mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-12 02:37:45 +08:00
8073549234
## skill-memory.md Optimization - Restructured file from 553 to 534 lines (-19 lines, -3.4%) - Eliminated duplicate content in 3 areas: * Auto-Continue mechanism (3 occurrences → 1) * Execution flow descriptions (2 occurrences → 1) * Phase 4 never-skip notes (2 occurrences → 1) - Merged "TodoWrite Pattern" and "Auto-Continue Execution Flow" into unified "Implementation Details" section - Improved hierarchy: Overview → Execution → Implementation Details → Parameters → Examples - Added Example 5 demonstrating Skip Path usage - All content preserved, no information loss ## context-search-strategy.md Enhancement - Added Skill() as highest priority tool in Core Search Tools (1 line) - Emphasized: "FASTEST way to get project context - use FIRST if SKILL exists (higher priority than CLI analysis)" - Added to Tool Selection Matrix: "FASTEST context loading - use FIRST if SKILL exists" - Added Quick Command Reference with intelligent auto-trigger emphasis - Total addition: 3 lines as requested ## Benefits - Clearer file structure with eliminated redundancy - Skill() now prominently featured as first-priority context tool - Intelligent auto-trigger mechanism emphasized - Consistent messaging across documentation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
74 lines
2.7 KiB
Markdown
74 lines
2.7 KiB
Markdown
---
|
|
name: context-search-strategy
|
|
description: Strategic guidelines for context search commands
|
|
type: search-guideline
|
|
---
|
|
|
|
# Context Search Strategy
|
|
|
|
## ⚡ Execution Environment
|
|
|
|
**CRITICAL**: All commands execute in **Bash environment** (Git Bash on Windows)
|
|
|
|
**❌ Forbidden**: Windows commands (`findstr`, `dir`, `where`) - Use Bash (`grep`, `find`, `cat`)
|
|
|
|
## ⚡ Core Search Tools
|
|
|
|
**Skill()**: FASTEST way to get project context - use FIRST if SKILL package exists (higher priority than CLI analysis)
|
|
**codebase-retrieval**: Semantic file discovery via Gemini CLI with all files analysis
|
|
**rg (ripgrep)**: Fast content search with regex support
|
|
**find**: File/directory location by name patterns
|
|
**grep**: Built-in pattern matching (fallback when rg unavailable)
|
|
**get_modules_by_depth.sh**: Program architecture analysis (MANDATORY before planning)
|
|
|
|
## 📋 Tool Selection Matrix
|
|
|
|
| Need | Tool | Use Case |
|
|
|------|------|----------|
|
|
| **Project understanding** | Skill() | FASTEST context loading - use FIRST if SKILL exists |
|
|
| **Semantic discovery** | codebase-retrieval | Find files relevant to task/feature context |
|
|
| **Pattern matching** | rg | Search code content with regex |
|
|
| **File name lookup** | find | Locate files by name patterns |
|
|
| **Architecture** | get_modules_by_depth.sh | Understand program structure |
|
|
|
|
## 🔧 Quick Command Reference
|
|
|
|
```bash
|
|
# SKILL Package (FIRST PRIORITY - fastest way to get project context)
|
|
Skill(command: "skill_name") # Intelligent auto-trigger by task context - use FIRST if SKILL exists
|
|
|
|
# Semantic File Discovery (codebase-retrieval)
|
|
cd [directory] && gemini -p "
|
|
PURPOSE: Discover files relevant to task/feature
|
|
TASK: List all files related to [task/feature description]
|
|
MODE: analysis
|
|
CONTEXT: @**/*
|
|
EXPECTED: Relevant file paths with relevance explanation
|
|
RULES: Focus on direct relevance to task requirements
|
|
"
|
|
|
|
# Program Architecture (MANDATORY before planning)
|
|
~/.claude/scripts/get_modules_by_depth.sh
|
|
|
|
# Content Search (rg preferred)
|
|
rg "pattern" --type js -n # Search JS files with line numbers
|
|
rg -i "case-insensitive" # Ignore case
|
|
rg -C 3 "context" # Show 3 lines before/after
|
|
|
|
# File Search
|
|
find . -name "*.ts" -type f # Find TypeScript files
|
|
find . -path "*/node_modules" -prune -o -name "*.js" -print
|
|
|
|
# Workflow Examples
|
|
rg "IMPL-\d+" .workflow/ --type json # Find task IDs
|
|
find .workflow/ -name "*.json" -path "*/.task/*" # Locate task files
|
|
rg "status.*pending" .workflow/.task/ # Find pending tasks
|
|
```
|
|
|
|
## ⚡ Performance Tips
|
|
|
|
- **rg > grep** for content search
|
|
- **Use --type filters** to limit file types
|
|
- **Exclude dirs**: `--glob '!node_modules'`
|
|
- **Use -F** for literal strings (no regex)
|