Claude-Code-Workflow/.claude/commands/enhance-prompt.md at 920b1794400c1bc4e755e4ee6080a4bb924bb6d0

mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-05 01:50:27 +08:00

Files

catlog22 920b179440 docs: 更新所有命令描述并重新生成索引文件

- 更新所有69个命令文件的description字段，基于实际功能重新生成详细描述
- 重新生成5个索引文件（all-commands, by-category, by-use-case, essential-commands, command-relationships）
- 移动analyze_commands.py到scripts/目录并完善功能
- 移除临时备份文件

命令描述改进示例：
- workflow:plan: 增加了工具和代理的详细说明（Gemini, action-planning-agent）
- cli:execute: 说明了YOLO权限和多种执行模式
- memory:update-related: 详细说明了批处理策略和工具回退链

索引文件改进：
- usage_scenario从2种扩展到10种（更精细分类）
- command-relationships覆盖所有69个命令
- 区分built-in（内置调用）和sequential（用户顺序执行）关系

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

Co-Authored-By: Claude <noreply@anthropic.com>

2025-11-06 15:11:31 +08:00

3.4 KiB

Raw Blame History

name, description, argument-hint

name	description	argument-hint
enhance-prompt	Enhanced prompt transformation using session memory and codebase analysis with --enhance flag detection	user input to enhance

Overview

Systematically enhances user prompts by combining session memory context with codebase patterns, translating ambiguous requests into actionable specifications.

Core Protocol

Enhancement Pipeline: Intent Translation → Context Integration → Gemini Analysis (if needed) → Structured Output

Context Sources:

Session memory (conversation history, previous analysis)
Codebase patterns (via Gemini when triggered)
Implicit technical requirements

Gemini Trigger Logic

FUNCTION should_use_gemini(user_prompt):
  critical_keywords = ["refactor", "migrate", "redesign", "auth", "payment", "security"]

  RETURN (
    prompt_affects_multiple_modules(user_prompt, threshold=3) OR
    any_keyword_in_prompt(critical_keywords, user_prompt)
  )
END

Gemini Integration: ~/.claude/workflows/intelligent-tools-strategy.md

Enhancement Rules

Intent Translation

User Says	Translate To	Focus
"fix"	Debug and resolve	Root cause → preserve behavior
"improve"	Enhance/optimize	Performance/readability
"add"	Implement feature	Integration + edge cases
"refactor"	Restructure quality	Maintain behavior
"update"	Modernize	Version compatibility

Context Integration Strategy

Session Memory First:

Reference recent conversation context
Reuse previously identified patterns
Build on established understanding

Codebase Analysis (via Gemini):

Only when complexity requires it
Focus on integration points
Identify existing patterns

Example:

# User: "add login"
# Session Memory: Previous auth discussion, JWT mentioned
# Inferred: JWT-based auth, integrate with existing session management
# Gemini (if multi-module): Analyze AuthService patterns, middleware structure

Output Structure

INTENT: [Clear technical goal]
CONTEXT: [Session memory + codebase patterns]
ACTION: [Specific implementation steps]
ATTENTION: [Critical constraints]

Output Examples

Simple (no Gemini):

# Input: "fix login button"
INTENT: Debug non-functional login button
CONTEXT: From session - OAuth flow discussed, known state issue
ACTION: Check event binding → verify state updates → test auth flow
ATTENTION: Preserve existing OAuth integration

Complex (with Gemini):

# Input: "refactor payment code"
INTENT: Restructure payment module for maintainability
CONTEXT: Session memory - PCI compliance requirements
         Gemini - PaymentService → StripeAdapter pattern identified
ACTION: Extract reusable validators → isolate payment gateway logic
ATTENTION: Zero behavior change, maintain PCI compliance, full test coverage

Automatic Triggers

Ambiguous language: "fix", "improve", "clean up"
Multi-module impact (>3 modules)
Architecture changes
Critical systems: auth, payment, security
Complex refactoring

Key Principles

Memory First: Leverage session context before analysis
Minimal Gemini: Only when complexity demands it
Context Reuse: Build on previous understanding
Clear Output: Structured, actionable specifications
Avoid Duplication: Reference existing context, don't repeat

3.4 KiB Raw Blame History