catlog22
360f6f79dc
feat: optimize SKILL.md description format for better trigger sensitivity
...
Enhance description generation in Phase 4 Step 3:
- New format emphasizes "Load this SKILL" pattern for improved triggering
- Explicitly covers three key scenarios: analyzing, working with, or learning
- Prioritizes SKILL as primary context source for project understanding
- Added trigger optimization guidance for context retrieval scenarios
Before: "{Function}. Use when {trigger conditions}."
After: "{Project} {core capabilities}. Load this SKILL when analyzing, working with, or learning about {project_name} for comprehensive context."
Example:
"Workflow orchestration system with CLI tools and documentation generation.
Load this SKILL when analyzing, working with, or learning about workflow
management for comprehensive context."
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-03 20:57:09 +08:00
catlog22
152037ad7b
fix: correct relative path in skill-memory SKILL.md template
...
Update documentation path references from ../../ to ../../../:
- From: .claude/skills/{project_name}/SKILL.md
- To: .workflow/docs/{project_name}/
- Correct path depth: ../../../.workflow/docs/
Fixed paths:
- Documentation root reference
- Level 0: README.md link
- Level 2: ARCHITECTURE.md link
- Level 3: EXAMPLES.md link
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-03 20:49:16 +08:00
catlog22
78569a7b75
refactor: eliminate TodoWrite duplication in skill-memory phases
...
Simplify TodoWrite updates in each phase to one-line format, matching auto-parallel.md pattern.
**Changes**:
- Phase 1-4: Replace code block with single line "Mark phase X completed, phase Y in_progress"
- Maintain detailed TodoWrite Pattern section for complete reference
- Remove 32 redundant lines (36 deletions, 4 insertions)
**Before**:
```
**TodoWrite Update**:
```javascript
TodoWrite({todos: [
{"content": "...", "status": "completed"},
{"content": "...", "status": "in_progress"},
...
]})
```
**After**:
```
**TodoWrite**: Mark phase X completed, phase Y in_progress
```
**Benefits**:
- Eliminates duplication between phase updates and TodoWrite Pattern section
- Improves readability with concise phase-level updates
- Maintains complete TodoWrite lifecycle in dedicated pattern section
- Consistent with auto-parallel.md orchestrator pattern
**File size**: 488 lines → 456 lines (-32 lines, -6.6%)
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-03 20:08:03 +08:00
catlog22
7aca88104b
feat: enhance skill-memory auto-continue mechanism with detailed execution flow
...
Optimize TodoWrite auto-continuation pattern based on auto-parallel.md and docs.md best practices.
**Enhanced Auto-Continue Mechanism**:
- Added detailed "Auto-Continue Execution Flow" section with implementation rules
- Enhanced Core Rules with specific auto-continue logic (7 rules → clearer guidelines)
- Added "Completion Criteria" for each phase (validates phase success)
- Added explicit "TodoWrite Update" code blocks at each phase
- Added "After Phase X" auto-continue triggers with "no user input required" emphasis
**Improved Phase Documentation**:
- Phase 1-4: Added completion criteria and validation requirements
- Each phase now has explicit TodoWrite update pattern
- Clear state transitions: completed → in_progress → execute
- Error handling rules for failed phases
**New Sections**:
- "Auto-Continue Execution Flow" - Visual execution sequence diagram
- "Critical Implementation Rules" - 4 key rules for autonomous execution
- Status-driven execution pattern with TodoList checking
- Error handling guidelines (do not continue on failure)
**TodoWrite Pattern Enhancement**:
- Added inline comments explaining each action
- Added "Auto-Continue Logic" explanation
- Shows complete lifecycle from initialize to completion
- Includes FIRST/NEXT/FINAL action annotations
**Benefits**:
- Clear autonomous execution expectations
- No ambiguity about when to continue phases
- Explicit validation criteria for each phase
- Better error handling guidance
- Consistent with auto-parallel.md orchestrator pattern
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-11-03 20:02:44 +08:00
catlog22
bcebd229df
feat: update SKILL.md generation process with intelligent description extraction and streamlined file handling
2025-11-03 17:22:09 +08:00
catlog22
e53a1bf397
feat: add CLI execution mode support to documentation commands and update argument hints
2025-11-03 15:47:18 +08:00
catlog22
b18647353b
feat: enhance documentation generation process with improved structure and quality guidelines
2025-11-03 15:17:37 +08:00
catlog22
cdc0af90ba
feat: add support for 'codex' tool and enhance --regenerate flag handling in skill-memory command
2025-11-03 14:54:10 +08:00
catlog22
507cd696b1
Refactor skill-memory command to streamline documentation generation process
...
- Updated command description and argument hints for clarity.
- Changed the orchestrator role to emphasize its function as a pure orchestrator without task JSON generation.
- Implemented a 4-phase workflow for documentation generation, including auto-continue mechanisms.
- Enhanced argument parsing to include a new mode option for full or partial documentation generation.
- Simplified the output structure and improved validation steps throughout the phases.
- Revised the SKILL.md generation process to include a progressive loading guide and module index.
- Removed unnecessary complexity and reduced code size by approximately 70%.
2025-11-03 14:49:44 +08:00
catlog22
fdba75dd79
Implement feature X to enhance user experience and fix bug Y in module Z
2025-11-03 11:26:37 +08:00
catlog22
cefe6076e2
feat: add skill-memory command for generating SKILL packages with path mirroring
2025-11-03 10:31:18 +08:00
