prompt-library
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChinesePrompt Library
提示词资源库
Collection of professional, tested, and optimized prompt templates.
包含经过专业测试和优化的提示词模板集合。
Categories
分类
Agents (6 executable agents)
Agents(6个可执行Agent)
| Template | Description | Usage |
|---|---|---|
| code-reviewer | Code review with SOLID | |
| support-assistant | Multichannel customer support | |
| data-analyst | Data analysis | |
| technical-writer | Technical documentation | |
| security-auditor | OWASP security audit | |
| api-designer | REST/GraphQL API design | |
| 模板 | 描述 | 使用方式 |
|---|---|---|
| code-reviewer | 基于SOLID原则的代码评审 | |
| support-assistant | 多渠道客户支持 | |
| data-analyst | 数据分析 | |
| technical-writer | 技术文档撰写 | |
| security-auditor | OWASP安全审计 | |
| api-designer | REST/GraphQL API设计 | |
Tasks (6 executable agents)
任务类(6个可执行Agent)
| Template | Description | Usage |
|---|---|---|
| summarizer | Adaptive text summarization | |
| translator | Multilingual translation | |
| extractor | Structured data extraction | |
| classifier | Content classification | |
| generator | Content generation | |
| validator | Data validation | |
| 模板 | 描述 | 使用方式 |
|---|---|---|
| summarizer | 自适应文本摘要 | |
| translator | 多语言翻译 | |
| extractor | 结构化数据提取 | |
| classifier | 内容分类 | |
| generator | 内容生成 | |
| validator | 数据验证 | |
Specialized (6 executable agents)
专业领域类(6个可执行Agent)
| Template | Description | Usage |
|---|---|---|
| legal-assistant | Legal analysis | |
| medical-writer | Medical writing | |
| financial-analyst | Financial analysis | |
| marketing-strategist | Marketing strategy | |
| hr-assistant | Human resources | |
| educational-tutor | Educational tutoring | |
| 模板 | 描述 | 使用方式 |
|---|---|---|
| legal-assistant | 法律分析 | |
| medical-writer | 医学文档撰写 | |
| financial-analyst | 财务分析 | |
| marketing-strategist | 营销策略制定 | |
| hr-assistant | 人力资源支持 | |
| educational-tutor | 教育辅导 | |
Commands
命令
bash
undefinedbash
undefinedList all templates
列出所有模板
/prompt library list
/prompt library list
Search for a template
搜索模板
/prompt library search "code review"
/prompt library search "code review"
View a template
查看模板详情
/prompt library show code-reviewer
/prompt library show code-reviewer
Use a template (copy and customize)
使用模板(复制并自定义)
/prompt library use code-reviewer
/prompt library use code-reviewer
Use with customization
自定义使用模板
/prompt library use code-reviewer --lang python --focus security
undefined/prompt library use code-reviewer --lang python --focus security
undefinedAgent Structure
Agent结构
Each agent follows the standard Claude Code format:
yaml
---
name: agent-name
description: Clear description for automatic triggering
model: sonnet|opus|haiku
color: color-name
tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch
skills: skill-name
---每个Agent都遵循标准的Claude Code格式:
yaml
---
name: agent-name
description: Clear description for automatic triggering
model: sonnet|opus|haiku
color: color-name
tools: Read, Write, Edit, Bash, Grep, Glob, WebSearch
skills: skill-name
---Required Fields
必填字段
| Field | Description | Values |
|---|---|---|
| Unique identifier | kebab-case |
| Trigger + usage context | Descriptive text |
| Claude model to use | |
| Display color | green, blue, red, amber, etc. |
| Available tools | Read, Write, Edit, Bash, Grep, Glob, WebSearch |
| Associated skill | Linked skill name |
| 字段 | 描述 | 取值 |
|---|---|---|
| 唯一标识符 | 短横线分隔格式(kebab-case) |
| 触发条件及使用场景 | 描述性文本 |
| 使用的Claude模型 | |
| 显示颜色 | green, blue, red, amber等 |
| 可用工具 | Read, Write, Edit, Bash, Grep, Glob, WebSearch |
| 关联技能 | 关联的技能名称 |
Agent Body
Agent主体内容
After the YAML frontmatter, the Markdown body contains:
- Instructions and processes
- Output formats
- Examples and patterns
- Rules and prohibitions (Forbidden)
YAML前置声明之后,Markdown主体包含:
- 操作说明与流程
- 输出格式
- 示例与模式
- 规则与禁忌(Forbidden)
Contribution
贡献指南
To add an agent:
- Create the file in the appropriate category (
.md,agents/,tasks/)specialized/ - Use the standard YAML frontmatter (name, description, model, color, tools, skills)
- Test the agent with at least 3 use cases
- Document output formats and rules (Forbidden)
添加新Agent的步骤:
- 在对应分类目录(、
agents/、tasks/)中创建specialized/文件.md - 使用标准YAML前置声明(name, description, model, color, tools, skills)
- 至少用3个使用场景测试该Agent
- 记录输出格式与规则(禁忌内容)