← Back to Skills Marketplace
289
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install 51mee-position-parse
Description
职位解析。触发场景:用户提供职位描述要求解析;用户想分析JD的核心要求。
README (SKILL.md)
职位解析技能
功能说明
解析职位描述(JD)文本,使用大模型提取结构化信息。
处理流程
- 接收文本 - 用户提供职位描述
- 调用大模型 - 使用以下 prompt 解析
- 返回 JSON - 结构化职位信息
Prompt 模板
```text
{职位描述文本}
扮演一个职位分析专家,详细分析上面的职位描述
- 按照下方的typescript结构定义,返回json格式的PositionInfo结构
- 有数据就填上数据,JD上没有提到,相应的值即为null,绝对不要虚构新的或删除定义中的字段
- 不要做任何解释,直接返回json
export interface PositionInfo {
positionName: string; // 职位名称
positionType: string | null; // 职位类型:技术类/市场类/运营类等
experienceRequired: string | null; // 经验要求,如"3-5年"
educationRequired: string | null; // 学历要求
salaryRange: {
min: number | null;
max: number | null;
};
company: {
name: string | null;
industry: string | null;
scale: string | null; // 公司规模
};
requirements: {
skills: string[]; // 技能要求
responsibilities: string[]; // 岗位职责
softSkills: string[]; // 软技能要求
};
keywords: string[];
}
## 返回数据结构
```json
{
"positionName": "高级Java开发工程师",
"positionType": "技术类",
"experienceRequired": "5年以上",
"educationRequired": "本科及以上",
"salaryRange": {
"min": 20000,
"max": 35000
},
"company": {
"name": null,
"industry": "互联网/IT",
"scale": null
},
"requirements": {
"skills": ["Java", "Spring Boot", "MySQL"],
"responsibilities": ["系统架构设计", "核心代码开发"],
"softSkills": ["团队协作", "沟通能力"]
},
"keywords": ["Java", "Spring Boot", "架构"]
}
输出格式
## 职位分析报告
### 基本信息
- **职位**: [positionName]
- **类型**: [positionType]
- **经验要求**: [experienceRequired]
- **学历要求**: [educationRequired]
### 薪资范围
[salaryRange.min]K - [salaryRange.max]K
### 技能要求
| 必备 | 加分 |
|------|------|
| [skill1] | [skillA] |
### 岗位职责
1. [responsibility1]
2. [responsibility2]
### 软技能要求
- [softSkill1]
- [softSkill2]
### 关键词
[keywords]
注意事项
- 职位描述越详细,解析越准确
- 没有 的字段填
null - 直接返回 JSON,不要额外解释
Usage Guidance
This skill looks coherent and low-risk: it simply sends the job description text to the platform LLM and returns structured JSON. Before using it, avoid submitting sensitive personal data (candidate PII or confidential company details), because those will be sent to the model. Also validate parsed outputs (the skill asks the model not to invent values, but LLMs can still hallucinate). If you need offline/local parsing or stronger privacy guarantees, do not use this cloud/LLM-based skill.
Capability Analysis
Type: OpenClaw Skill
Name: 51mee-position-parse
Version: 1.2.1
The skill is a straightforward utility designed to parse job descriptions (JD) into structured JSON and markdown reports. It contains no executable code, network requests, or instructions to access sensitive data, focusing entirely on text analysis and data extraction as described in SKILL.md.
Capability Assessment
Purpose & Capability
Name/description (职位解析) match the actual instructions: receive a job description, run an LLM prompt, and return structured JSON. No unrelated env vars, binaries, or installs are requested.
Instruction Scope
SKILL.md confines the agent to taking the provided JD, calling the model with a fixed prompt template, and returning JSON. That scope is appropriate. Note: the prompt instructs 'do not fabricate' but parsing accuracy depends on the LLM and hallucination remains a residual risk.
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes on-disk risk.
Credentials
No environment variables, credentials, or config paths are required. Requested access is minimal and proportional to the stated purpose.
Persistence & Privilege
always:false and no mentions of modifying agent/system config. The skill does not request persistent or elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install 51mee-position-parse - After installation, invoke the skill by name or use
/51mee-position-parse - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.1
- Initial release of 51mee-position-parse.
- Provides structured position analysis from job description text using large language models.
- Outputs JSON data following a fixed TypeScript interface for consistent data structure.
- Returns key job info: title, type, experience, education, salary, company details, skills, responsibilities, soft skills, and keywords.
- Ensures that only information present in the JD is returned—missing fields are set to null.
v1.1.0
Initial release.
- Provides structured parsing of job descriptions (JD) into JSON using a large language model.
- Accepts JD text and extracts key details such as position name, type, experience, education, salary, company, requirements, and keywords.
- Ensures no fields are invented or omitted; missing data is returned as null.
- Output is in a standardized JSON format for easy integration and analysis.
- Markdown template for a position analysis report is included in documentation.
v1.0.0
- Initial release of 51mee-position-parse skill for JD (职位描述) parsing
- Automatically extracts structured position information from job descriptions using a large language model
- Outputs results in standardized JSON format matching a detailed TypeScript interface
- No hallucination or omission of interface fields; missing fields are set to null
- Supports extraction of position name, type, experience, education, salary, company info, requirements, and keywords
Metadata
Frequently Asked Questions
What is 51mee Position Parse?
职位解析。触发场景:用户提供职位描述要求解析;用户想分析JD的核心要求。 It is an AI Agent Skill for Claude Code / OpenClaw, with 289 downloads so far.
How do I install 51mee Position Parse?
Run "/install 51mee-position-parse" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 51mee Position Parse free?
Yes, 51mee Position Parse is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 51mee Position Parse support?
51mee Position Parse is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 51mee Position Parse?
It is built and maintained by 51mee (@51mee-com); the current version is v1.2.1.
More Skills