catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-10 02:24:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: update file naming conventions and restrictions for analysis outputs in multiple agents

Browse Source
This commit is contained in:
catlog22
2025-10-25 13:15:14 +08:00
parent b7db6c86bd
commit 89f22ec3cf
4 changed files with 652 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.claude/commands/workflow/brainstorm/auto-parallel.md
View File

@@ -125,12 +125,17 @@ TOPIC: {user-provided-topic}
## Expected Deliverables
1. **analysis.md**: Comprehensive {role-name} analysis addressing all framework discussion points
- **File Naming**: MUST start with `analysis` prefix (e.g., `analysis.md`, `analysis-1.md`, `analysis-2.md`)
- **FORBIDDEN**: Never use `recommendations.md` or any filename not starting with `analysis`
- **Auto-split if large**: If content >800 lines, split to `analysis-1.md`, `analysis-2.md` (max 3 files: analysis.md, analysis-1.md, analysis-2.md)
- **Content**: Includes both analysis AND recommendations sections within analysis files
2. **Framework Reference**: Include @../guidance-specification.md reference in analysis
3. **User Intent Alignment**: Validate analysis aligns with original user objectives from session_context
## Completion Criteria
- Address each discussion point from guidance-specification.md with {role-name} expertise
- Provide actionable recommendations from {role-name} perspective
- Provide actionable recommendations from {role-name} perspective within analysis files
- All output files MUST start with `analysis` prefix (no recommendations.md or other naming)
- Reference framework document using @ notation for integration
- Update workflow-session.json with completion status
"
@@ -147,7 +152,10 @@ TOPIC: {user-provided-topic}
- guidance-specification.md path
**Validation**:
- Each role creates `.workflow/WFS-{topic}/.brainstorming/{role}/analysis.md`
- Each role creates `.workflow/WFS-{topic}/.brainstorming/{role}/analysis.md` (primary file)
- If content is large (>800 lines), may split to `analysis-1.md`, `analysis-2.md` (max 3 files total)
- **File naming pattern**: ALL files MUST start with `analysis` prefix (use `analysis*.md` for globbing)
- **FORBIDDEN naming**: No `recommendations.md`, `recommendations-*.md`, or any non-`analysis` prefixed files
- All N role analyses completed
**TodoWrite**: Mark all N role agent tasks completed, phase 3 in_progress

26
.claude/commands/workflow/tools/context-gather.md
View File

@@ -60,12 +60,17 @@ Agent-driven intelligent context collector that gathers relevant information fro
### Phase 2: Agent Execution (Context Gathering & Packaging)
**Agent**: context-search-agent
**Documentation**: `.claude/agents/context-search-agent.md`
**Agent Invocation**:
```javascript
Task(
subagent_type="universal-executor",
description="Gather project context and generate context package",
prompt=`
You are executing as the context-search-agent. Follow the complete execution process documented in .claude/agents/context-search-agent.md.
## Execution Context
**Session ID**: WFS-{session-id}
@@ -77,13 +82,15 @@ Task(
### Session Metadata
{session_metadata_content}
### Search Tools
- ripgrep: Available for content search and pattern matching
- find: Available for file discovery
- exa-code: Available for external research
- exa-web: Available for web search
### Search Tools Available
- ripgrep: Content search and pattern matching
- find: File discovery
- exa-code: External research (MCP)
- exa-web: Web search (MCP)
## Phase 2: Context Gathering Task
## Your Mission
Execute the complete context-search-agent workflow documented in .claude/agents/context-search-agent.md. For detailed specifications, refer to the agent documentation which includes:
### Core Responsibilities
1. **Project Structure Analysis**: Execute get_modules_by_depth.sh for architecture overview
@@ -420,3 +427,10 @@ if (!fs.existsSync(sessionPath)) {
- All required fields present and properly formatted
- Agent reports completion status with statistics
## Agent Reference
For complete execution details, refer to the context-search-agent documentation:
- **Location**: `.claude/agents/context-search-agent.md`
- **Capabilities**: Multi-layer discovery, intelligent filtering, dependency analysis, conflict detection
- **Output Format**: Standardized context-package.json with metadata, assets, dependencies, and risk assessment