini/qwen 进行跨命令对比、最佳实践、工作流分析
- 添加查询复杂度自动分类和降级策略

更新文档
- SKILL.md: 添加 Mode 6 说明和 Reference Documentation 章节
- implementation-details.md: 添加完整的 Mode 6 实现逻辑
- 版本更新至 v1.3.0

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 16:27:58 +08:00
catlog22
0ab3d0e1af fix: 更新命令指南描述中的触发器，统一格式以提高一致性 2025-11-06 15:46:08 +08:00
catlog22
5aa1b75e95 feat: 增强问题报告和诊断模板，添加执行流程强调和隐私保护指南 2025-11-06 15:40:00 +08:00
catlog22
958567e35a docs: 发布 v5.5.0 - 交互式命令指南与增强文档 
版本更新: v5.4.0 → v5.5.0

核心改进:
- ✨ 命令指南技能 - 支持 CCW-help 和 CCW-issue 关键词触发
- ✨ 增强命令描述 - 所有 69 个命令更新了详细功能说明
- ✨ 5 索引命令系统 - 按分类、使用场景、关系和核心命令组织
- ✨ 智能推荐 - 基于上下文的下一步操作建议

文档更新:
- README.md / README_CN.md: 新增"需要帮助？"章节，介绍 CCW-help/CCW-issue 用法
- CHANGELOG.md: 添加完整的 v5.5.0 版本说明（109行详细内容）
- SKILL.md: 更新版本至 v1.1.0

命令指南功能:
- 🔍 智能命令搜索 - 按关键词、分类或场景查找
- 🤖 下一步推荐 - 工作流引导和上下文建议
- 📖 详细文档 - 参数、示例和最佳实践
- 🎓 新手入门 - 14 个核心命令学习路径
- 📝 问题报告 - 标准化 bug 报告和功能请求模板

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.5.0 		2025-11-06 15:25:11 +08:00
catlog22
920b179440 docs: 更新所有命令描述并重新生成索引文件 
- 更新所有69个命令文件的description字段，基于实际功能重新生成详细描述
- 重新生成5个索引文件（all-commands, by-category, by-use-case, essential-commands, command-relationships）
- 移动analyze_commands.py到scripts/目录并完善功能
- 移除临时备份文件

命令描述改进示例：
- workflow:plan: 增加了工具和代理的详细说明（Gemini, action-planning-agent）
- cli:execute: 说明了YOLO权限和多种执行模式
- memory:update-related: 详细说明了批处理策略和工具回退链

索引文件改进：
- usage_scenario从2种扩展到10种（更精细分类）
- command-relationships覆盖所有69个命令
- 区分built-in（内置调用）和sequential（用户顺序执行）关系

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 15:11:31 +08:00
catlog22
6993677ed9 feat: Add command relationships and essential commands JSON files 
- Introduced command-relationships.json to define relationships between various commands.
- Created essential-commands.json to provide detailed descriptions and usage scenarios for key commands.
- Implemented update-index.sh script for maintaining command index files, including backup and validation processes.
- Added templates for bug reports, feature requests, and questions to streamline issue reporting and feature suggestions.
 2025-11-06 12:59:14 +08:00
catlog22
8e3dff3d0f refactor: optimize universal templates - reduce to <120 lines 
- Streamline 00-universal-rigorous-style.txt: 148→92 lines (-38%)
  - Merge capabilities and thinking mode sections
  - Consolidate execution checklist
  - Simplify quality standards
  - Preserve complete response structure (8 sections)
  - Combine style and constraints sections

- Streamline 00-universal-creative-style.txt: 205→95 lines (-54%)
  - Merge capabilities and thinking mode sections
  - Consolidate exploration phases
  - Simplify quality standards
  - Condense multi-perspective sections
  - Preserve complete response structure (10 sections)
  - Condense creative techniques to optional toolkit

Benefits:
✅ Both templates under 120 lines (92 and 95)
✅ Reduced verbosity by 53% (310→187 lines)
✅ Maintained all core functionality
✅ Clearer, more scannable structure
✅ Faster to load and parse

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 12:42:23 +08:00
catlog22
775c982218 feat: add universal fallback templates and fix template reference 
- Add universal templates for flexible task execution:
  - 00-universal-rigorous-style.txt: Precision-driven execution
  - 00-universal-creative-style.txt: Innovation-focused exploration
- Update intelligent-tools-strategy.md:
  - Document universal templates as fallback option
  - Add usage guide and selection criteria
  - Update task-template matrix with universal fallbacks
  - Add RULES field examples for universal templates
- Fix update_module_claude.sh template path:
  - Update reference from claude-module-unified.txt to 02-document-module-structure.txt
  - Align with priority prefix naming convention (854464b)

Benefits:
✅ Fallback templates available when no specific template matches
✅ Support both rigorous and creative execution styles
✅ Script correctly references renamed template file
✅ Comprehensive documentation for template selection

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 12:39:00 +08:00
catlog22
164d1df341 docs: 更新文档以反映v5.4.0版本更新 
更新内容：
- CHANGELOG.md：添加v5.4.0完整更新日志
  - CLI模板系统重组（19个模板，优先级前缀）
  - Gemini 404错误回退策略
  - 21处模板引用更新
  - 目录结构优化

- README.md & README_CN.md：更新版本号和核心亮点
  - 版本徽章：v5.2.0 → v5.4.0
  - 版本说明：更新为v5.4核心改进
  - 突出优先级模板、错误处理、统一引用、组织优化

文档变更详情：
- 完整的v5.4.0变更日志（141行）
- 双语README版本信息同步更新
- 清晰的升级说明和使用指南

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 11:07:43 +08:00
catlog22
bbddbebef2 docs: 添加Gemini模型404错误回退策略 
在intelligent-tools-strategy.md中添加错误处理准则：
- Model Selection部分：快速参考404错误回退到gemini-2.5-pro
- Tool Specifications部分：详细的错误处理指南，涵盖HTTP 429和404错误

变更详情：
- HTTP 404: gemini-3-pro-preview-11-2025返回404时回退到gemini-2.5-pro
- HTTP 429: 保持现有处理逻辑（检查结果是否存在）

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.4.0 		2025-11-06 11:01:11 +08:00
catlog22
854464b221 refactor: 重组CLI模板系统，采用优先级前缀命名 
主要变更：
- 模板重命名：采用优先级前缀（01-通用, 02-专用, 03-领域特定）
- 目录调整：bug-diagnosis从development移至analysis
- 引用更新：5个命令文件中21处模板引用更新为新路径
- 路径统一：所有引用统一使用完整路径格式

模板变更详情：
- analysis/：8个模板（01-trace-code-execution, 01-diagnose-bug-root-cause等）
- development/：5个模板（02-implement-feature, 02-refactor-codebase等）
- planning/：5个模板（01-plan-architecture-design, 02-breakdown-task-steps等）
- memory/：1个模板（02-document-module-structure）

命令文件更新：
- cli/mode/bug-diagnosis.md（6处引用）
- cli/mode/code-analysis.md（6处引用）
- cli/mode/plan.md（6处引用）
- task/execute.md（1处引用）
- workflow/tools/test-task-generate.md（2处引用）

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-06 10:57:17 +08:00
catlog22
afed67cd3a docs: 更新智能工具选择策略文档，明确规则和命令模板的使用要求 v5.3.0 2025-11-06 10:00:28 +08:00
catlog22
b6b788f0d8 Refactor intelligent-tools-strategy.md: 
- Introduced a universal prompt template for CLI tools.
- Streamlined tool selection and command syntax for clarity.
- Enhanced model selection details for Gemini, Qwen, and Codex.
- Updated quick decision matrix to reflect new structure.
- Clarified core principles and best practices for tool usage.
- Improved context configuration and memory integration guidelines.
- Revised rules field configuration for command substitution.
- Added detailed examples for command usage and session management.
- Optimized directory navigation and context optimization strategies.
 2025-11-06 09:27:47 +08:00
catlog22
63acd94bbf docs: 更新智能工具选择策略文档，增强模型选择和命令模板结构的清晰度 2025-11-06 09:16:25 +08:00
catlog22
43d647e7b2 docs: 强调--include-directories参数减少无关文件干扰的优势 
在多个关键位置强化cd + --include-directories模式的核心价值：
- Quick Decision Matrix添加多目录分析场景示例
- Core Principles新增"最小化上下文噪音"原则
- 更新Purpose说明减少无关文件噪音的核心目的
- Benefits部分突出最小化无关文件干扰优势
- 示例中添加注释展示实际效果和文件范围控制

通过精确的目录导航和依赖引入，减少token使用并提高分析精度

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.2.3 		2025-11-05 22:29:55 +08:00
catlog22
76aa20cdfd docs: 更新.gitignore以包含新的命令模板文件 2025-11-05 22:14:03 +08:00
catlog22
39c956c703 docs: 更新CLI初始化命令以使用Write函数创建配置文件 2025-11-05 22:13:02 +08:00
catlog22
dd04433079 docs: 在任务生成命令中添加focus_paths路径清晰度准则 
在三个任务生成命令中添加核心准则：
- task-generate.md
- task-generate-tdd.md
- task-generate-agent.md

路径要求：
- 优先使用绝对路径（如 D:\project\src\module）
- 或使用从项目根目录的清晰相对路径（如 ./src/module）
- 避免模糊的相对路径（如 analysis, interfaces）

更新示例JSON展示混合使用两种路径方式

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-05 21:51:58 +08:00
catlog22
c36ff8fcec docs: 继续标准化工作流会话和版本命令文档格式 
移除剩余命令文档中的表情符号和视觉装饰：
- version.md - 版本检查和更新命令
- workflow/session/list.md - 会话列表命令
- workflow/session/resume.md - 会话恢复命令
- workflow/session/start.md - 会话启动命令

保持与其他命令文档的格式一致性

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-05 21:49:03 +08:00
catlog22
967e3805b7 docs: 标准化命令文档格式，移除表情符号并添加命令模板规范 
更新所有命令文档以提高可读性和一致性：
- 移除所有表情符号（⚠️, ✅, ❌, ▸等），使用纯文本替代
- 统一标题格式，改进章节结构
- 简化状态指示器和格式标记
- 添加三个新的命令模板规范文档

新增文档：
- COMMAND_FLOW_STANDARD.md - 标准命令流程规范
- COMMAND_TEMPLATE_EXECUTOR.md - 执行器命令模板
- COMMAND_TEMPLATE_ORCHESTRATOR.md - 编排器命令模板

影响范围：
- CLI命令（cli-init, codex-execute, discuss-plan, execute）
- 内存管理命令（skill-memory, tech-research, workflow-skill-memory）
- 任务管理命令（breakdown, create, execute, replan）
- 工作流命令（所有workflow相关命令）

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-05 21:48:43 +08:00
catlog22
e898ebc322 docs: 更新SKILL.md生成描述和变量替换指南，增强文档的清晰度和准确性 2025-11-05 20:15:18 +08:00
catlog22
a38a216cc9 docs: 移除完成工作流会话的SKILL包更新选项，简化文档并优化流程描述 2025-11-05 19:59:57 +08:00
catlog22
3b351693fc refactor: 重构UI设计工作流的交互模式和字段架构 
主要变更：

1. animation-extract.md 重构交互流程
   - Phase 2 交互从Agent移至主流程（参考artifacts.md模式）
   - 使用【问题N - 标签】格式，提供方向性指导而非具体示例
   - Phase 3 Agent改为纯合成任务（无用户交互）
   - 保留独立的animation-tokens.json输出

2. style-extract.md 字段扩展优化
   - 保留字段扩展：typography.combinations、opacity、component_styles、border_radius、shadows
   - 移除animations字段（由专门的animation-tokens.json提供）
   - 完善design-tokens.json格式文档

3. generate.md 支持新字段
   - 保留animation-tokens.json可选加载
   - 支持typography.combinations、opacity、component_styles
   - 生成对应CSS类（组件样式类、排版预设类）

4. batch-generate.md 字段支持
   - 解析新的design-tokens字段结构
   - 使用组件预设和排版预设

架构改进：
- 清晰分离：design-tokens.json（基础设计系统）+ animation-tokens.json（动画配置）
- 主流程交互：用户决策在主流程完成，Agent只负责合成
- 字段完整性：保留所有设计系统扩展字段

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-05 19:50:47 +08:00
catlog22
ab266a38b1 docs: Add templates for tech stack module documentation and SKILL index generation 2025-11-04 22:51:21 +08:00
catlog22
dc9d63b349 docs: Update context search strategy to clarify SKILL usage and enhance project documentation 2025-11-04 22:31:57 +08:00
catlog22
72bdb3470e docs: Clarify usage and validation for workflow-skill-memory command, ensuring only WFS-* sessions are processed 2025-11-04 22:26:00 +08:00
catlog22
f496a35da5 Remove benefits and architecture sections from workflow-skill-memory documentation for clarity and conciseness. 2025-11-04 22:10:06 +08:00
catlog22
15bf9cdbed Refactor workflow session archival and SKILL package updates 
- Updated command invocation for SKILL memory generator to use session ID instead of incremental mode.
- Enhanced documentation on the processing of archived sessions and intelligent aggregation by the agent.
- Added templates for generating conflict patterns, lessons learned, SKILL index, and sessions timeline.
- Established clear update strategies for incremental and full modes across all new templates.
- Improved structure and formatting rules for better clarity and usability in generated documents.
 2025-11-04 21:46:37 +08:00
catlog22
779581ec3b Add workflow-skill-memory command and skill aggregation prompt 
- Implemented the workflow-skill-memory command for generating SKILL packages from archived workflow sessions.
- Defined a 4-phase execution process for reading sessions, extracting data, organizing information, and generating SKILL files.
- Created a detailed prompt for skill aggregation, outlining tasks for analyzing archived sessions, aggregating lessons learned, conflict patterns, and implementation summaries.
- Established output formats for aggregated lessons, conflict patterns, and implementation summaries to ensure structured and actionable insights.
 2025-11-04 21:34:36 +08:00
catlog22
483ab621bc docs: Replace project-specific examples with generic examples in load-skill-memory 2025-11-03 22:53:41 +08:00
catlog22
6adbe7c1e9 feat: Make skill_name optional with intelligent auto-detection in load-skill-memory 
## Major Changes

### Parameter Flexibility
- Changed `<skill_name>` from Required to Optional `[skill_name]`
- Updated argument-hint: `[skill_name] "task intent description"`
- Description: "Activate SKILL package (auto-detect or manual)"

### Auto-Detection Strategy (New Feature)
Added Step 1: Determine SKILL Name (if not provided)
1. **Path Extraction**: Scan task for file paths, extract project names
   - Example: `"D:\projects\my_project\src\auth.py"` → extracts `my_project`
2. **Keyword Matching**: Match task keywords against SKILL descriptions
3. **Validation**: Check if extracted name exists in `.claude/skills/`

### Core Philosophy Update
- Changed from "Manual Activation" → "Flexible Activation"
- Auto-detect from task description/paths OR user explicitly specifies

### Enhanced Documentation
- Parameters section: Added auto-detection explanation and path example
- Task intent description: Now serves dual purpose (auto-detection + scope selection)
- Updated all execution flow steps (Step 1 → Step 2 → Step 3)

### Usage Examples
- **Example 1**: Manual specification (explicit skill_name)
- **Example 2**: Auto-detection from path (NEW)
  - Shows complete auto-detection workflow
  - Path extraction → Validation → Activation

## Benefits
- ✅ **Smarter activation**: System extracts skill name from context
- ✅ **Reduced user effort**: No need to specify obvious skill names
- ✅ **Backward compatible**: Manual specification still supported
- ✅ **Path-aware**: Intelligent extraction from file paths in task description

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-03 22:50:38 +08:00
catlog22
b5fb4e3d48 docs: Enhance path trigger strategy with intelligent skill name extraction 
## Enhancement
- Updated path mention trigger description for clarity
- Emphasized intelligent extraction: "system extracts skill name from file paths for intelligent triggering"
- Removed example, replaced with mechanism description for better understanding

## Changes
- Line 25: Changed from "e.g., mentioning files under SKILL's project path" to "system extracts skill name from file paths for intelligent triggering"
- Clearer expression of automatic SKILL activation via path-based extraction

## Example Mechanism
- User mentions: `D:\projects\hydro_generator_module\src\file.py`
- System extracts: `hydro_generator_module` as potential skill name
- Automatic trigger: Activates corresponding SKILL package if exists

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-03 22:32:41 +08:00
catlog22
1cabccbbdd docs: Add path-based trigger strategy to load-skill-memory command 
## Enhancement
- Added path mention trigger strategy in Note section (1 line)
- Clarified: "Normal SKILL activation happens automatically via description triggers or path mentions"
- Example: Mentioning files under SKILL's project path auto-triggers SKILL package
- Helps users understand automatic SKILL activation mechanisms

## Changes
- Modified line 25: Added "or path mentions (e.g., mentioning files under SKILL's project path)"
- Total addition: 1 line as requested

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-03 22:30:29 +08:00
catlog22
8073549234 docs: Optimize skill-memory.md structure and add Skill() to context search strategy 
## skill-memory.md Optimization
- Restructured file from 553 to 534 lines (-19 lines, -3.4%)
- Eliminated duplicate content in 3 areas:
  * Auto-Continue mechanism (3 occurrences → 1)
  * Execution flow descriptions (2 occurrences → 1)
  * Phase 4 never-skip notes (2 occurrences → 1)
- Merged "TodoWrite Pattern" and "Auto-Continue Execution Flow" into unified "Implementation Details" section
- Improved hierarchy: Overview → Execution → Implementation Details → Parameters → Examples
- Added Example 5 demonstrating Skip Path usage
- All content preserved, no information loss

## context-search-strategy.md Enhancement
- Added Skill() as highest priority tool in Core Search Tools (1 line)
- Emphasized: "FASTEST way to get project context - use FIRST if SKILL exists (higher priority than CLI analysis)"
- Added to Tool Selection Matrix: "FASTEST context loading - use FIRST if SKILL exists"
- Added Quick Command Reference with intelligent auto-trigger emphasis
- Total addition: 3 lines as requested

## Benefits
- Clearer file structure with eliminated redundancy
- Skill() now prominently featured as first-priority context tool
- Intelligent auto-trigger mechanism emphasized
- Consistent messaging across documentation

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-03 22:28:27 +08:00
catlog22
3eec2a542b feat(v5.2.2): Add intelligent skip logic to /memory:skill-memory with parameter naming correction 
## Smart Documentation Generation
- Automatically detects existing documentation and skips Phase 2/3 when docs exist
- Jump directly to Phase 4 (SKILL.md generation) for fast SKILL index updates
- Phase 4 always executes to ensure SKILL.md stays synchronized
- Explicit --regenerate flag for forced full documentation refresh

## Parameter Naming Correction
- Reverted --update back to --regenerate for accurate semantic meaning
- "regenerate" = delete and recreate (destructive operation)
- "update" was misleading (implied incremental update, not implemented)

## Execution Paths
- Full Path: All 4 phases (no docs OR --regenerate specified)
- Skip Path: Phase 1 → Phase 4 (docs exist AND no --regenerate)
- Added comprehensive TodoWrite patterns and flow diagrams for both paths

## Phase 1 Enhancement
- Step 4: Determine Execution Path - decision logic with SKIP_DOCS_GENERATION flag
- Checks existing documentation count
- Evaluates --regenerate flag presence
- Displays appropriate skip or regeneration messages

## Benefits
- 5-10x faster SKILL updates when documentation already exists
- Always fresh SKILL.md index reflecting current documentation structure
- Explicit control via --regenerate flag for full refresh

## Modified Files
- .claude/commands/memory/skill-memory.md (553 lines, +59 lines for skip logic)
- CHANGELOG.md (added v5.2.2 release notes)

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.2.2 		2025-11-03 22:21:08 +08:00
catlog22
f1c89127dc chore: release v5.2.1 - SKILL workflow improvements 
Major Changes:
- Redesigned /memory:load-skill-memory as manual activation tool
- Changed --regenerate to --update flag in skill-memory command
- Enhanced context search strategy with SKILL first priority

Details:
1. load-skill-memory command redesign:
   - Manual activation: user specifies SKILL name explicitly
   - Intent-driven doc loading: 5 levels based on task description
   - Memory-based validation: removed bash checks
   - File size: 355→132 lines (-62.8%)

2. Parameter naming consistency:
   - Renamed --regenerate to --update in skill-memory.md
   - Updated all references and examples

3. Context search strategy (global .claude):
   - Added SKILL packages as first priority tool
   - Emphasized use BEFORE Gemini analysis
   - Updated tool selection matrix and examples

See CHANGELOG.md for complete details.
v5.2.1 		2025-11-03 22:07:09 +08:00
catlog22
8926611964 refactor: update load-skill-memory command to manual activation and intent-driven loading 2025-11-03 21:55:22 +08:00
catlog22
8a9bc7a210 refactor: optimize load-skill-memory structure and remove emojis 
- Merge duplicate content: consolidate Sections 4, 6, 7, 9, 10
- Reduce file size from 382 to 348 lines (-8.9%)
- Remove all emoji icons, replace with text alternatives
- Improve section flow: 8 sections total (was 11)
- Preserve all information while eliminating redundancy
 2025-11-03 21:38:42 +08:00
catlog22
25a358b729 feat: implement dynamic SKILL discovery with intelligent matching 
Transform load-skill-memory from manual specification to automatic discovery:

**Core Change**:
- From: User specifies SKILL name manually
- To: System automatically discovers and matches SKILL based on task context

**New Capabilities**:

1. **Three-Step Execution**:
   - Step 1: Discover all available SKILLs (.claude/skills/)
   - Step 2: Match most relevant SKILL using scoring algorithm
   - Step 3: Activate matched SKILL via Skill() tool

2. **Intelligent Matching Algorithm**:
   - **Path-Based** (Highest Priority): Direct path match from file paths
   - **Keyword Matching** (Secondary): Score by keyword overlap
   - **Action Matching** (Tertiary): Detect action verbs (分析/修改/学习)

3. **Updated Parameters**:
   - From: `<skill_name> [--level] [task description]`
   - To: `"task description or file path"`
   - More intuitive user experience

4. **New Examples**:
   ```bash
   /memory:load-skill-memory "分析热模型builder pattern实现"
   /memory:load-skill-memory "D:\dongdiankaifa9\hydro_generator_module\builders\base.py"
   /memory:load-skill-memory "修改workflow文档生成逻辑"
   ```

**Matching Examples**:

Task: "分析热模型builder pattern实现"
- hydro_generator_module: 4 points (thermal+builder+analyzing) ✅
- Claude_dms3: 1 point (analyzing only)

Task: "D:\dongdiankaifa9\hydro_generator_module\builders\base.py"
- Path match: hydro_generator_module ✅ (exact path)

**Benefits**:
- No manual SKILL name required
- Automatic best match selection
- Path-based intelligent routing
- Keyword scoring for relevance
- Action verb detection for context

**User Experience**:
Before: "/memory:load-skill-memory hydro_generator_module '分析热模型'"
After: "/memory:load-skill-memory '分析热模型实现'"

System automatically discovers and activates hydro_generator_module SKILL.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-03 21:31:06 +08:00
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
catlog22
7b2160d51f feat: add /memory:load-skill-memory command for progressive SKILL loading 
New command for loading SKILL package documentation with intelligent level selection:

**Two-Step Process**:
1. Validate SKILL existence in .claude/skills/{skill_name}/
2. Load documentation based on task requirements and complexity

**Progressive Loading Levels**:
- Level 0: Quick Start (~2K tokens) - Overview exploration
- Level 1: Core Modules (~10K tokens) - Module analysis
- Level 2: Complete (~25K tokens) - Code modification
- Level 3: Deep Dive (~40K tokens) - Feature implementation

**Auto-Level Selection**:
- Keyword-based detection from task description
- "快速了解" → Level 0
- "分析" → Level 1
- "修改" → Level 2
- "实现" → Level 3

**Key Features**:
- SKILL existence validation with available SKILLs listing
- Task-driven level auto-selection
- Token budget estimation
- Error handling for missing SKILLs/documentation
- Explicit --level override support

**Usage Examples**:
```bash
/memory:load-skill-memory hydro_generator_module "分析热模型"
/memory:load-skill-memory Claude_dms3 --level 2 "修改workflow"
/memory:load-skill-memory multiphysics_network "实现耦合器"
```

**Integration**:
- Works with SKILL packages generated by /memory:skill-memory
- Optimizes token usage through progressive loading
- Supports workflow planning and execution commands

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-03 21:10:32 +08:00
catlog22
aa1900a3e7 feat: enhance SKILL description to prioritize context loading when memory is empty 
Optimize description format to emphasize SKILL as primary context source:

**Key Changes**:
1. Action verbs updated: "working with" → "modifying" (more explicit)
2. Added priority trigger: "especially when no relevant context exists in memory"
3. Expanded Trigger Optimization guidance with three key scenarios

**Three Key Actions**:
- analyzing (分析) - Understanding codebase structure
- modifying (修改) - Making changes to code
- learning (了解) - Exploring unfamiliar modules

**Priority Context Loading**:
- Emphasize SKILL loading when conversation memory lacks relevant context
- Position SKILL as first-choice context source for fresh inquiries
- Improve trigger sensitivity for cold-start scenarios

**Before**:
"Load this SKILL when analyzing, working with, or learning about {domain}
or files under this path for comprehensive context."

**After**:
"Load this SKILL when analyzing, modifying, or learning about {domain}
or files under this path, especially when no relevant context exists in memory."

**Impact**:
- Higher trigger rate when users ask about unfamiliar modules
- Better context initialization for new analysis sessions
- Clearer action vocabulary aligns with actual use cases

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-03 21:06:52 +08:00