yanliudesign/offer-toolkit-skill / job-hunt-skill
job-hunt-skill
Verified批量发现、整理和持续维护求职岗位清单。根据用户的简历、目标方向或种子 JD,搜索 LinkedIn 与公开网页,去重并建立尽量完整的候选池,用证据区分已核验事实和方向性推断,最后生成可搜索、可筛选的单文件 HTML job-hunt-skill 报告。用户说‘帮我批量找岗位’、‘整理职位清单’、‘使用 job-hunt-skill’、‘根据简历搜工作’、‘把这些 LinkedIn 职位做成表格’、‘持续跟踪岗位’时必须使用。只发现和分析岗位;绝不自动申请、处理登录凭据或绕过访问限制。
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 5.7 KB |
| README.zh.md | markdown | 5.5 KB |
| SKILL.md | skill md | 7.3 KB |
| assets/report-spec.md | markdown | 2.6 KB |
| evals/evals.json | config | 1.4 KB |
| examples/cn/job-search-01.png | binary | 403.6 KB |
| examples/cn/job-search-02.png | binary | 600.2 KB |
| examples/cn/job-search-03.png | binary | 568.0 KB |
| examples/cn/job-search-04.png | binary | 442.1 KB |
| examples/cn/job-search-05.png | binary | 372.5 KB |
| examples/en/job-search-01.png | binary | 304.1 KB |
| examples/en/job-search-02.png | binary | 480.2 KB |
| examples/en/job-search-03.png | binary | 500.3 KB |
| examples/en/job-search-04.png | binary | 470.9 KB |
| examples/en/job-search-05.png | binary | 368.4 KB |
| references/evidence-ranking.md | markdown | 2.2 KB |
assets/report-spec.md
View on GitHub# job-hunt-skill HTML Contract
Generate one self-contained HTML file with inline CSS and JavaScript. Do not require a build step, external framework, server, or remote font.
## Data shape
Each normalized job record should support:
```js
{
id: "",
title: "",
company: "",
url: "",
source: "",
firstSeen: "",
lastChecked: "",
posted: "",
postedEvidence: "unknown",
location: "",
workMode: "",
salary: "",
domains: [],
reviewStatus: "discovered",
match: "未深评",
reason: "",
reasonType: "directional",
gap: "",
gapType: "directional",
priority: 0
}
```
Keep source data in one clearly named JavaScript collection so a later run can parse and update it.
## Table
Use six columns:
1. 职位 / 公司 / 推荐理由 / Gap
2. 发布日期
3. 地点 / 工作方式
4. 薪资范围
5. 匹配度
6. Open link icon
Place searchable domain tags immediately beside the company name. Do not show job ids or Tier A/B badges in the visible row.
Unknown salary should be an empty cell. Use `待核验` for unknown date, location, or work mode when an empty cell would be ambiguous.
## Interactions
- Search title, company, domain tags, reason, gap, location, salary, and posted information.
- Include filters for all, deep reviewed, priority, AI / Agentic, Principal, and Staff when those categories exist.
- Update visible count after every search/filter change.
- Open job links in a new tab with `rel="noreferrer"` or `rel="noopener"`.
- Make keyboard focus visible.
- Respect `prefers-reduced-motion`.
## Visual hierarchy
- Treat this as a dense operational tool, not a marketing landing page.
- Keep the first viewport focused on search context and the table.
- Use restrained surfaces, compact rows, and strong column headers.
- Domain tags need distinct color families but must remain secondary to title and company.
- Keep labels square or lightly rounded; avoid decorative pill overload.
- Preserve usable horizontal scrolling on narrow screens.
## Evidence copy
- Deep evidence label: `为什么适合你`
- Directional label: `方向性理由`
- Gap label: `需要补足的 Gap`
- Unknown match: `未深评`
- Unknown field: `待核验`
Add a visible evidence note explaining that unreviewed does not mean unqualified and unknown values were not guessed.
## Static validation
Check all of the following before delivery:
- Inline script parses with `new Function(script)`.
- Rendered or generated row count matches unique job count.
- Every row has six cells.
- No `.tier-badge` element exists by default.
- Search index includes domains, reason, and gap.
- Salary values appear only for records with evidence.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |