← Back to Skills Marketplace
339
Downloads
0
Stars
2
Active Installs
2
Versions
Install in OpenClaw
/install 51mee-resume-parse
Description
简历解析。触发场景:用户上传简历文件要求解析、提取结构化信息。
README (SKILL.md)
简历解析技能
功能说明
读取简历文件(PDF/DOC/DOCX/JPG/PNG),使用大模型提取结构化信息。
处理流程
- 读取文件 - 用户上传简历时,读取文件内容
- 提取文本 - 从文件中提取纯文本内容
- 调用大模型 - 使用以下 prompt 解析
- 返回 JSON - 解析结果为结构化数据
Prompt 模板
```html
{简历文本内容}
扮演一个简历分析专家,详细地分析上面的简历
- 按照下方的typescript结构定义,返回json格式的ResumeInfo结构
- 有数据就填上数据,简历上没有提到,相应的值即为null,绝对不要虚构新的或者删除定义中的字段
- 不要做任何解释,直接返回json
- 日期格式:"Y-m-d",如 "2025-01-01"; 年格式:"Y",如 "2025"
- 手机号无区号,如"19821450628"
export interface WorkExperience {
startDate: string | null;
endDate: string | null;
company: string;
industry: string | null;
department: string | null;
positionName: string;
blueCollarPosition: boolean | null;
responsibility: string | null;
workPerformance: string | null;
current: boolean | null;
workDesc: string | null;
};
export interface ProjectExperience {
name: string;
startDate: string | null;
endDate: string | null;
roleName: string | null;
projectDesc: string | null;
};
export interface EducationExperience {
startDate: string | null;
endDate: string | null;
school: string;
major: string | null;
degreeName: string | null; // 高中、本科、专科、硕士、博士、其它
};
export interface ResumeInfo {
name: string | null;
gender: number | null; // 0=男, 1=女
age: string | null;
birthday: string | null;
description: string | null;
workExpList: WorkExperience[];
projExpList: ProjectExperience[];
eduExpList: EducationExperience[];
expectPosition: {
positionName: string | null;
lowSalary: number | null;
highSalary: number | null;
locationName: string | null;
};
contact: {
phone: string | null;
weixin: string | null;
email: string | null;
};
keywords: string[];
awards: string[];
englishCertificates: string[];
professionalSkills: string;
}
## 返回数据结构
```json
{
"name": "张三",
"gender": 0,
"age": "30",
"birthday": "1995-01-15",
"description": "5年Java开发经验...",
"workExpList": [...],
"projExpList": [...],
"eduExpList": [...],
"expectPosition": {...},
"contact": {...},
"keywords": ["Java", "Spring"],
"awards": ["优秀员工"],
"englishCertificates": ["CET-6"],
"professionalSkills": "精通Java..."
}
输出格式
## 简历解析结果
### 基本信息
- **姓名**: [name]
- **性别**: [男/女]
- **年龄**: [age]
- **生日**: [birthday]
### 联系方式
- **手机**: [phone]
- **微信**: [weixin]
- **邮箱**: [email]
### 工作经历
[遍历 workExpList]
### 项目经历
[遍历 projExpList]
### 教育经历
[遍历 eduExpList]
### 期望职位
- **职位**: [positionName]
- **薪资**: [lowSalary]K-[highSalary]K
- **地点**: [locationName]
### 关键词
[keywords]
### 奖项
[awards]
### 英语证书
[englishCertificates]
### 专业技能
[professionalSkills]
注意事项
- 支持格式:PDF、DOC、DOCX、JPG、PNG
- 日期格式统一为
Y-m-d - 没有 的字段填
null - 直接返回 JSON,不要额外解释
Usage Guidance
This skill appears to do what it says (parse uploaded resumes into structured JSON). Before installing, confirm the following: (1) Clarify expected output format — the prompt asks for raw JSON but the doc also shows a Markdown summary; decide which you need and test with examples. (2) Ensure the host supports text extraction/OCR for PDFs/JPG/PNG (the SKILL.md assumes you can extract text but doesn't provide tools). (3) Treat parsed resumes as sensitive PII: verify where the model invocation runs (local vs external API), retention/logging policies, and legal/compliance needs. (4) Consider adding redaction or minimization (e.g., mask ID numbers) if you cannot guarantee secure model endpoints. (5) Run tests with representative resumes to validate date/phone formats and that the model doesn't hallucinate fields.
Capability Analysis
Type: OpenClaw Skill
Name: 51mee-resume-parse
Version: 1.2.1
The skill is a standard resume parsing tool designed to extract structured information from uploaded documents (PDF, DOCX, images) using an LLM. The SKILL.md file contains a well-defined prompt template and TypeScript interface for data extraction, with no evidence of malicious intent, data exfiltration, or unauthorized command execution.
Capability Assessment
Purpose & Capability
The name/description (resume parsing) match the instructions: read uploaded resume files, extract text, call a large model, and return structured JSON. There are no unexpected required binaries, env vars, or installs that would be disproportionate to the stated purpose.
Instruction Scope
Instructions stay within the resume-parsing task (read file, extract text, run LLM prompt, return JSON). However there are two inconsistencies: the prompt explicitly says '直接返回 JSON,不要额外解释' while a later '输出格式' section shows a human-readable Markdown summary — this is contradictory and can cause unpredictable outputs. The SKILL.md requires extracting text from images/PDFs but does not specify how (no OCR/tool instructions), and there is no guidance about handling or redacting sensitive PII before sending full resume text to the model.
Install Mechanism
No install spec and no code files — instruction-only — so nothing will be downloaded or written to disk by the skill itself. This is the lowest-risk install profile.
Credentials
The skill requests no environment variables or credentials, which is appropriate. Note: processing resumes entails handling sensitive personal data (phones, emails, birthdates) — the skill does not declare any retention, redaction, or external transmission policies; ensure the hosting environment and model endpoint are acceptable for PII.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent privileges or modify other skills/configs. Autonomous invocation is allowed by platform default but not excessive here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install 51mee-resume-parse - After installation, invoke the skill by name or use
/51mee-resume-parse - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.1
Initial release: Automated extraction of structured data from resumes in multiple file formats.
- Supports PDF, DOC, DOCX, JPG, and PNG resume files for parsing.
- Extracts and returns structured resume information (basic details, work/education/project experience, contact, skills, etc.) in a consistent JSON schema.
- Uses a detailed prompt to guide analysis, ensuring no fields are invented or omitted.
- Standardizes dates and phone formats.
- Provides a suggested Markdown output structure for easy presentation of parsed resume details.
v1.0.0
Initial release of the 51mee-resume-parse skill:
- Supports parsing resumes in PDF, DOC, DOCX, JPG, and PNG formats.
- Extracts structured information from resumes using a large model and a detailed prompt.
- Returns information in a standardized ResumeInfo JSON structure, including work experience, project experience, education, expected position, contact info, keywords, awards, certificates, and skills.
- Ensures fields not present in the resume are set to null, with no fabrication or removal of required fields.
- Output includes a recommended markdown formatting template for easy presentation.
Metadata
Frequently Asked Questions
What is 51mee Resume Parse?
简历解析。触发场景:用户上传简历文件要求解析、提取结构化信息。 It is an AI Agent Skill for Claude Code / OpenClaw, with 339 downloads so far.
How do I install 51mee Resume Parse?
Run "/install 51mee-resume-parse" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 51mee Resume Parse free?
Yes, 51mee Resume Parse is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 51mee Resume Parse support?
51mee Resume Parse is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 51mee Resume Parse?
It is built and maintained by 51mee (@51mee-com); the current version is v1.2.1.
More Skills