Commit Graph

459 Commits

Author SHA1 Message Date
catlog22
07775cda30 fix: correct spelling of 'cli-execution-agent' in documentation 2025-11-24 21:46:08 +08:00
catlog22
3acf6fcba8 docs: enhance test task generation documentation with existing test infrastructure and framework usage 2025-11-24 21:14:32 +08:00
catlog22
f798dd4172 refactor: consolidate workflow commands and add UI design templates
1. Remove deprecated task-generate.md
   - Replaced by task-generate-agent.md in previous commits
   - Clean up duplicate command documentation

2. Update ui-design-agent.md
   - Refine agent specifications and workflow integration

3. Add UI design template files
   - Create ~/.claude/workflows/cli-templates/ui-design/systems/
   - Add animation-tokens.json for animation and transition patterns
   - Add design-tokens.json for color, typography, spacing tokens
   - Add layout-templates.json for structural layout patterns
   - Modular design system management

4. Update analyze_commands.py
   - Enhance command analysis capabilities
   - Improve metadata extraction

Key improvements:
- Remove duplicate/deprecated documentation
- Modular UI design template management
- Better workflow command organization
2025-11-24 19:36:33 +08:00
catlog22
aabc6294f4 refactor: optimize test workflow commands and extract templates
1. Optimize test-task-generate.md structure
   - Simplify from 417 lines to 217 lines (~48% reduction)
   - Reference task-generate-agent.md structure for consistency
   - Enhance agent prompt with clear specifications:
     * Explicit agent configuration reference
     * Detailed TEST_ANALYSIS_RESULTS.md integration mapping
     * Complete test-fix cycle configuration
     * Clear task structure requirements (IMPL-001 test-gen, IMPL-002+ test-fix)
   - Fix format errors (remove nested code blocks in agent prompt)
   - Emphasize "planning only" nature (does NOT execute tests)

2. Refactor test-concept-enhanced.md to use cli-execute-agent
   - Simplify from 463 lines to 142 lines (~69% reduction)
   - Change from direct Gemini execution to cli-execute-agent delegation
   - Extract Gemini prompt template to separate file:
     * Create ~/.claude/workflows/cli-templates/prompts/test/test-concept-analysis.txt
     * Use $(cat ~/.claude/...) pattern for template reference
   - Clarify responsibility separation:
     * Command: Workflow coordination and validation
     * Agent: Execute Gemini analysis and generate outputs
   - Agent generates both gemini-test-analysis.md and TEST_ANALYSIS_RESULTS.md
   - Remove verbose embedded prompts and output format descriptions

Key improvements:
- Modular template management for easier maintenance
- Clear command vs agent responsibility separation
- Consistent documentation structure across workflow commands
- Enhanced agent prompts ensure correct output generation
- Use ~/.claude paths for installed workflow location
2025-11-24 19:33:02 +08:00
catlog22
adbb2070bb docs: update action-planning-agent and task-generate-agent documentation to clarify loading strategies and steps 2025-11-24 10:47:37 +08:00
catlog22
3c9cf3a677 docs: enhance action-planning-agent and task-generate-agent documentation with progressive loading strategy and smart artifact selection 2025-11-24 10:36:06 +08:00
catlog22
ff808ed539 docs: update task-generate-agent documentation for clarity on planning document generation and execution phases 2025-11-23 22:57:43 +08:00
catlog22
99a5c75b13 docs: enhance task generation agent documentation with progressive loading strategy and smart artifact selection 2025-11-23 22:44:11 +08:00
catlog22
7453987cfe Add documentation for new CLI commands: docs-related-cli and lite-fix
- Implemented the `docs-related-cli` command for context-aware documentation generation and update for changed modules using CLI execution with tool fallback.
- Introduced the `lite-fix` command for lightweight bug diagnosis and fix workflow, featuring intelligent severity assessment and optional hotfix mode for production incidents.
2025-11-23 22:18:39 +08:00
catlog22
4bb4bdc124 refactor: migrate agents to path-based context loading
- Update action-planning-agent and task-generate-agent to load context
  via file paths instead of embedded context packages
- Streamline test-cycle-execute workflow execution
- Remove redundant content from conflict-resolution and context-gather
- Update SKILL.md and tdd-plan documentation
2025-11-23 22:06:13 +08:00
catlog22
3915f7cb35 docs: update execute.md to clarify task loading and resume mode behavior 2025-11-23 21:18:30 +08:00
catlog22
657af628fd refactor: remove performance metrics and context management details from execute.md 2025-11-23 21:13:49 +08:00
catlog22
b649360cd6 docs: update agent documentation for context package and execution responsibilities 2025-11-23 21:04:25 +08:00
catlog22
20aa0f3a0b feat: add agent-task execution rules to ensure one agent per task JSON 2025-11-23 20:37:03 +08:00
catlog22
0207677857 feat: enhance lite-fix workflow with session folder setup and artifact management 2025-11-23 20:05:34 +08:00
catlog22
c0c894ced1 feat: enhance action-planning-agent task JSON schema definition
- Add missing top-level field: context_package_path
- Add missing context fields: parent, inherited, shared_context
- Add meta fields for parallelization: execution_group, context_signature
- Fix status enumeration: pending|active|completed|blocked|container
- Fix meta.type enumeration: distinguish test-gen from test-fix
- Expand meta.agent options: add action-planning-agent, test-fix-agent, universal-executor
- Enhance artifacts structure: add source, usage, contains fields
- Restructure schema presentation into 4 clear sections
- Add practical pre_analysis examples with CLI bash search commands
- Emphasize quantification requirements for requirements/acceptance fields

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 19:24:46 +08:00
catlog22
7517f4f8ec docs: clarify manifest.json location in plan.md Phase 1
Add explicit note in Phase 1 validation to prevent main Claude from
incorrectly looking for manifest.json in .workflow/active/WFS-xxx/.

manifest.json only exists in .workflow/archives/ (for archived sessions).
Active sessions only have workflow-session.json (metadata).

This prevents confusion during plan execution before agent invocation.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 13:44:02 +08:00
catlog22
0416b23186 feat: add context-package.json sync to synthesis and design-sync workflows
Add Phase 6 to both synthesis.md and design-sync.md to automatically
update context-package.json when artifacts are modified, preventing
stale cache issues when transitioning to /workflow:plan.

Changes:
- synthesis.md: Add Phase 6 to sync updated role analyses to context-package
- design-sync.md: Add Phase 5 to sync design system refs + role analyses

This ensures:
- synthesis → plan: context-package reflects synthesis enhancements
- ui-design → plan: context-package includes design system references
- No manual context-gather re-run needed after artifact updates

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 12:53:08 +08:00
catlog22
4272ca9ebd Add CLI commands for full and related documentation generation
- Implemented `/memory:docs-full-cli` for comprehensive project documentation generation using CLI execution with batched agents and tool fallback.
- Introduced `/memory:docs-related-cli` to generate/update documentation for git-changed modules, optimizing for efficiency with direct parallel execution for fewer modules and agent batch processing for larger sets.
- Defined execution flows, strategies, and error handling for both commands, ensuring robust documentation processes.
2025-11-23 11:27:23 +08:00
catlog22
65a204a563 fix: enforce synchronous bash execution in memory update workflows
Explicitly set run_in_background: false for all Bash commands in update-full and update-related workflows to prevent unwanted background execution. This ensures synchronous execution without requiring BashOutput polling.

Changes:
- Phase 1-4: Add run_in_background: false to all Bash calls
- Simplify code examples and remove redundant explanations
- Update both direct execution and agent batch execution patterns

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 10:23:30 +08:00
catlog22
4f533f6fd5 feat(lite-execute): intelligent task grouping with parallel/sequential execution
Major improvements:
- Implement dependency-aware task grouping algorithm
  * Same file modifications → sequential batch
  * Different files + no dependencies → parallel batch
  * Keyword-based dependency inference (use/integrate/call/import)
  * Batch limits: Agent 7 tasks, CLI 4 tasks

- Add parallel execution strategy
  * All parallel batches launch concurrently (single Claude message)
  * Sequential batches execute in order
  * No concurrency limit for CLI tools
  * Execution flow: parallel-first → sequential-after

- Enhance code review with task.json acceptance criteria
  * Unified review template for all tools (Gemini/Qwen/Codex/Agent)
  * task.json in CONTEXT field for CLI tools
  * Explicit acceptance criteria verification

- Clarify execution requirements
  * Remove ambiguous strategy instructions
  * Add explicit "MUST complete ALL tasks" requirement
  * Prevent CLI tools from partial execution misunderstanding

- Simplify documentation (~260 lines reduced)
  * Remove redundant examples and explanations
  * Keep core algorithm logic with inline comments
  * Eliminate duplicate descriptions across sections

Breaking changes: None (backward compatible)
2025-11-22 21:05:43 +08:00
catlog22
530c348e95 feat: enhance task execution with intelligent grouping and dependency analysis 2025-11-22 20:57:16 +08:00
catlog22
a98b26b111 feat: add session folder structure for lite-plan artifacts
- Create dedicated session folder (.workflow/.lite-plan/{task-slug}-{timestamp}/)
  for each lite-plan execution to organize all planning artifacts
- Always export task.json (removed optional export question from Phase 4)
- Save exploration.json, plan.json, and task.json to session folder
- Add session artifact paths to executionContext for lite-execute delegation
- Update lite-execute to use artifact file paths for CLI/agent context
- Enable CLI tools (Gemini/Qwen/Codex) and agents to access detailed
  planning context via file references

Benefits:
- Clean separation between different task executions
- All artifacts automatically saved for reusability
- Enhanced context available for execution phase
- Natural audit trail of planning sessions
2025-11-22 20:32:01 +08:00
catlog22
9f7e33cbde Merge branch 'main' of https://github.com/catlog22/Claude-Code-Workflow 2025-11-22 20:22:21 +08:00
Claude
b8889d99c9 refactor: simplify session selection logic expression
- Condense Case A/B/C headers for clarity
- Merge bash if-else into single line using && ||
- Combine steps 1-4 in Case C into compact flow
- Remove redundant explanations while keeping key info
- Reduce from 64 lines to 39 lines (39% reduction)
2025-11-20 12:12:56 +00:00
Claude
a79a3221ce fix: enhance workflow execute session selection with user interaction
- Add detailed session discovery logic with 3 cases (none, single, multiple)
- Implement AskUserQuestion for multiple active sessions
- Display rich session metadata (project name, task progress, completion %)
- Support flexible user input (session number, full ID, or partial ID)
- Maintain backward compatibility for single-session scenarios
- Improve user experience with clear confirmation messages

This minimal change addresses session conflict issues without complex
locking mechanisms, focusing on explicit user choice when ambiguity exists.
2025-11-20 12:08:35 +00:00
catlog22
8d828e8762 Merge branch 'main' of https://github.com/catlog22/Claude-Code-Workflow 2025-11-20 19:44:31 +08:00
Claude
229a9867e6 docs: remove URL support from UI workflow commands
Removed all URL-related parameters and functionality from UI design commands
as they are no longer supported. All commands now only accept local files.

Changes:
- style-extract.md: Removed --urls parameter and all URL mode logic
- layout-extract.md: Removed --urls parameter and DOM extraction via URLs
- COMMAND_SPEC.md: Deleted capture and explore-layers commands, updated syntax

Affected commands:
- /workflow:ui-design:style-extract: Only accepts --images and --prompt
- /workflow:ui-design:layout-extract: Only accepts --images and --prompt
- Removed: /workflow:ui-design:capture (command deleted)
- Removed: /workflow:ui-design:explore-layers (command deleted)

All UI workflow commands now require manual input of local resources
(images, code files, HTML, CSS, JS) instead of fetching from URLs.
2025-11-20 11:35:00 +00:00
catlog22
196951ff4f Merge pull request #19 from catlog22/claude/analyze-planning-phase-01LgSNX3QxNDKmaUGpwn11gc
Analyze planning phase for overlooked scenarios
2025-11-20 19:07:20 +08:00
catlog22
07caf20e0d Merge branch 'main' of https://github.com/catlog22/Claude-Code-Workflow 2025-11-20 18:51:24 +08:00
Claude
1e9ca574ed refactor: simplify lite-fix command modes and parameters
Reduced complexity from 3 modes to 2 modes with intelligent adaptation:

Before (complex):
- 3 modes: Regular, Critical, Hotfix
- 3 parameters: --critical, --hotfix, --incident

After (simplified):
- 2 modes: Default (auto-adaptive), Hotfix
- 1 parameter: --hotfix

Key improvements:
- Default mode intelligently adapts based on risk score (Phase 2)
- Automatic workflow adjustment (diagnosis depth, test strategy, review)
- Risk score thresholds determine process complexity automatically
- Removed manual Critical mode selection (now auto-detected)
- Removed --incident parameter (can include in bug description)

Adaptive behavior:
- risk_score <3.0: Full test suite, comprehensive diagnosis
- 3.0-5.0: Focused integration tests, moderate diagnosis
- 5.0-8.0: Smoke+critical tests, focused diagnosis
- ≥8.0: Smoke tests only, minimal diagnosis

Line count: 652 lines (reduced from 707)
Matches lite-plan simplicity while maintaining full functionality
2025-11-20 10:44:20 +00:00
catlog22
d0ceb835b5 Merge pull request #25 from catlog22/claude/add-document-analysis-template-01T8qhUKLCGSev5RunZyxBwp
Add document analysis prompt template
2025-11-20 18:43:05 +08:00
Claude
837bee79c7 feat: add document analysis template for technical documents and papers
Add new CLI mode for systematic technical document analysis with:
- CLI command: /cli:mode:document-analysis for Gemini/Qwen/Codex
- Comprehensive analysis template with 6-phase protocol
- Support for README, API docs, research papers, specifications, tutorials
- Evidence-based analysis with pre-planning and self-critique requirements
- Precise language constraints and structured output format

Template features:
- Pre-analysis planning phase for approach definition
- Multi-phase analysis: assessment, extraction, critical analysis, synthesis
- Self-critique requirement before final output
- Mandatory section references and evidence citations
- Output length control proportional to document size
2025-11-20 10:05:09 +00:00
Claude
842ed624e8 fix: use ~/.claude path format for template reference
Update template path from .claude/templates to ~/.claude/templates
to follow project convention for path references.
2025-11-20 09:54:41 +00:00
Claude
4693527a8e feat: add HTML dashboard generation to workflow status command
Add --dashboard parameter to /workflow:status command that generates
an interactive HTML task board displaying active and archived sessions.

Features:
- Responsive layout with modern CSS design
- Real-time statistics for sessions and tasks
- Task cards with status indicators (pending/in_progress/completed)
- Progress bars for each session
- Search and filter functionality
- Dark/light theme toggle
- Separate panels for active and archived sessions

Implementation:
- Added Dashboard Mode section to .claude/commands/workflow/status.md
- Created HTML template at .claude/templates/workflow-dashboard.html
- Template uses data injection pattern with {{WORKFLOW_DATA}} placeholder
- Generated dashboard saved to .workflow/dashboard.html

Usage:
  /workflow:status --dashboard

The dashboard provides a visual overview of all workflow sessions
and their tasks, making it easier to track project progress.
2025-11-20 09:49:54 +00:00
Claude
5f0dab409b refactor: convert lite-fix.md to full English
Changed all Chinese text to English for consistency:
- Table headers: "适用场景" → "Use Case", "流程特点" → "Workflow Characteristics"
- Example comments: Chinese descriptions → English descriptions
- All mixed language content now fully in English

Maintains same structure and functionality (707 lines).
2025-11-20 09:49:05 +00:00
Claude
c679253c30 refactor: streamline lite-fix.md to match lite-plan's concise style (707 lines)
Reduced from 1700+ lines to 707 lines while preserving core functionality:

Preserved:
- Complete 6-phase execution flow
- Three severity modes (Regular/Critical/Hotfix)
- Data structure definitions
- Best practices and quality gates
- Related commands and comparisons

Removed/Condensed:
- Redundant examples (kept 3 essential ones)
- Verbose implementation details
- Duplicate explanations
- Extended discussion sections

Format matches lite-plan.md (667 lines) for consistency.
Detailed design rationale remains in LITE_FIX_DESIGN.md.
2025-11-20 09:41:32 +00:00
Claude
ca9653c2e6 refactor: rename phase2-analysis.json to doc-planning-data.json
Optimize the Phase 2 output filename in /memory:docs command for better clarity:
- Old: phase2-analysis.json (generic, non-descriptive)
- New: doc-planning-data.json (clear purpose, self-documenting)

The new name better reflects that this file contains comprehensive
documentation planning data including folder analysis, grouping
information, existing docs, and statistics.

Updated all references in command documentation and skill guides.
2025-11-20 09:22:32 +00:00
Claude
38f2355573 feat: add lite-fix command design for bug diagnosis and emergency fixes
Introduces /workflow:lite-fix - a lightweight bug fixing workflow optimized
for rapid diagnosis, targeted fixes, and streamlined verification.

Command Design:
- Three severity modes: Regular (2-4h), Critical (30-60min), Hotfix (15-30min)
- Six-phase execution: Diagnosis → Impact → Planning → Verification → Confirmation → Execution
- Intelligent code search: cli-explore-agent (regular) → direct search (critical) → minimal (hotfix)
- Risk-aware verification: Full test suite → Focused tests → Smoke tests

Key Features:
- Structured root cause analysis (file:line, reproduction steps, blame info)
- Quantitative impact assessment (risk score 0-10, user/business impact)
- Multi-strategy fix planning (immediate patch vs comprehensive refactor)
- Adaptive branch strategy (feature branch vs hotfix branch from production tag)
- Automatic follow-up task generation for hotfixes (tech debt management)
- Real-time deployment monitoring with auto-rollback triggers

Integration:
- Complements /workflow:lite-plan (fix vs feature development)
- Reuses /workflow:lite-execute for execution layer
- Integrates with /cli:mode:bug-diagnosis for preliminary analysis
- Escalation path to /workflow:plan for complex refactors

Design Documents:
- .claude/commands/workflow/lite-fix.md - Complete command specification
- LITE_FIX_DESIGN.md - Architecture design and decision records

Addresses: PLANNING_GAP_ANALYSIS.md Scenario #8 (Emergency Fix)

Expected Impact:
- Reduce bug fix time by 50-70%
- Improve diagnosis accuracy to 85%+
- Reduce production hotfix risks
- Systematize technical debt from quick fixes
2025-11-20 09:21:26 +00:00
catlog22
d7bee9bdf2 docs: clarify path parameter description in /memory:docs command
Improve the path parameter documentation to eliminate ambiguity:
- Change "Target directory" to "Source directory to analyze"
- Explicitly state documentation is generated in .workflow/docs/{project_name}/ at workspace root
- Emphasize docs are NOT created within the source path itself
- Add concrete example showing path mirroring behavior

This resolves potential confusion about where documentation files are created.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-20 15:48:06 +08:00
catlog22
2a63ab5e0a Merge pull request #11 from catlog22/claude/refactor-task-workflow-01WBDUE6UgN74q4JhmwDJ6c1
Refactor task replan into workflow structure
2025-11-20 12:34:31 +08:00
Claude
46527c5b9a docs: remove Core Principles sections from replan commands
Remove unnecessary Core Principles sections that reference task-core.md
and workflow-architecture.md from both workflow:replan and task:replan
documentation to align with execute.md style and maintain simplicity.
2025-11-20 04:32:00 +00:00
Claude
b9e893245b refactor(workflow): simplify workflow:replan documentation
## Changes

### Documentation Simplification
- Removed version information and comparison tables
- Removed "Migration from task:replan" section
- Removed "Related Commands" section
- Removed redundant "Implementation Notes" section
- Streamlined examples to essential use cases only

### Followed execute.md Style
- Clean, focused structure
- Direct entry into core functionality
- Clear phase-based execution lifecycle
- Concise error handling
- Essential file structure reference

### Maintained Core Content
- Overview with core capabilities
- Operation modes (Session/Task)
- 6-phase execution lifecycle
- Interactive clarification questions
- TodoWrite progress tracking
- Error handling examples
- Practical usage examples

The documentation now follows the established pattern from execute.md
and other workflow commands, providing essential information without
redundant sections or comparisons.
2025-11-20 03:19:47 +00:00
Claude
d96a8a06a0 feat(workflow): add workflow:replan command with session-level replanning support
## Changes

### New Command: workflow:replan
- Created `.claude/commands/workflow/replan.md` with comprehensive session-level replanning
- Supports dual modes: session-wide and task-specific replanning
- Interactive boundary clarification using guided questioning
- Updates multiple artifacts: IMPL_PLAN.md, TODO_LIST.md, task JSONs, session metadata
- Comprehensive backup management with restore capability

### Key Features
1. **Interactive Clarification**: Guided questions to define modification scope
   - Modification scope (tasks only, plan update, task restructure, comprehensive)
   - Affected modules detection
   - Task change types (add, remove, merge, split, update)
   - Dependency relationship updates

2. **Session-Aware Operations**:
   - Auto-detects active sessions from `.workflow/active/`
   - Updates all session artifacts consistently
   - Maintains backup history in `.process/backup/replan-{timestamp}/`

3. **Comprehensive Artifact Updates**:
   - IMPL_PLAN.md section modifications
   - TODO_LIST.md task list updates
   - Task JSON files (requirements, implementation, dependencies)
   - Session metadata tracking

4. **Impact Analysis**: Automatically determines affected files and operations

### Deprecation
- Added deprecation notice to `/task:replan` in both command and reference files
- Updated `COMMAND_REFERENCE.md` to:
  - Add workflow:replan to Core Workflow section
  - Mark task:replan as deprecated with migration guidance

### Migration Path
- Old: `/task:replan IMPL-1 "changes"`
- New: `/workflow:replan IMPL-1 "changes"`

### Files Modified
- `.claude/commands/task/replan.md`: Added deprecation notice
- `.claude/commands/workflow/replan.md`: New command implementation
- `.claude/skills/command-guide/reference/commands/task/replan.md`: Deprecation notice
- `.claude/skills/command-guide/reference/commands/workflow/replan.md`: Reference documentation
- `COMMAND_REFERENCE.md`: Updated command listings

This change enhances workflow replanning capabilities by providing interactive,
session-aware modifications that maintain consistency across all workflow artifacts.
2025-11-20 03:11:28 +00:00
Claude
c56bf68d87 Remove version evolution content from tdd-plan.md
Removed 104 lines of version history and enhancement documentation (lines 420-523):
- TDD Workflow Enhancements section
- Key Improvements (adopted features from test-gen and plan workflows)
- Workflow Comparison table (Previous vs Current)
- Migration Notes and backward compatibility info
- Configuration examples

This content represented ~19% of the file and was historical/evolutionary
information rather than core command functionality. Focuses the documentation
on what the command does, not how it evolved.

Improves task focus and documentation clarity as identified in audit report.
2025-11-20 02:57:21 +00:00
catlog22
292dc113e3 refactor(workflow): complete migration from .workflow/sessions/ to .workflow/active/ directory structure
Update all command files to use the new standardized directory structure:
- Active sessions: .workflow/active/WFS-{session}/
- Archived sessions: .workflow/archives/WFS-{session}/

Changes:
- Updated workflow-architecture.md with new directory structure (active/ not sessions/)
- Fixed 31 path references across 12 command files
- Verified compliance across all 73 command files using parallel agent checks
- Confirmed directory naming: active/ (adjective, no plural) + archives/ (noun plural)

Files modified:
- .claude/workflows/workflow-architecture.md (directory structure definition)
- .claude/commands/cli/*.md (8 files: analyze, chat, codex-execute, discuss-plan, execute, mode/*)
- .claude/commands/memory/docs.md (4 path fixes)
- .claude/commands/task/*.md (execute, replan)

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-20 10:25:28 +08:00
catlog22
c3818fdb79 Refactor workflow file paths from .workflow/sessions/ to .workflow/active/ for improved session management and consistency across commands. Updated documentation and command references to reflect the new directory structure, ensuring all relevant commands and outputs are correctly aligned with the active session model. 2025-11-20 09:40:58 +08:00
catlog22
9f322e0f34 refactor(workflow): simplify explore-auto command and remove Phase 11 duplication
- Simplify Phase 1-3: Use unified principles (Detect→Classify→Store) to avoid string concatenation and escaping
- Reduce Phase 1-3 from 70+ lines to 30 lines with clear priority chains
- Remove Phase 11 (preview generation): Delegated to generate.md command to eliminate duplication
- Update workflow from 11 phases to 10 phases
- Convert all content to English for internationalization
- Update TodoWrite pattern from 5 tasks to 4 tasks (remove preview generation task)

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-20 09:35:53 +08:00
catlog22
89a61acb71 Refactor workflow output paths to use a standardized sessions directory structure
- Updated output paths in various command files to reflect the new structure: `.workflow/sessions/{session_id}/` instead of `.workflow/{session_id}/`.
- Adjusted documentation and code comments to ensure consistency across all agents and commands.
- Ensured that all references to session-related files are correctly pointing to the new directory format.
2025-11-19 23:04:10 +08:00
catlog22
9b07310d68 refactor(workflow): enhance init command documentation with memory discovery features 2025-11-19 20:46:37 +08:00