catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-13 02:41:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add dynamic output format for prompt-enhancer and update README

Browse Source 
- Redesign output format to be dynamic and task-adaptive
- Replace fixed template with core + optional fields structure
- Add simple and complex task examples
- Update workflow and enhancement guidelines
- Add Agent Skills section to README.md and README_CN.md
- Document Prompt Enhancer skill usage with -e/--enhance flags
- Provide skill creation best practices

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-10-18 23:00:08 +08:00
parent 44734a447c
commit 24aad6238a
3 changed files with 204 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

142
.claude/skills/prompt-enhancer/SKILL.md
View File

@@ -18,81 +18,107 @@ allowed-tools: (none)
## Output Format ## Output Format
**Dynamic Structure**: Adapt fields based on task type and context needs. Not all fields are required.
**Core Fields** (always present):
- **INTENT**: One-sentence technical goal
- **ACTION**: Concrete steps with technical details
**Optional Fields** (include when relevant):
- **TECH STACK**: Relevant technologies (when tech-specific)
- **CONTEXT**: Session memory findings (when context matters)
- **ATTENTION**: Critical constraints (when risks/requirements exist)
- **SCOPE**: Affected modules/files (for multi-module tasks)
- **METRICS**: Success criteria (for optimization/performance tasks)
- **DEPENDENCIES**: Related components (for integration tasks)
**Example (Simple Task)**:
``` ```
📋 ENHANCED PROMPT 📋 ENHANCED PROMPT
INTENT: [One-sentence technical goal with tech stack / 明确技术目标含技术栈] INTENT: Fix authentication token validation in JWT middleware
TECH STACK: [Relevant technologies from memory / 相关技术栈]
- [Framework/Library: Purpose]
CONTEXT: [Session memory findings / 会话记忆发现]
- [Key context point 1]
- [Key context point 2]
- [Design patterns/constraints from session]
ACTION: ACTION:
1. [Concrete step with technical details / 具体步骤含技术细节] 1. Review token expiration logic in auth middleware
2. [Concrete step with technical details] 2. Add proper error handling for expired tokens
3. [Testing/validation step] 3. Test with valid/expired/malformed tokens
```
ATTENTION: [Critical constraints / 关键约束] **Example (Complex Task)**:
- [Security/compatibility/performance concerns] ```
- [Design pattern requirements] 📋 ENHANCED PROMPT
INTENT: Optimize API performance with caching and database indexing
TECH STACK:
- Redis: Response caching
- PostgreSQL: Query optimization
CONTEXT:
- API response times >2s mentioned in previous conversation
- PostgreSQL slow query logs show N+1 problems
ACTION:
1. Profile endpoints to identify slow queries
2. Add PostgreSQL indexes on frequently queried columns
3. Implement Redis caching for read-heavy endpoints
4. Add cache invalidation on data updates
METRICS:
- Target: <500ms API response time
- Cache hit ratio: >80%
ATTENTION:
- Maintain backward compatibility with existing API contracts
- Handle cache invalidation correctly to avoid stale data
``` ```
## Workflow ## Workflow
``` ```
Trigger → Internal Analysis → Direct Output Trigger (-e/--enhance) → Internal Analysis → Dynamic Output
↓ ↓ ↓ ↓ ↓ ↓
P1-4 Semantic+Memory Enhanced Prompt User Input Assess Task Type Select Fields
(3 dimensions) (Structured) Extract Memory Context Structure Prompt
``` ```
1. **Detect**: Check triggers (P1-P4) 1. **Detect**: User input contains `-e` or `--enhance`
2. **Internal Analysis**: 2. **Analyze**:
- Semantic (EN/CN) intent analysis - Determine task type (fix/optimize/implement/refactor)
- Memory extraction (tech stack, patterns, constraints) - Extract relevant session context
- Enhancement (structure + supplement + clarify) - Identify tech stack and constraints
3. **Output**: Present enhanced structured prompt directly 3. **Structure**:
- Always include: INTENT + ACTION
- Conditionally add: TECH STACK, CONTEXT, ATTENTION, METRICS, etc.
4. **Output**: Present dynamically structured prompt
## Enhancement Checklist (Internal) ## Enhancement Guidelines (Internal)
**Structure**: **Always Include**:
- [ ] INTENT: Clear, one-sentence technical goal - Clear, actionable INTENT
- [ ] TECH STACK: Relevant technologies from session - Concrete ACTION steps with technical details
- [ ] CONTEXT: Key session findings and constraints
- [ ] ACTION: Concrete steps with technical details
- [ ] ATTENTION: Critical constraints and patterns
**Supplement**: **Add When Relevant**:
- [ ] Add tech stack/frameworks mentioned in session - TECH STACK: Task involves specific technologies
- [ ] Include design patterns if relevant - CONTEXT: Session memory provides useful background
- [ ] Add testing/validation requirements - ATTENTION: Security/compatibility/performance concerns exist
- [ ] Specify performance metrics if applicable - SCOPE: Multi-module or cross-component changes
- METRICS: Performance/optimization goals need measurement
- DEPENDENCIES: Integration points matter
**Clarify**: **Quality Checks**:
- [ ] Make vague intent explicit - Make vague intent explicit
- [ ] Resolve ambiguous references (it/that/这个/那个) - Resolve ambiguous references
- [ ] Expand multi-module scope with dependencies - Add testing/validation steps
- [ ] Add missing context from memory - Include constraints from memory
## Best Practices ## Best Practices
- ✅ Detect `-e`/`--enhance` flags first (P1) - ✅ Trigger only on `-e`/`--enhance` flags
- ✅ Support EN + CN semantic keywords - ✅ Use **dynamic field selection** based on task type
- ✅ Extract **memory context ONLY** (no file reading) - ✅ Extract **memory context ONLY** (no file reading)
- ✅ Add tech stack, design patterns, testing requirements - ✅ Always include INTENT + ACTION as core fields
- ✅ Direct output (no intermediate steps) - ✅ Add optional fields only when relevant to task
- ✅ Use INTENT/TECH STACK/CONTEXT/ACTION/ATTENTION format - ✅ Direct output (no intermediate steps shown)
- ❌ NO tool calls (AskUserQuestion removed) - ❌ NO tool calls
- ❌ NO Bash, Read, Glob, Grep operations - ❌ NO file operations (Bash, Read, Glob, Grep)
- ❌ NO file analysis or codebase scanning - ❌ NO fixed template - adapt to task needs
## Key Changes
1. **Removed all tools** - Pure analysis and output
2. **Removed user confirmation** - Direct output for speed
3. **Added tech stack section** - Supplement with technologies
4. **Enhanced internal analysis** - 3 dimensions (structure + supplement + clarify)
5. **Focus on memory** - Session context only, no file reading

60
README.md
View File

@@ -289,6 +289,66 @@ MCP (Model Context Protocol) tools provide advanced codebase analysis. **Recomme
--- ---
## 🎯 Agent Skills
**Agent Skills** extend Claude's capabilities with modular, reusable expertise packages. Skills are automatically discovered and triggered based on context.
### **Available Skills**
#### **Prompt Enhancer**
Transform vague prompts into structured, actionable specifications.
**Usage**: Add `-e` or `--enhance` flag to any request
```bash
# Example
fix authentication issue -e
optimize database queries --enhance
```
**What it does**:
- Analyzes session context and tech stack
- Structures intent into INTENT → ACTION format
- Adds relevant context, constraints, and metrics
- Outputs ready-to-execute specifications
**Output**: Dynamic structured prompt adapted to task type (simple tasks get minimal fields, complex tasks get comprehensive specifications)
### **Creating Custom Skills**
Skills are stored in `.claude/skills/` (project) or `~/.claude/skills/` (personal):
```bash
# Create a new skill
mkdir -p .claude/skills/my-skill
```
**SKILL.md structure**:
```yaml
---
name: My Skill Name
description: What it does and when to use it. Use when [trigger conditions].
allowed-tools: Read, Grep, Glob # Optional tool restrictions
---
# My Skill Name
## Instructions
[Step-by-step guidance for Claude]
## Examples
[Concrete usage examples]
```
**Best Practices**:
- Write specific descriptions with clear trigger conditions
- Include both what the skill does and when to use it
- Keep skills focused on single capabilities
- Test by asking questions that match your description
For complete documentation, see [skills.md](skills.md).
---
## 🚀 Getting Started ## 🚀 Getting Started
### Complete Development Workflow ### Complete Development Workflow

60
README_CN.md
View File

@@ -289,6 +289,66 @@ MCP (模型上下文协议) 工具提供高级代码库分析。**推荐安装**
--- ---
## 🎯 智能体技能 (Agent Skills)
**智能体技能** 通过模块化、可复用的专业知识包扩展 Claude 的能力。技能会根据上下文自动发现和触发。
### **可用技能**
#### **提示词增强器 (Prompt Enhancer)**
将模糊提示转换为结构化、可执行的规范。
**使用方式**：在任何请求中添加 `-e` 或 `--enhance` 标志
```bash
# 示例
修复认证问题 -e
优化数据库查询 --enhance
```
**功能说明**:
- 分析会话上下文和技术栈
- 将意图结构化为 INTENT → ACTION 格式
- 添加相关上下文、约束和指标
- 输出可立即执行的规范
**输出**：根据任务类型动态调整的结构化提示（简单任务使用最少字段，复杂任务使用全面规范）
### **创建自定义技能**
技能存储在 `.claude/skills/`（项目）或 `~/.claude/skills/`（个人）：
```bash
# 创建新技能
mkdir -p .claude/skills/my-skill
```
**SKILL.md 结构**:
```yaml
---
name: 我的技能名称
description: 功能说明和使用时机。使用时机：[触发条件]。
allowed-tools: Read, Grep, Glob # 可选工具限制
---
# 我的技能名称
## 指令
[Claude 的分步指导]
## 示例
[具体使用示例]
```
**最佳实践**:
- 编写具体的描述，包含明确的触发条件
- 同时说明功能和使用时机
- 保持技能专注于单一能力
- 通过匹配描述的问题进行测试
完整文档请参阅 [skills.md](skills.md)。
---
## 🚀 快速入门 ## 🚀 快速入门
### 完整开发工作流 ### 完整开发工作流