UP 简历 - 让 Agent 帮你写简历找工作

UP 简历 AI 求职助手。创建专业简历、搜索校招/社招/实习岗位、JD 对照优化、简历诊断、每日求职监控、智能投递指导。当用户说"创建简历"、"编辑简历"、"搜索校招"、"找工作"、"优化简历"、"投递"、"监控校招"时使用。

This skill appears to do what it says (resume creation, job search, monitoring, ATS guidance) but check a few things before enabling: - The SKILL.md expects you to run 'claude' CLI commands and to install an MCP server via npx (@upcv/mcp-server). The registry metadata did not declare required binaries (node/npm, npx, or claude). Make sure you have these tools installed and review the npm package (@upcv/mcp-server) source (the README points to a GitHub repo) before running npx. - The skill asks you to provide an API Key from clawjob.upcv.tech/upcv.tech. That key likely gives the external service access to your resumes — confirm what permissions the key grants and that you trust the service. - If you use the job-monitor feature the skill will create monitor.sh, a cron job or a launchd plist, and save daily reports to ~/.jobsclaw/reports and ATS metadata to ats-records/. Those files can contain personal data from your resume. Review the monitor script and scheduled task entries yourself before enabling; do not paste sensitive fields (e.g., ID numbers) into automated scripts. - Because scheduled jobs will run the agent CLI ('claude -p') automatically, consider whether you want automated agent invocations on your machine. Review the exact command text in monitor.sh and confirm any network calls and API usage. - Best practice: inspect the npm package code or GitHub repo referenced in README, audit the monitor script and any files it writes, and only install if you trust upcv and the @upcv/mcp-server package. If unsure, run the skill interactively without enabling the monitor persistence, or use a disposable environment.

Type: OpenClaw Skill Name: upcv-clawjob Version: 1.0.1 The skill bundle provides a comprehensive suite for resume management and job searching via the UPCV MCP server (upcv.tech). However, it is classified as suspicious due to high-risk persistence and execution capabilities defined in job-monitor/SKILL.md, which instructs the AI agent to create shell scripts and configure system-level task schedulers (cron or launchd) to automatically execute AI prompts. While these actions are plausibly intended for the stated purpose of daily job monitoring, the automated generation of executable scripts and persistence mechanisms represents a significant attack surface.