jd-import

A command for importing job descriptions from web pages or files into structured information. A job description, or JD, lists a role’s duties, requirements, and details such as location.

In plain words
What is it for?
Use it to import individual or batches of job postings from LinkedIn, Indeed, Glassdoor, company websites, text, Markdown, Word, or CSV files.
Why use it?
Copying job postings by hand is slow and makes it harder to process many applications consistently. The command extracts the relevant details from supported sources.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/huifer/claude-code-interview/jd-import
Clone the repo
git clone --depth 1 https://github.com/huifer/claude-code-interview

Made for: Claude Code.

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.03504
Opus 5 $0.00020 $0.01752
Sonnet 5 $0.00008 $0.00701
Haiku 4.5 $0.00004 $0.00350

Measured 2d ago against content hash 5bf002167f58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jd-import scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/jd-import.md · 560 lines

How it starts

The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.

智能JD导入

智能导入职位描述(JD),支持多种来源和格式。

使用方法

从URL导入单个JD

# 从LinkedIn导入
/jd/import https://www.linkedin.com/jobs/view/123456789/

# 从Indeed导入
/jd/import https://www.indeed.com/viewjob?jk=123456789

# 从公司官网导入
/jd/import https://careers.google.com/jobs/results/123456/

从文件导入JD

# 从文本文件导入
/jd-import ~/Downloads/google-jd.txt

# 从Markdown文件导入
/jd-import ~/Downloads/amazon-jd.md

# 从Word文档导入
/jd-import ~/Downloads/meta-jd.docx

批量导入

# 批量导入多个URL
/jd-import --batch ~/jd-urls.txt

# 批量导入目录中的所有JD文件
/jd-import --batch-dir ~/Downloads/jds/

# 从CSV导入
/jd-import --csv ~/job-applications.csv

交互式导入

# 交互式粘贴JD
/jd-import --interactive

# 然后粘贴JD文本

支持的平台

1. LinkedIn

URL格式:

https://www.linkedin.com/jobs/view/[job-id]/
https://www.linkedin.com/jobs/search/?keywords=...

提取内容:

  • ✅ 职位名称和级别
  • ✅ 公司和团队信息
  • ✅ 职位描述全文
  • ✅ 技能要求
  • ✅ 职位详情(地点、类型、级别)
  • ⚠️ 薪资信息(如果提供)

处理方式:

  1. 读取LinkedIn页面
  2. 提取职位详情区域
  3. 清理HTML标签
  4. 结构化存储

2. Indeed

URL格式:

https://www.indeed.com/viewjob?jk=[job-id]
https://www.indeed.com/company/[company-name]/jobs

提取内容:

  • ✅ 完整职位描述
  • ✅ 公司信息
  • ✅ 职位类型和地点
  • ✅ 薪资范围(常见)

3. Glassdoor

URL格式:

https://www.glassdoor.com/job-listing/[job-title]-[company]-JI.htm

提取内容:

  • ✅ 职位描述
  • ✅ 薪资估算
  • ✅ 公司评价和评分

4. 公司官网

URL格式:

https://careers.company.com/jobs/123456
https://jobs.company.com/position/123456
https://www.company.com/careers/openings/...

处理方式:

  • 自动检测常见ATS系统(Workday, Greenhouse, Lever)
  • 针对性提取内容
  • 保存原始链接

5. 招聘网站

支持:

  • Boss直聘 (bosszhipin.com)
  • 拉勾网 (lagou.com)
  • 猎聘 (liepin.com)
  • 其他本地招聘平台

导入流程

步骤 1: 检测来源类型

# 分析输入类型
URL? → 自动检测平台
File? → 读取文件内容
Text? → 直接处理

步骤 2: 获取JD内容

# URL方式
使用 webReader MCP 工具:
- 读取网页内容
- 转换为Markdown
- 提取职位信息

# 文件方式
- 读取文件内容
- 检测格式(.txt, .md, .html, .docx)
- 解析文本

步骤 3: 提取关键信息

{
  "extraction": {
    "company_name": "自动检测或手动确认",
    "position_title": "从JD提取",
    "position_level": "从JD推断 (Junior/Mid/Senior/Staff)",
    "location": "提取工作地点",
    "description": "清理后的完整JD文本",
    "salary": "提取薪资信息(如果存在)",
    "skills": "技能列表"
  }
}

Read the full file on GitHub · 560 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 560 lines · 40 tokens per session scan A 5bf002167f58

Subscribe to this mod's changes

jd-import is a command published in the GitHub repository huifer/claude-code-interview (23 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 3,504 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.