Job Ok

What it does

When your agent uses it

• Helping a Chinese job seeker
• Especially students
• Early-career users
• Prepare job applications with an agent without fabricating experience

Example prompts

• “/job-ok”

Requirements

• Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

1. 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. 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. 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. 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. 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…
6. 6评分和短名单。 用 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. 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. 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. 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.csv 和 review-log.md。

What it can do on your machine

Read from SKILL.md and the folder at commit c5da0c6. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Job Ok loads about 745 tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 98 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~62

When it runs · the whole SKILL.md, loaded when a task matches

~745

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from GresonKwan/JobOK at commit c5da0c6, republished under its MIT licence (© GresonKwan). 98 words, ~745 tokens.

name

job-ok

description

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.

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

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

© GresonKwan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 39 other files (scripts, references, assets) in the repository root of GresonKwan/JobOK.

• SKILL.md
• .gitignore
• CHANGELOG.md
• CONTRIBUTING.md
• LICENSE
• README.md
• agents/openai.yaml
• assets/templates/application-tracker.csv
• assets/templates/brief.yaml
• assets/templates/experience-assets.md
• assets/templates/interview-practice.md
• assets/templates/interview-story-bank.md
• assets/templates/profile.yaml
• assets/templates/review-log.md
• assets/templates/sample-jobs.md
• assets/templates/strengths.md
• assets/templates/target-roles.csv
• docs
• … and 22 more

Open the folder on GitHubat commit c5da0c6