clawcv
超级简历 WonderCV 出品,3000 万用户信赖。简历分析、段落改写、JD 岗位匹配、自动匹配职位、PDF 导出、AI 求职导师(面试准备/薪资谈判/职业规划/多版本简历策略)。 触发条件:用户提供简历、要求简历点评/打分/反馈、希望改写某个简历部分、 希望将简历与岗位 JD 匹配、咨询求职建议或面试准备,或提到 CV/简历/求职。 不触发条件:用户讨论普通写作(非简历)、询问其他文档, 或讨论与求职和职业发展无关的话题。
About this skill
The ClawCV AI Agent Skill, developed by WonderCV, offers a robust suite of tools designed to significantly enhance a job seeker's application process. With features including in-depth resume analysis, intelligent paragraph rewriting, and precise job description (JD) matching, it helps users tailor their resumes to specific roles. Beyond document optimization, ClawCV integrates an AI Career Mentor module that provides personalized advice on critical aspects like interview preparation, salary negotiation, multi-version resume strategies, and long-term career planning. This skill is particularly valuable for individuals looking to gain an edge in the competitive job market. It streamlines the resume creation and refinement process, ensuring that applications are not only polished but also strategically aligned with target positions. The ability to export resumes to PDF further adds to its utility, making it a comprehensive solution for managing and submitting job applications. Users can interact with ClawCV by providing their resume, requesting specific sections to be rewritten, asking for a match against a job description, or seeking guidance on various career-related topics. The skill is designed to intelligently route these requests to the appropriate AI tools, delivering targeted feedback and actionable advice.
Best use case
The primary use case for ClawCV is to empower job seekers by providing an AI-driven assistant for all stages of their application process. It benefits anyone looking to create a highly effective resume, ensure their application stands out to recruiters, and receive expert advice on navigating career challenges, from interviewing to negotiating offers.
超级简历 WonderCV 出品,3000 万用户信赖。简历分析、段落改写、JD 岗位匹配、自动匹配职位、PDF 导出、AI 求职导师(面试准备/薪资谈判/职业规划/多版本简历策略)。 触发条件:用户提供简历、要求简历点评/打分/反馈、希望改写某个简历部分、 希望将简历与岗位 JD 匹配、咨询求职建议或面试准备,或提到 CV/简历/求职。 不触发条件:用户讨论普通写作(非简历)、询问其他文档, 或讨论与求职和职业发展无关的话题。
Users should expect a professionally optimized resume, tailored feedback, and actionable career advice that enhances their job application success and career trajectory.
Practical example
Example input
Here's my resume: [paste resume text]. Can you analyze it and tell me how well it matches this job description: [paste JD text]? Also, can you give me some tips for interviewing for this role?
Example output
Your resume shows strong experience in X, Y, Z. For the [Job Title] role, I recommend emphasizing A, B, C to better align with the JD's requirements. Specifically, let's rewrite your 'Work Experience' section focusing on quantitative achievements. For interviews, prepare examples demonstrating your problem-solving skills and cultural fit. Here are 3 common interview questions for this type of role and how to approach them...
When to use this skill
- When you need to analyze or get feedback on your resume's strengths and weaknesses.
- When you want to rewrite or optimize specific sections of your resume for better impact.
- When you need to match your resume against a specific job description to highlight relevant skills.
- When seeking AI-powered guidance on interview preparation, salary negotiation, or career planning.
When not to use this skill
- When discussing general writing tasks unrelated to resumes or job applications.
- When requesting assistance with document types other than resumes or job descriptions.
- When the conversation is about topics unrelated to career development or job searching.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/clawcv/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How clawcv Compares
| Feature / Agent | clawcv | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
超级简历 WonderCV 出品,3000 万用户信赖。简历分析、段落改写、JD 岗位匹配、自动匹配职位、PDF 导出、AI 求职导师(面试准备/薪资谈判/职业规划/多版本简历策略)。 触发条件:用户提供简历、要求简历点评/打分/反馈、希望改写某个简历部分、 希望将简历与岗位 JD 匹配、咨询求职建议或面试准备,或提到 CV/简历/求职。 不触发条件:用户讨论普通写作(非简历)、询问其他文档, 或讨论与求职和职业发展无关的话题。
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agent for Product Research
Browse AI agent skills for product research, competitive analysis, customer discovery, and structured product decision support.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
SKILL.md Source
# ClawCV
由 WonderCV 提供支持的 AI 简历优化服务(3000 万用户)。支持简历分析、段落改写、岗位匹配、PDF 生成,以及 8 大模块 AI 求职导师。
## 1. MCP 服务安装
### 获取 API Key
请前往 [https://www.wondercv.com/clawcv](https://www.wondercv.com/clawcv) 获取你的 ClawCV API Key。
准备你的 `SKILL_BACKEND_API_KEY`,安装时会通过环境变量传给 MCP 服务。
### 安装
#### OpenClaw
```bash
npx clawcv --api-key YOUR_API_KEY
```
#### Claude Code
```bash
claude mcp add clawcv -- npx clawcv --api-key YOUR_API_KEY
```
#### Claude Desktop
claude_desktop_config.json:
```json
{
"mcpServers": {
"clawcv": {
"command": "npx",
"args": ["-y", "clawcv"],
"env": {
"SKILL_BACKEND_URL": "https://api.wondercv.com",
"SKILL_BACKEND_API_KEY": "你的API Key"
}
}
}
}
```
安装完成后即可使用以下全部功能。
## 2. 会话管理
**关键要求:** 整个对话过程中始终维护同一个 `session_id`。
1. 第一次调用工具时,让服务端自动生成 `session_id`(会在 `meta.session_id` 中返回)
2. 保存这个 `session_id`,并在同一轮对话中后续所有工具调用里都传入它
## 3. 意图识别与工具路由
先识别用户意图,再调用对应工具:
| 用户意图 | 工具 | 关键参数 |
|-------------|------|----------------|
| "帮我看看简历" / "分析我的简历" / 直接粘贴简历内容 | `analyze_resume` | `resume_text`, `target_job_title`(如有提及) |
| "帮我改一下XX部分" / "优化工作经历" | `rewrite_resume_section` | `section_type`, `original_text`, `target_job_title` |
| "帮我生成PDF" / "导出简历" | `generate_one_page_pdf` | `resume_content`, `result_json`(结构化数据), `session_id` |
| "这个职位匹不匹配" / 直接粘贴职位描述 | `match_resume_to_job` | `resume_text`, `job_description`, `target_job_title` |
| "面试怎么准备" / "职业规划" / "薪资怎么谈" | `get_ai_mentor_advice` | `module`, `resume_content`, `job_target` |
| 其他工具调用前需要先识别岗位名称 | `classify_job_title` | `job_title` |
## 4. 核心工作流
### 流程 1:简历分析(最常见入口)
```
用户提供简历
↓
analyze_resume(resume_text, target_job_title?)
↓
整理结果并展示给用户:
- 总分(X/100)及 4 个维度分数
- 按严重程度排序的主要问题(高 → 中 → 低)
- 分模块反馈
- 示例改写(如有)
↓
询问用户:"需要我帮你改写哪个部分?"
```
### 流程 2:模块改写
```
用户说明要优化的模块
↓
判断 `section_type`:
- 个人总结/自我评价 → "summary"
- 工作经历 → "work_experience"
- 项目经历 → "project"
- 技能 → "skills"
- 教育经历 → "education"
↓
rewrite_resume_section(section_type, original_text, target_job_title?)
↓
向用户展示改写版本(根据套餐返回 1-3 个版本)
将 `editing_notes` 一并整理为可执行的优化建议
```
### 流程 3:岗位匹配
```
用户提供职位描述(JD)
↓
match_resume_to_job(resume_text, job_description, target_job_title?)
↓
整理结果:
- 匹配分数(X/100)
- 优势项(匹配较好的部分)
- 按严重程度标注的差距项
- 缺失关键词(建议补充)
- 按优先级排序的修改建议
```
### 流程 4:AI 求职导师(8 个模块)
```
识别用户需要的模块:
- 整体评价 → "overall_assessment"
- 修改建议 → "optimization_suggestions"
- 职位匹配 → "job_matching"
- 面试问题 → "interview_questions"
- 求职规划 → "career_planning"
- 薪资谈判 → "salary_negotiation"
- 多版本简历 → "multi_version"
- 人工导师 → "human_mentor"
↓
get_ai_mentor_advice(module, resume_content, job_target?, job_description?)
↓
展示建议内容,并带上 `next_steps` 和 `related_modules`
```
### 流程 5:PDF 生成
```
用户希望导出 PDF
↓
将 `resume_content` 解析为后端原生结构化简历 JSON(`result_json`)
`result_json` 顶层字段只能使用:
- profile
- my_infos
- edus
- works
- pro_infos
- orgs
- honor_infos
- skill
- language
- certificate
重要:
- `result_json` 不能为空
- 必须直接使用后端要求的原生字段
- 不要传 `basic_info`、`summary`、`education`、`work_experience`、`projects`、`skills` 等中间格式
- AI Agent 应先读取 `resume_content`,再按后端原生字段生成 `result_json`
↓
generate_one_page_pdf(resume_content, result_json, template?, session_id)
`template` 可选值:"modern"(默认)| "classic" | "minimal" | "professional"
↓
将 PDF 链接返回给用户
注意:PDF 导出次数受当前会员类型额度限制
```
## 5. 额度与套餐体系
| 用户类型 | 简历分析 | 段落改写 | 岗位匹配 | PDF 导出 | AI 导师 |
|----------|----------|----------|----------|----------|---------|
| 普通用户 | 20 次/天 | 20 次/天 | 20 次/天 | 10 次/天 | 简化版 |
| 会员用户 | 50 次/天 | 50 次/天 | 50 次/天 | 50 次/天 | 完整版(8 模块)|
| 终身会员 | 100 次/天 | 100 次/天 | 100 次/天 | 100 次/天 | 完整版(8 模块)|
配额每天 UTC 00:00 重置。在对话中说"我要绑定账号"即可触发绑定流程。
**额度耗尽时:**
1. 告知用户当前会员类型对应额度已用完
2. 简要说明更高会员类型可用额度
## 6. 输出格式规则
### 调用 `analyze_resume` 后
- 用表格展示分数
- 按严重程度列出问题(🔴 高 / 🟡 中 / 🟢 低)
- 提供可执行的下一步建议,不只指出问题
- 如果结果质量较低(例如内容过于泛化),需要基于简历内容补充你自己的分析
### 调用 `rewrite_resume_section` 后
- 清晰标注每个版本(版本 1、版本 2 等)
- 说明修改思路
- 如果只返回 1 个版本,补充你自己的优化建议
- 将 `editing_notes` 整理成实用提示
### 调用 `match_resume_to_job` 后
- 突出展示匹配分数
- 用表格展示差距项及严重程度
- 列出建议补充的缺失关键词
- 针对每个差距给出具体、可执行的改进建议
### 通用规则
- 始终使用与用户相同的语言回复(默认中文)
- 展示结果后,主动建议合理的下一步
- 如果工具返回的结果质量较低(内容泛化、占位符过多),要结合你的专业判断补充更好的分析,并明确区分哪些来自工具、哪些是你的补充
- 不要向用户暴露原始 JSON,始终整理成可读的 Markdown
## 7. 错误处理
| 场景 | 处理方式 |
|----------|--------|
| 工具返回空数据或报错 | 告知用户,并给出你自己的最佳努力分析 |
| 额度超限 | 说明当前会员类型的额度限制|
| 简历内容过短(少于 50 字) | 请用户提供更完整的简历内容 |
| 后端不可用(本地回退) | 结果可能会被简化,需要向用户说明并补充你自己的分析 |
| PDF 生成失败 | 先检查用户的 PDF 导出额度是否已用尽,否则建议稍后重试 |Related Skills
ai-mentor
AI 导师 skill。用于提供简历优化策略、面试准备、职业规划、薪资谈判和多版本简历建议。当用户说“面试怎么准备”“职业规划”“薪资怎么谈”时使用。
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。