feat: Add intelligent tool selection strategy and simplify plan.md analysis

- Create intelligent-tools.md as strategic guide for tool selection
- Reference intelligent-tools.md from CLAUDE.md for global access
- Add three analysis levels to plan.md (quick/standard/deep)
- Separate tool selection strategy from plan command implementation
- Maintain clear separation of concerns between strategy and execution

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-09-14 20:10:31 +08:00
parent 8a823920bf
commit 845925dffb
3 changed files with 115 additions and 2 deletions

View File

@@ -102,6 +102,31 @@ The command automatically detects input type:
- Updates session state with task references
- Runs project structure analysis to populate paths field
### Project Analysis Options
Three analysis levels available:
```bash
# Quick - Structure only (5 seconds)
/workflow:plan "requirements"
# Standard - Structure + Gemini analysis (30 seconds)
/workflow:plan --analyze "requirements"
# Deep - Structure + Parallel comprehensive analysis (1-2 minutes)
/workflow:plan --deep "requirements"
```
**Analysis Selection**:
- Default: Auto-selects based on project complexity
- Manual: Use flags to override automatic selection
- Strategy: See @~/.claude/workflows/intelligent-tools.md for tool selection principles
**Execution**:
1. Always runs `get_modules_by_depth.sh` for structure
2. Applies selected analysis level
3. Populates task paths automatically
### Task Saturation Assessment
Evaluates whether to merge preparation and execution:

View File

@@ -0,0 +1,87 @@
---
name: intelligent-tools
description: Strategic tool selection guide - references unified tool documentation
type: strategic-guideline
---
# Intelligent Tools Selection Strategy
## Overview
This document provides strategic guidance for selecting the appropriate analysis tool based on task characteristics and project requirements.
## Tool Documentation References
- **Gemini CLI**: @~/.claude/workflows/gemini-unified.md
- **Codex CLI**: @~/.claude/workflows/codex-unified.md
## Tool Characteristics Comparison
### Gemini
- **Strengths**:
- Large context window for analyzing many files simultaneously
- Excellent pattern recognition across modules
- Superior for architectural and structural analysis
- **Optimal Use Cases**:
- Large codebase analysis (>50 files)
- Cross-module pattern detection
- Coding convention analysis
- Refactoring with broad dependencies
### Codex
- **Strengths**:
- Superior mathematical and algorithmic reasoning
- Deeper technical knowledge base
- Better for focused, deep analysis
- **Optimal Use Cases**:
- Complex algorithm analysis
- Security vulnerability assessment
- Performance optimization
- Database schema design
- API protocol specifications
## Strategic Selection Matrix
| Analysis Need | Recommended Tool | Rationale |
|--------------|------------------|-----------|
| Project Architecture | Gemini | Needs broad context across many files |
| Algorithm Optimization | Codex | Requires deep mathematical reasoning |
| Security Analysis | Codex | Leverages deeper security knowledge |
| Code Patterns | Gemini | Pattern recognition across modules |
| Refactoring | Gemini | Needs understanding of all dependencies |
| API Design | Codex | Technical specification expertise |
| Test Coverage | Gemini | Cross-module test understanding |
| Performance Tuning | Codex | Mathematical optimization capabilities |
## Parallel Analysis Strategy
For complex projects requiring both broad context and deep analysis:
```bash
# Use Task agents to run both tools in parallel
Task(subagent_type="general-purpose",
prompt="Use Gemini (see @~/.claude/workflows/gemini-unified.md) for architectural analysis")
+
Task(subagent_type="general-purpose",
prompt="Use Codex (see @~/.claude/workflows/codex-unified.md) for algorithmic analysis")
```
## Implementation Guidelines
1. **Default Selection**: Let project characteristics drive tool choice
2. **Complexity Thresholds**:
- Simple projects (≤50 files): Either tool based on content type
- Medium projects (50-200 files): Gemini for overview, Codex for specifics
- Large projects (>200 files): Parallel analysis with both tools
3. **Content-Based Selection**:
- Mathematical/algorithmic content → Codex
- Architectural/structural content → Gemini
- Mixed content → Both via Task agents
## Usage in Commands
Commands should reference this strategy guide for tool selection decisions.
Specific tool usage syntax and examples are documented in their respective unified guides.
**See also**:
- Gemini detailed usage: @~/.claude/workflows/gemini-unified.md
- Codex detailed usage: @~/.claude/workflows/codex-unified.md

View File

@@ -6,7 +6,8 @@ This document defines project-specific coding standards and development principl
### CLI Tool Context Protocols
For all CLI tool usage, command syntax, and integration guidelines:
- **Gemini (Analysis)**: @~/.claude/workflows/gemini-unified.md
- **Codex (Analysis)**: @~/.claude/workflows/codex-unified.md
- **Codex (Development)**: @~/.claude/workflows/codex-unified.md
- **Tool Selection Strategy**: @~/.claude/workflows/intelligent-tools.md
### Intelligent Context Acquisition
@@ -25,7 +26,7 @@ Bash(codex --full-auto exec "analyze [scope] architecture")
- Identify 3+ existing similar patterns before implementation
- Map dependencies and integration points
- Understand testing framework and coding conventions
- Use Task agents for parallel context gathering when needed
## Philosophy