catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-14 02:42:04 +08:00
Code Issues Packages Projects Releases Wiki Activity
651 Commits 20 Branches 102 Tags
9b07310d68c304b620d18b59696a853ace61470a
Commit Graph

12 Commits

Author SHA1 Message Date
catlog22
19ebb2dc82 fix(workflow): complete path migration and enhance session:complete 
Comprehensive update to eliminate all old path references and implement transactional archival in session:complete.

## Part 1: Complete Path Migration (43 files)

### Files Updated
- action-plan-verify.md
- session/list.md, session/resume.md
- tdd-verify.md, tdd-plan.md, test-*.md
- All brainstorm/*.md files (13 files)
- All tools/*.md files (10 files)
- All ui-design/*.md files (10 files)
- lite-plan.md, lite-execute.md, plan.md

### Path Changes
- `.workflow/.active-*` → `find .workflow/sessions/ -name "WFS-*" -type d`
- `.workflow/WFS-{session}` → `.workflow/sessions/WFS-{session}`
- `.workflow/.archives/` → `.workflow/archives/`
- Removed all marker file operations (touch/rm .active-*)

### Verification
- ✅ 0 references to .active-* markers remain
- ✅ 0 references to direct .workflow/WFS-* paths
- ✅ 0 references to .workflow/.archives/ (dot prefix)

## Part 2: Transactional Archival Enhancement

### session/complete.md - Complete Rewrite

**New Four-Phase Architecture**:

1. **Phase 1: Pre-Archival Preparation**
   - Find active session in .workflow/sessions/
   - Check for existing .archiving marker (resume detection)
   - Create .archiving marker to prevent concurrent operations

2. **Phase 2: Agent Analysis (In-Place)**
   - Agent processes session WHILE STILL in sessions/ directory
   - Pure analysis - no file moves or manifest updates
   - Returns complete metadata package for atomic commit
   - Failure here → session remains active, safe to retry

3. **Phase 3: Atomic Commit**
   - Only executes if Phase 2 succeeds
   - Move session to archives/
   - Update manifest.json
   - Remove .archiving marker
   - All-or-nothing guarantee

4. **Phase 4: Project Registry Update**
   - Extract feature metadata and update project.json

**Key Improvements**:
- **Agent-first, move-second**: Prevents inconsistent states
- **Transactional guarantees**: All-or-nothing file operations
- **Resume capability**: .archiving marker enables safe retry
- **Error recovery**: Comprehensive failure handling documented

**Old Design Flaw (Fixed)**:
- Old: Move first → Agent processes → If agent fails, session moved but metadata incomplete
- New: Agent processes → If success, atomic commit → Guaranteed consistency

## Benefits

1. **Consistency**: All commands use identical path patterns
2. **Robustness**: Transactional archival prevents data loss
3. **Maintainability**: Single source of truth for directory structure
4. **Recoverability**: Failed operations can be safely retried
5. **Alignment**: Closer to OpenSpec's clean three-layer model

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-18 12:39:23 +08:00
catlog22
30071f48e8 refactor(ui-design): streamline output files for animation, layout, and style extraction commands by removing unnecessary guide files 2025-11-11 20:23:46 +08:00
catlog22
78e7e7663b refactor(ui-design): shift from automatic capture to user-driven input model 
Major Changes:
- Remove MCP-based automatic screenshot capture dependency
- Remove automatic code extraction mechanisms
- Shift to user-provided images and prompts as primary input

animation-extract.md:
- Remove MCP chrome-devtools integration
- Change from URL-based to image-based inference
- Use AI analysis of images instead of CSS extraction
- Update parameters: --urls → --images (glob pattern)

explore-auto.md:
- Fix critical parameter passing bug in animation-extract phase
- Add --images and --prompt parameter passing to animation-extract
- Ensure consistent context propagation across all extraction phases

imitate-auto.md:
- Add --refine parameter to all extraction commands (style, animation, layout)
- Add --images parameter passing to animation-extract phase
- Add --prompt parameter passing to animation-extract phase
- Align with refinement-focused design intent

Parameter Transmission Matrix (Fixed):
- style-extract: --images ✓ --prompt ✓ --refine ✓ (imitate only)
- animation-extract: --images ✓ --prompt ✓ --refine ✓ (imitate only)
- layout-extract: --images ✓ --prompt ✓ --refine ✓ (imitate only)

Deprecation Notice:
- capture.md and explore-layers.md will be removed in future versions
- Workflows now rely on user-provided inputs instead of automated capture

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-10 10:29:15 +08:00
catlog22
6a50b714d0 Enhance layout and style extraction commands with dual mode support for exploration and refinement. 
- Updated `layout-extract` command to include a refinement mode (`--refine`) for generating single refined layouts, alongside exploration mode for multiple contrasting variants.
- Added detailed reporting and validation for variants count based on the selected mode.
- Implemented logic to load existing layouts for refinement and generate specific refinement options categorized by density, responsiveness, grid specifics, and component arrangement.
- Updated `style-extract` command similarly to support refinement mode, allowing for detailed adjustments to existing design systems.
- Enhanced user interaction phases to accommodate selection of refinements or design directions based on the active mode.
 2025-11-10 09:49:10 +08:00
catlog22
22b2cecd1f refactor(ui-design): unify ID architecture with design-id parameter 
Replace --base-path with --design-id/--session across all UI design commands to eliminate ambiguity and improve consistency.

Key changes:
- New command: list.md for viewing available design runs
- Unified ID format: design_id = directory_name = "design-run-YYYYMMDD-RANDOM"
- Consistent path resolution: --design-id > --session > auto-detect/create
- Updated 11 commands: explore-auto, imitate-auto, capture, style/layout/animation-extract, generate, update, explore-layers, import-from-code
- Enhanced error handling with /workflow:ui-design:list hints
- Fixed import race condition with cleanup logic in explore-auto

Verified by Gemini: 5.0/5.0 consistency score

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-09 21:14:54 +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
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
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
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
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
80196cc0a0 feat: integrate animation token system into UI workflow 
Fixes critical P0 issue where animation-tokens.json wasn't consumed by the
generate command, breaking the value chain. The animation extraction system
now properly flows through: animation-extract → tokens → generate → prototypes.

Changes:
- Added animation-extract command with hybrid CSS extraction + interactive
  fallback strategy
- Updated generate.md to load and inject animation tokens into prototypes
- Added CSS animation support (custom properties, keyframes, interactions,
  accessibility)
- Integrated animation extraction into explore-auto and imitate-auto workflows

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-17 11:01:22 +08:00