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
658 Commits 20 Branches 102 Tags
claude/refactor-task-workflow-01WBDUE6UgN74q4JhmwDJ6c1
Commit Graph

658 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
catlog22
a2862090e1 docs(ui-design): remove key features and examples sections from explore-auto and imitate-auto documentation 2025-11-09 15:23:53 +08:00
catlog22
fb65e8f90f docs(ui-design-agent): add remote assets reference guidelines 
Add comprehensive remote assets reference section:
- Image CDN services (Unsplash, Picsum, Placeholder.com)
- Icon libraries (Lucide, Font Awesome, Material Icons)
- Usage patterns with HTML examples
- Best practices for external resource loading

Guidelines include:
- HTTPS URLs mandatory
- Width/height attributes for layout stability
- Lazy loading for below-fold images
- Accessibility requirements (alt attributes)
- Prohibit local file paths and base64 embedding

Position: Between Typography System and Visual Effects System

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 15:05:47 +08:00
catlog22
0d11a29577 docs(explore-auto): add animation-extraction folder structure 
Add missing animation-extraction output structure:
- .intermediates/animation-analysis/: analysis-options.json (with embedded user_selection), animations-*.json (URL mode)
- animation-extraction/: animation-tokens.json, animation-guide.md

Complete file structure now includes all three extraction phases:
- style-extraction
- animation-extraction
- layout-extraction

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 15:04:07 +08:00
catlog22
e488352f15 fix(explore-auto): correct intermediate file structure references 
Fix file structure documentation to reflect actual implementation:
- user_selection is embedded in analysis-options.json, not separate file
- computed-styles.json only exists in URL mode
- dom-structure-*.json only exists in URL mode
- Remove obsolete design-space-analysis.json reference

Updated:
- .intermediates/style-analysis/: analysis-options.json (with embedded user_selection), computed-styles.json (URL mode)
- .intermediates/layout-analysis/: analysis-options.json (with embedded user_selection), dom-structure-*.json (URL mode)

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 15:02:29 +08:00
catlog22
dd0348c3eb docs(ui-design): add batch text format interaction strategy for user questions 
Add universal question interaction rules to UI design commands:
- Use batch text format (1a 2b) when questions > 4 OR options > 3
- Otherwise use AskUserQuestion tool
- Support multi-selection: [N][key1,key2] format for layout/style commands
- Variable-based templates with option descriptions for clarity

Updated commands:
- animation-extract.md: Single selection per question
- layout-extract.md: Multi-selection per target support
- style-extract.md: Multi-selection for variants

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 14:59:27 +08:00
catlog22
3be5663ab0 Remove batch-generate command documentation and related references; update explore-auto and layout-extract commands to enable interactive mode by default and embed user selections in analysis-options.json; enhance style-extract command to capture user selections and update analysis JSON; revise command reference and specification documents accordingly. 2025-11-09 14:35:30 +08:00
catlog22
d410ed20d6 docs(command-guide): add standardized update guideline and enhance documentation 
- Add UPDATE-GUIDELINE.md: version-agnostic update process (6 phases)
- Update SKILL.md: remove version info, reference update guideline
- Update ui-design-workflow-guide.md: document explore-auto default non-interactive mode
- Sync reference docs: latest UI design command changes (9 files)
- Rebuild indexes: reflect explore-auto --interactive parameter addition

Refs: 47e05f2 (explore-auto default mode change)

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 13:38:34 +08:00
catlog22
47e05f2142 fix: change explore-auto default to non-interactive mode 
- Update default interactive_mode from true to false
- Add --interactive parameter documentation
- Non-interactive batch generation is now the default behavior

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 13:30:06 +08:00
catlog22
6caf5eed49 Merge branch 'main' of https://github.com/catlog22/Claude-Code-Workflow 2025-11-09 13:29:02 +08:00
catlog22
084f7b7254 docs(command-guide): sync reference docs and rebuild indexes 
- Sync latest agent files (action-planning-agent, ui-design-agent)
- Sync latest UI design workflow commands (11 files)
- Sync latest test workflow commands (8 files)
- Rebuild all 5 index files with updated metadata

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 13:24:49 +08:00
catlog22
c647787b86 feat: add interactive multi-selection mechanism for UI design workflow 
- Add --interactive flag to style-extract and layout-extract commands
- Enhance animation-extract --mode interactive with selection storage
- Implement unified user-selections storage in .intermediates/user-selections/
- Add parameter passthrough in explore-auto (default: enabled) and imitate-auto (always enabled)
- Support fallback to generate all variants when no selection file exists
- Fix explore-auto.md bug: duplicate --base-path in import-from-code call (line 313)

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 23:53:27 +08:00
catlog22
d213885f52 Refactor layout and style extraction workflows for multi-selection capabilities 
- Updated `layout-extract` command to support user multi-selection of layout concepts, allowing for multiple layout templates to be generated based on user preferences.
- Revised argument hints and output structures to reflect changes in selection handling and output file formats.
- Enhanced user interaction by enabling multi-select options in both layout and style extraction phases.
- Streamlined the generation of layout templates and design systems to accommodate multiple selected variants, improving flexibility and user experience.
- Adjusted validation and output verification processes to ensure consistency with new multi-selection features.
 2025-11-08 23:23:06 +08:00
catlog22
7269f20f57 refactor: reorganize ui-design-agent with 3 task patterns covering 6 task types 
Restructure agent documentation to avoid confusion and clarify responsibilities.
All 6 task types now organized into 3 clear patterns with shared standards.

## New Structure

**Task Patterns** (replaces Core Capabilities):
- Pattern 1: Option Generation (2 tasks)
  * DESIGN_DIRECTION_GENERATION_TASK
  * LAYOUT_CONCEPT_GENERATION_TASK

- Pattern 2: System Generation (3 tasks)
  * DESIGN_SYSTEM_GENERATION_TASK
  * LAYOUT_TEMPLATE_GENERATION_TASK
  * ANIMATION_TOKEN_GENERATION_TASK

- Pattern 3: Assembly (1 task)
  * LAYOUT_STYLE_ASSEMBLY

Each pattern documents:
- Purpose and autonomy level
- Task types covered
- Common process flow
- Task-specific inputs/outputs
- Key principles

## Benefits

1. **Complete Coverage**: All 6 task types explicitly documented
2. **Clear Organization**: Tasks grouped by similar characteristics
3. **Reduced Duplication**: Shared design standards and execution principles
4. **Pattern Recognition**: Agent knows which rules apply per task type
5. **Maintainability**: Single agent easier to maintain than multiple agents

## Updated Sections

- **Task Patterns**: New section replacing fragmented Core Capabilities
- **Execution Flow**: Generic pattern-based flow (was task-specific)
- **Core Execution Principles**: Simplified with pattern-specific autonomy levels
- **Key Reminders**: Updated to reference patterns, removed external invocation terms

## Verification

✅ Pattern 1 covers: DESIGN_DIRECTION_GENERATION, LAYOUT_CONCEPT_GENERATION
✅ Pattern 2 covers: DESIGN_SYSTEM_GENERATION, LAYOUT_TEMPLATE_GENERATION, ANIMATION_TOKEN_GENERATION
✅ Pattern 3 covers: LAYOUT_STYLE_ASSEMBLY

All commands (style-extract, layout-extract, animation-extract, generate) now properly supported.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 21:20:23 +08:00
catlog22
3199b91255 refactor: remove external invocation references from ui-design-agent 
Agent should focus on task execution, not who invokes it. Remove all
references to orchestrator commands and external callers.

Changes:
1. **Agent description** (line 19):
   - Before: "invoked by orchestrator commands (e.g., generate.md)"
   - After: Focus on autonomous execution

2. **Core Capabilities** (line 25):
   - Removed: "Invoked by: generate.md Phase 2"
   - Agent doesn't need to know its caller

3. **Execution Process** (line 250):
   - Before: "When invoked by orchestrator command"
   - After: "Standard execution flow for design generation tasks"

4. **Task prompt terminology** (line 259):
   - Changed: "orchestrator prompt" → "task prompt"

5. **Invocation Model → Task Responsibilities** (lines 295-305):
   - Before: "You are invoked by orchestrator commands..."
   - After: Focus on task responsibilities and expected output

6. **Execution Principles** (lines 310, 315):
   - Changed: "orchestrator command" → "task prompt"
   - Changed: "Each invocation" → "Each task"

7. **Performance Optimization → Generation Approach** (lines 342-348):
   - Removed: Two-layer architecture with orchestrator responsibility
   - Added: Single-pass assembly focus (matches current implementation)

8. **Scope & Boundaries** (line 359):
   - Simplified "NOT Your Responsibilities" to "Out of Scope"
   - Removed: workflow orchestration, task scheduling references
   - Focus on what agent does, not external workflow

9. **Path Handling** (lines 423-426):
   - Changed: "Orchestrator provides" → "Task prompts provide"
   - Changed: "Agent uses" → "Use" (more direct)

Result: Agent documentation now focuses on task execution without
references to external callers or orchestration.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 21:12:06 +08:00
catlog22
e20604bb21 refactor: align ui-design-agent.md with current generate.md implementation 
Remove obsolete content and update documentation to match actual workflow:

1. **Remove consolidate.md references**:
   - Updated agent invocation description (line 19)
   - Replaced "Invocation Model" section (lines 296-308)
   - consolidate.md doesn't exist in current workflow

2. **Replace obsolete Core Capabilities section** (lines 21-101):
   - Removed outdated task definitions:
     * Design Token Synthesis (referenced consolidate.md)
     * Layout Strategy Generation (referenced consolidate.md)
     * Obsolete UI Prototype Generation with CSS placeholders
     * Consistency Validation (no longer used)
   - Added correct "Layout & Style Assembly" documentation matching generate.md:
     * Task type: [LAYOUT_STYLE_ASSEMBLY]
     * Direct CSS reference: <link href="{target}-style-{style_id}-layout-{layout_id}.css">
     * Self-contained CSS architecture (no placeholders)
     * Assembly process matching generate.md lines 130-174

3. **Remove CSS placeholder instructions**:
   - Removed {{STRUCTURAL_CSS}} and {{TOKEN_CSS}} placeholder pattern
   - These placeholders are NOT used in current implementation
   - Current system uses direct CSS file references with resolved var() values

Key improvements:
- Accurate documentation of current [LAYOUT_STYLE_ASSEMBLY] task
- Correct CSS reference pattern matching generate.md:134
- Removed all references to non-existent consolidate.md
- Self-contained CSS architecture properly documented

Verified consistency with generate.md implementation (lines 130-174).

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 21:07:21 +08:00
catlog22
1fb5b3cbe9 refactor: standardize UI design workflow folder naming and add absolute path conversion 
Unified folder naming format across all UI design commands:
- Session mode: .workflow/WFS-{session}/design-run-YYYYMMDD-RANDOM
- Standalone mode: .workflow/.design/design-run-YYYYMMDD-RANDOM

Key changes:
- Standardized run directory naming to design-run-* format
- Added absolute path conversion for all base_path variables
- Updated path discovery patterns from design-* to design-run-*
- Maintained backward compatibility for existing directory discovery

Modified commands (10 files):
- explore-auto.md, imitate-auto.md: Unified standalone path format
- explore-layers.md: Changed from design-layers-* to design-run-*
- capture.md: Added design- prefix to standalone mode
- animation-extract.md, style-extract.md, layout-extract.md,
  generate.md, batch-generate.md: Added absolute path conversion
- update.md: Updated path discovery pattern

Technical improvements:
- Eliminates path ambiguity between command and agent execution contexts
- Ensures all file operations use absolute paths for reliability
- Provides consistent directory structure across workflows

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 20:52:10 +08:00
catlog22
a8ab192c72 refactor: remove Related Commands section from workflow tool commands 
Only orchestrator commands (plan, execute, resume, test-gen, test-fix-gen,
tdd-plan) retain Related Commands section to document workflow phases.
Tool commands (conflict-resolution, task-generate-tdd, test-task-generate,
test-concept-enhanced, test-context-gather, tdd-coverage-analysis) have
Related Commands removed to reduce documentation redundancy.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 17:55:55 +08:00
catlog22
b62b42e9f4 feat: migrate test-task-generate to agent-driven architecture 
- Refactor test-task-generate.md to use action-planning-agent
- Add two-phase execution flow (Discovery → Agent Execution)
- Integrate Memory-First principle and MCP tool enhancements
- Support both agent-mode (default) and cli-execute-mode
- Add test-specific context package with TEST_ANALYSIS_RESULTS.md
- Align with task-generate-agent.md architecture
- Remove 556 lines of redundant old content (Phase 1-4 old structure)
- Update test-gen.md and test-fix-gen.md to reflect agent-driven changes

Changes include:
- Core Philosophy with agent-driven principles
- Agent Context Package structure for test sessions
- Discovery Actions for test context loading
- Agent Invocation with test-specific requirements
- Test Task Structure Reference
- Updated Integration & Usage sections
- Enhanced Related Commands documentation

Now test task generation uses autonomous agent planning with MCP enhancements for better test coverage analysis and generation.

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.6.2 		2025-11-08 17:23:55 +08:00
catlog22
52fce757f8 refactor: update tdd-plan to use --cli-execute parameter 
- Change --agent flag to --cli-execute for consistency
- Make Agent Mode the default execution mode
- Update CLI Mode to use --cli-execute flag
- Align with agent-driven task generation architecture
- Update Phase 5 command documentation
- Update Related Commands section

This completes the migration to agent-driven architecture for both /workflow:plan and /workflow:tdd-plan commands.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 17:17:09 +08:00
catlog22
c12f6b888a feat: migrate task-generate-tdd to agent-driven architecture 
- Refactor task-generate-tdd.md to use action-planning-agent
- Add two-phase execution flow (Discovery → Agent Execution)
- Integrate Memory-First principle and MCP tool enhancements
- Support both agent-mode (default) and cli-execute-mode
- Change --agent flag to --cli-execute for consistency
- Add TDD-specific context package with test coverage integration
- Align with task-generate-agent.md architecture

Now both /workflow:plan and /workflow:tdd-plan use agent-driven task generation for autonomous planning and execution.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 17:11:17 +08:00
catlog22
47667b8360 refactor: streamline task generation workflow architecture 
- Remove 150+ lines of duplicate content from task-generate-agent.md
- Implement reference-based design following Content Uniqueness Rules
- Simplify plan.md to use task-generate-agent exclusively
- Remove --agent parameter (agent mode is now default)
- Improve separation of concerns between command and agent layers

Changes:
- task-generate-agent.md: Replace detailed specs with references to action-planning-agent.md
- plan.md: Remove task-generate command, unify on agent-driven approach

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-08 17:03:18 +08:00
catlog22
915eb396e7 feat: enhance quantification requirements across workflow tools 
Enhanced task generation with mandatory quantification standards to eliminate ambiguity:

- Add Quantification Requirements section to all task generation commands
- Enforce explicit counts and enumerations in requirements, acceptance criteria, and modification points
- Standardize formats: "Implement N items: [list]" vs vague "implement features"
- Include verification commands for measurable acceptance criteria
- Simplify documentation by removing verbose examples while preserving all key information

Changes:
- task-generate.md: Add quantification section, streamline Task JSON schema, remove CLI examples
- task-generate-agent.md: Add quantification rules, improve template selection clarity
- task-generate-tdd.md: Add TDD-specific quantification formats for Red-Green-Refactor phases
- action-planning-agent.md: Add quantification requirements with validation checklist and updated examples

Impact:
- Reduces task documentation from ~900 lines to ~600 lines (33% reduction)
- All requirements now require explicit counts: "5 files", "15 test cases", ">=85% coverage"
- Acceptance criteria must include verification commands
- Modification points must specify exact targets with line numbers

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.5.2 		2025-11-08 15:02:07 +08:00
catlog22
1cb83c07e0 feat: 强化任务生成命令，新增量化要求以消除模糊性 2025-11-08 14:39:45 +08:00
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