job-detail-extraction
Extract clean, source-grounded job, company, and business-registration fields from a noisy BOSS job-detail page captured as plain text.
Skill by kyle-kw
Chalk Labs
Need help deploying job-detail-extraction?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kyle-kw-job-detail-extraction
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/job-detail-extraction
What's inside
- Skill name
job-detail-extraction- Description
- Extract clean, source-grounded job, company, and business-registration fields from a noisy BOSS job-detail page captured as plain text.
- License
- MIT
- Instructions
- 57 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# 岗位详情结构化提取
你会收到一条 BOSS 岗位的基础元数据和 `rawDetailText`。原文可能同时包含职位正文、招聘者姓名与活跃状态、竞争力分析、安全提示、公司介绍、工商信息、工作地址、推荐职位、城市导航等页面噪声。
## 提取目标
只依据 `rawDetailText`,提取以下五类信息:
1. `jobDescription`:职位概述或未归入职责、要求的岗位正文。不要复制已经放入 `responsibilities` 或 `requirements` 的列表;若原文没有独立概述则返回空字符串。
2. `responsibilities`:岗位职责、主要职责、工作内容、What you will do 等段落,按原文中的独立要点拆为字符串数组。
3. `requirements`:任职要求、职位要求、任职资格、Requirements、Qualifications、加分项等段落,按独立要点拆为字符串数组;加分项需保留“加分项:”前缀。
4. `companyIntroduction`:仅提取明确位于“公司介绍/公司简介/About the company”等标题下的内容。
5. `businessInformation`:仅提取明确位于“工商信息”段落、且紧跟对应标签出现的值。
## 实际页面切分规则
- 标题可能使用中文括号、方括号、冒号、中英文或不同写法,例如“【岗位职责】”“主要职责”“职位要求”“Requirements / 任职要求”。按语义识别,不依赖单一固定标题。
- “职位描述”通常只是整个职位区的总标题,不等于所有后续页面文本。
- 遇到“公司介绍”后,后续内容不得再归入职位描述、岗位职责或任职要求。
- 遇到“工商信息”后,只读取工商字段,直到“查看全部”“工作地址”“点击查看地图”“更多职位”等边界。
- 删除“微信扫码分享”“举报”、技能标签堆叠、招聘者姓名/职位/活跃状态、竞争力分析、BOSS 安全提示、工作地址、地图、推荐职位、精选职位、搜索和城市导航等噪声。
- 保留原文事实、数字、技术名词、学历、年限和限定条件;只做去噪、断句与最小必要的格式整理,不扩写、不评价。
- 去除重复要点,但不要把两个不同条件合并成一个模糊总结。
## 事实完整性规则
1. 严禁根据公司名、行业常识、基础元数据或模型知识补全原文没有的信息。
2. 缺失字段必须返回空字符串或空数组,不能返回“未知”“暂无”“未提供”等占位文字。
3. 工商字段标签存在但值为空、为 `-`、被截断或无法和标签可靠配对时,返回空字符串。
4. 不要把招聘者姓名误识别为法定代表人,不要把岗位发布日期误识别为成立日期。
5. 不要把公司规模、融资阶段、行业、工作地址写入工商信息,除非输出合约中存在对应字段;当前合约不存在这些字段。
6. 输出必须是一个 JSON 对象,不得包含 Markdown、注释或额外说明。
## 输出合约
```json
{
"jobDescription": "",
"responsibilities": [""],
"requirements": [""],
"companyIntroduction": "",
"businessInformation": {
"companyName": "",
"legalRepresentative": "",
"establishedDate": "",
"companyType": "",
"operatingStatus": "",
"registeredCapital": ""
},
"extractedAt": "",
"extractorVersion": "job-detail-extraction@1.0.0"
}
```
`extractedAt` 可返回空字符串,应用会在保存时写入本地时间;`extractorVersion` 必须使用合约中的固定值。From kyle-kw/ai-job-app, MIT.
More from kyle-kw/ai-job-app
- 0.777score
interview-preparation
kyle-kw
Generate a focused interview preparation plan from aggregated local job-market statistics and, when available, confirmed resume facts.
SkillAFreshness: A★ 107Claude Code +9 - 0.777score
job-fit
kyle-kw
Evaluate a job posting against a confirmed resume and stated job preferences, producing evidence-backed fit dimensions, hard constraints, strengths, gaps…
SkillAFreshness: A★ 107Claude Code +9 - 0.777score
resume-extraction
kyle-kw
Extract a PDF, DOCX, pasted resume, or RenderCV YAML into a structured RenderCV-compatible candidate profile with source-backed facts and confidence.
SkillAFreshness: A★ 107Claude Code +9 - 0.777score
greeting-message
kyle-kw
Generate one concise Chinese greeting for a recruiter using a target job and confirmed resume facts.
SkillAFreshness: A★ 107Claude Code +9 - 0.773score
report-competitiveness
kyle-kw
Classify how a trusted master resume covers a fixed list of aggregated market skills using verifiable resume paths and confirmed fact IDs.
SkillAFreshness: A★ 107Claude Code +9 - 0.773score
resume-chat
kyle-kw
Propose reviewable structured edits to a local master resume from a user conversation, optionally using one job or a server-resolved local market sample as…
SkillAFreshness: A★ 107Claude Code +9 - 0.773score
resume-coverage
kyle-kw
Classify how a trusted resume covers a fixed set of job requirements using explicit resume paths and confirmed fact IDs.
SkillAFreshness: A★ 107Claude Code +9
Signals
- Stars
- 107
- Forks
- 5
- Open issues
- 1
- Last commit (this folder)
- Jul 12, 2026 (3 months ago)
- Last release
- Oct 10, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kyle-kw/ai-job-app
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kyle-kw
- 0.777score
interview-preparation
kyle-kw
Generate a focused interview preparation plan from aggregated local job-market statistics and, when available, confirmed resume facts.
SkillAFreshness: A★ 107Claude Code +9 - 0.777score
job-fit
kyle-kw
Evaluate a job posting against a confirmed resume and stated job preferences, producing evidence-backed fit dimensions, hard constraints, strengths, gaps…
SkillAFreshness: A★ 107Claude Code +9 - 0.777score
resume-extraction
kyle-kw
Extract a PDF, DOCX, pasted resume, or RenderCV YAML into a structured RenderCV-compatible candidate profile with source-backed facts and confidence.
SkillAFreshness: A★ 107Claude Code +9 - 0.777score
greeting-message
kyle-kw
Generate one concise Chinese greeting for a recruiter using a target job and confirmed resume facts.
SkillAFreshness: A★ 107Claude Code +9 - 0.773score
report-competitiveness
kyle-kw
Classify how a trusted master resume covers a fixed list of aggregated market skills using verifiable resume paths and confirmed fact IDs.
SkillAFreshness: A★ 107Claude Code +9 - 0.773score
resume-chat
kyle-kw
Propose reviewable structured edits to a local master resume from a user conversation, optionally using one job or a server-resolved local market sample as…
SkillAFreshness: A★ 107Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get job-detail-extraction running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
job-detail-extraction skill. Agent Mart. https://agentmart.dev/skills/kyle-kw-job-detail-extraction (last updated 2026-10-24)