release: v5.9.8 - Brainstorm workflow improvements and documentation updates

## Changes
- Simplify analysis output strategy to optional modular structure
- Update synthesis/artifacts documentation to use AskUserQuestion tool
- Add modular output strategy for brainstorm analysis
- Simplify clarification deduplication in lite-plan
- Add "Fix, Don't Hide" section to CLAUDE.md guidelines
- Simplify project.json schema by removing unused fields
- Update session ID format in lite-fix/lite-plan workflows
- Add development index to project JSON schema

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-12-03 22:45:04 +08:00
parent 7a61119c55
commit c43a72ef46
18 changed files with 713 additions and 1127 deletions

View File

@@ -98,10 +98,10 @@ Analyze project for workflow initialization and generate .workflow/project.json.
Generate complete project.json with:
- project_name: ${projectName}
- initialized_at: current ISO timestamp
- overview: {description, technology_stack, architecture, key_components, entry_points, metrics}
- overview: {description, technology_stack, architecture, key_components}
- features: ${regenerate ? 'preserve from backup' : '[] (empty)'}
- development_index: ${regenerate ? 'preserve from backup' : '{feature: [], enhancement: [], bugfix: [], refactor: [], docs: []}'}
- statistics: ${regenerate ? 'preserve from backup' : '{total_features: 0, total_sessions: 0, last_updated}'}
- memory_resources: {skills, documentation, module_docs, gaps, last_scanned}
- _metadata: {initialized_by: "cli-explore-agent", analysis_timestamp, analysis_mode}
## Analysis Requirements
@@ -118,23 +118,6 @@ Generate complete project.json with:
- Patterns: singleton, factory, repository
- Key components: 5-10 modules {name, path, description, importance}
**Metrics**:
- total_files: Source files (exclude tests/configs)
- lines_of_code: Use find + wc -l
- module_count: Use ~/.claude/scripts/get_modules_by_depth.sh
- complexity: low | medium | high
**Entry Points**:
- main: index.ts, main.py, main.go
- cli_commands: package.json scripts, Makefile targets
- api_endpoints: HTTP/REST routes (if applicable)
**Memory Resources**:
- skills: Scan .claude/skills/ → [{name, type, path}]
- documentation: Scan .workflow/docs/ → [{name, path, has_readme, has_architecture}]
- module_docs: Find **/CLAUDE.md (exclude node_modules, .git)
- gaps: Identify missing resources
## Execution
1. Structural scan: get_modules_by_depth.sh, find, wc -l
2. Semantic analysis: Gemini for patterns/architecture
@@ -168,17 +151,6 @@ Frameworks: ${projectJson.overview.technology_stack.frameworks.join(', ')}
Style: ${projectJson.overview.architecture.style}
Components: ${projectJson.overview.key_components.length} core modules
### Metrics
Files: ${projectJson.overview.metrics.total_files}
LOC: ${projectJson.overview.metrics.lines_of_code}
Complexity: ${projectJson.overview.metrics.complexity}
### Memory Resources
SKILL Packages: ${projectJson.memory_resources.skills.length}
Documentation: ${projectJson.memory_resources.documentation.length}
Module Docs: ${projectJson.memory_resources.module_docs.length}
Gaps: ${projectJson.memory_resources.gaps.join(', ') || 'none'}
---
Project state: .workflow/project.json
${regenerate ? 'Backup: .workflow/project.json.backup' : ''}

View File

@@ -113,11 +113,6 @@ Patterns: ${overview.architecture.patterns.join(', ')}
**Key Components** (${overview.key_components.length}):
${overview.key_components.map(c => `- ${c.name} (${c.path})\n ${c.description}`).join('\n')}
**Metrics**:
- Files: ${overview.metrics.total_files}
- Lines of Code: ${overview.metrics.lines_of_code}
- Complexity: ${overview.metrics.complexity}
---
` : ''}