BeClaude

job-ok

New
33GitHub TrendingGeneralby GresonKwan

Use when helping a Chinese job seeker, especially students, interns, or early-career users, prepare job applications with an agent without fabricating experience, auto-submitting applications, scraping hiring platforms, or promising offers.

First seen 6/19/2026

Summary

Job OK is a local skill for Chinese job seekers, especially students and early-career users, that helps organize real experiences into verifiable evidence for job matching, resume optimization, application tracking, and interview practice.

  • It prioritizes evidence-based conclusions, manual user confirmation for external actions, and strict boundaries against fabricating experience or auto-submitting applications.

Overview

Job OK

Job OK 是一个面向中文求职者的本地求职 Skill。它帮助学生、实习生和早期职场人把真实经历整理成可追溯的求职证据,再用于岗位匹配、简历优化、投递跟踪和面试表达训练。

核心原则:先证据,后结论;先岗位匹配,后简历改写;用户手动确认任何外部投递动作。

使用边界

  • 默认使用中文,除非用户要求其他语言。
  • 默认把简历、联系方式、截图、聊天记录等敏感材料保留在本地。
  • 输出中区分 factassumptioninferenceuser_preference
  • 不编造学历、实习、项目、奖项、指标、证书、技能或公司经历。
  • 不承诺面试、offer、薪资结果或平台曝光。
  • 不自动投递、不自动私信 HR、不绕过登录、不批量爬取招聘平台。
  • 不用于企业侧招聘、候选人排名或人事决策。

本地案例目录

每服务一个求职者,创建或复用:

text
job-search-cases/<yyyy-mm-dd-user-slug>/
├── brief.yaml
├── raw/
│   ├── resume/
│   └── job-posts/
├── profile.yaml
├── experience-assets.md
├── strengths.md
├── target-roles.csv
├── jobs.jsonl
├── job-matches.csv
├── resume-review.md
├── resume-versions/
├── interview-story-bank.md
├── interview-practice.md
├── application-tracker.csv
└── review-log.md

优先从 assets/templates/ 复制模板到案例目录,再开始分析。

工作流

  1. 先 Intake。 收集简历、目标城市、目标岗位、教育背景、项目/实习经历、限制条件、排除岗位、偏好行业和风险备注。核心信息不足时先追问,不急着推荐岗位或改简历。参考 references/intake-flow.md
  2. 提取真实经历。 把简历和用户回答整理到 experience-assets.md。可用 scripts/extract_resume_text.py 提取 .pdf.docx.txt.md 简历文本。
  3. 挖掘优势。 每个优势都必须走完 证据 -> 行为 -> 能力 -> 岗位信号。参考 references/strength-taxonomy.md,在 strengths.md 记录可信度和缺失证据。
  4. 生成岗位假设。 输出 3-5 个目标岗位簇到 target-roles.csv。参考 references/job-matching-rubric.md,写清匹配证据、差距、30 天补强动作和适合公司类型。
  5. 整理真实 JD。 只接受用户提供的岗位链接、截图、复制 JD、CSV 导出、Markdown 表格或浏览器可见页面。用 scripts/normalize_jobs.py 生成 jobs.jsonl。使用平台资料前先读 references/platform-boundaries.md
  6. 评分和短名单。scripts/score_job_matches.py 做确定性初筛。分数只用于 triage,不代表真实录取概率。低分岗位进入观察池,不进入投递列表。
  7. 优化简历。 参考 references/resume-rubric.md。每条建议必须能回到真实经历。输出 resume-review.md,并在 resume-versions/ 记录不同岗位版本。
  8. 训练面试表达。 参考 references/interview-training.md。一次只问一个问题,等待用户回答,再追问和复盘。首版只处理文本或语音转写稿。
  9. 跟踪和复盘。 每次投递、回复、面试、拒信或新增 JD 后,更新 application-tracker.csvreview-log.md

辅助脚本

bash
python3 .agents/skills/job-ok/scripts/extract_resume_text.py \
  --input job-search-cases/<case>/raw/resume/resume.pdf \
  --output job-search-cases/<case>/raw/resume/resume.txt

python3 .agents/skills/job-ok/scripts/normalize_jobs.py \
  --input job-search-cases/<case>/raw/job-posts/jobs.md \
  --output job-search-cases/<case>/jobs.jsonl \
  --source-type user_paste

python3 .agents/skills/job-ok/scripts/score_job_matches.py \
  --profile job-search-cases/<case>/profile.yaml \
  --strengths job-search-cases/<case>/strengths.md \
  --jobs job-search-cases/<case>/jobs.jsonl \
  --output job-search-cases/<case>/job-matches.csv

输出标准

  • 优势挖掘:写明证据、可信度、岗位信号和缺失证据。
  • 岗位建议:同时写为什么投、为什么不投、简历重点和下一步用户动作。
  • 简历修改:输出建议,不输出不可验证的最终表述;缺证据内容标记为 needs_proof
  • 面试训练:检查结构、具体性、证据、岗位相关性、风险表达和可追问性。
  • 外部动作:结尾使用“用户手动确认后再执行”,除非用户报告完成,否则不要写“已投递”。

Install & Usage

1
Create the agents directory
mkdir -p .claude/agents
2
Save the agent file

Add the configuration to .claude/agents/job-ok.md

3
Invoke with @agent-name
@job-ok

Use Cases

Extract and organize a user's resume and experience into structured evidence files for job applications.
Match a user's profile against real job postings they provide, scoring fit and identifying gaps.
Generate a set of target role clusters with actionable 30-day improvement plans.
Track application progress and interview practice sessions in a local directory.
Review and optimize resume versions based on specific job descriptions.
Build an interview story bank from the user's verified experiences.

Usage Examples

1

/job-ok intake my resume is at ./resume.pdf and I'm targeting data analyst roles in Shanghai

2

/job-ok match these job postings from jobs.jsonl against my profile

3

/job-ok start interview practice for the role at ByteDance using my story bank

View source on GitHub
apiagent

Security Audits

LicenseUnknownSourceWarnRepositoryPass

Frequently Asked Questions

What is job-ok?

Job OK is a local skill for Chinese job seekers, especially students and early-career users, that helps organize real experiences into verifiable evidence for job matching, resume optimization, application tracking, and interview practice. It prioritizes evidence-based conclusions, manual user confirmation for external actions, and strict boundaries against fabricating experience or auto-submitting applications.

How to install job-ok?

To install job-ok: create the agents directory (mkdir -p .claude/agents), then add the config to .claude/agents/job-ok.md. Finally, @job-ok in Claude Code.

What is job-ok best for?

job-ok is a agent categorized under General. It is designed for: api, agent. Created by GresonKwan.

What can I use job-ok for?

job-ok is useful for: Extract and organize a user's resume and experience into structured evidence files for job applications.; Match a user's profile against real job postings they provide, scoring fit and identifying gaps.; Generate a set of target role clusters with actionable 30-day improvement plans.; Track application progress and interview practice sessions in a local directory.; Review and optimize resume versions based on specific job descriptions.; Build an interview story bank from the user's verified experiences..