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.
npx skills add yanliudesign/offer-toolkit-skill --skill job-hunt-skillgit clone --depth 1 https://github.com/yanliudesign/offer-toolkit-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yanliudesign/offer-toolkit-skill/job-hunt-skill)<a href="https://agentmods.dev/skills/yanliudesign/offer-toolkit-skill/job-hunt-skill"><img src="https://agentmods.dev/badge/skills/yanliudesign/offer-toolkit-skill/job-hunt-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yanliudesign/offer-toolkit-skill/job-hunt-skill"><img src="https://agentmods.dev/badge/skills/yanliudesign/offer-toolkit-skill/job-hunt-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00167 | $0.01960 |
| Opus 5 | $0.00084 | $0.00980 |
| Sonnet 5 | $0.00033 | $0.00392 |
| Haiku 4.5 | $0.00017 | $0.00196 |
Grade A, and why
job-hunt-skill 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
job-hunt-skill
把“帮我看看有哪些工作”变成一份可以持续搜索、比较和更新的职位数据库,而不是一次性的推荐答案。
简历 / 目标方向 / 种子 JD
↓
搜索画像 → 查询矩阵 → 公开候选池 → 去重与证据分层
↓
完整 job-hunt-skill HTML 报告 → 搜索 / 筛选 / 打开职位 → 选择深评对象
职责边界
- 负责批量发现、采集公开信息、去重、初筛、证据分层、排序和生成职位清单。
- 默认保留所有通过硬条件的唯一职位;不要擅自压缩成 5–10 个 shortlist。
- 不自动点击 Apply,不填写表单,不发送消息,不代表用户投递。
- 不索取或处理密码、验证码、Cookie、session token 或其他登录凭据。
- 遇到登录墙、验证码、HTTP 429、robots 限制时停止该访问路径;切换到公开公司招聘页、公开搜索结果或可点击查询链接,不尝试绕过。
- 不把职位发现扩写成完整单岗位 Offer Strategy。用户选中岗位后再交给
job-description-skill。
0. 判断输入是否足够
优先使用用户已经提供的材料,不重复索取:
- 简历:PDF、Word、HTML 或纯文本均可。
- 目标:title、level、领域、地点、工作方式。
- 可选种子 JD:用于补充岗位语义,不得反向伪造简历能力。
- 可选已有链接:用于合并、补充或更新旧清单。
若缺少会显著改变结果集的信息,一次只问一个问题,顺序如下:
- 目标 title / level
- 地点与 remote / hybrid / relocation
- 时间范围
- 必须排除的行业、公司、合同类型或签证门槛
默认值为最近 30 天、full-time、目标 level 上下浮动一级。最终报告必须显式写出默认值。
1. 建立搜索画像
只从用户材料提取有证据的能力,形成:
target_titles: []
adjacent_titles: []
level: ""
locations: []
workplace: []
date_posted: "30d"
employment_types: ["full-time"]
core_capabilities: []
domains: []
company_preferences: []
exclusions: []
seed_signals: []
向用户回显不超过 8 行的画像。若用户没有纠正,继续执行,不要求二次确认。
2. 生成互补查询矩阵
生成 6–12 组短查询,每组只放 1–2 个判别词:
- Exact title:目标 title + 地点
- Adjacent title:相邻 title + 地点
- Capability-led:title + 核心能力
- Domain-led:title + 领域
- Scope-led:title + platform / growth / 0-to-1 / enterprise 等 scope
- Company-led:用户偏好公司或相邻公司 + title
记录每组 query、URL、执行时间和来源。不要把所有同义词塞进一个查询,否则会系统性漏岗。
3. 发现公开职位
按以下优先级使用可访问来源:
- 具体职位页或公司官方招聘页
- LinkedIn 可公开访问的职位页与搜索结果
- 搜索引擎中的
site:linkedin.com/jobs/view结果 - 其他公开招聘页面
每条候选尽可能采集:
- title
- company
- canonical URL / job id
- location 与 workplace
- posted date / age
- salary,仅页面明确展示时记录
- JD 可见程度:full / partial / unavailable
- source 与 checked_at
按 canonical job id / URL 去重。没有 id 时,使用 normalized company + title + location,并保留证据更完整、更新时间更新的记录。
停止条件:
- 查询矩阵全部跑完;或
- 每组已查看前 2 页 / 前 25 条;或
- 当前来源触发访问限制。
不要为了凑数量保留明显违反地点、level、employment type 或硬门槛的岗位。
4. 严格区分事实与推断
读取 references/evidence-ranking.md,为每条字段标记证据状态:
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/report-spec.md 2.6 KB
- evals/evals.json 1.4 KB
- examples/cn/job-search-01.png 404 KB
- examples/cn/job-search-02.png 600 KB
- examples/cn/job-search-03.png 568 KB
- examples/cn/job-search-04.png 442 KB
- examples/cn/job-search-05.png 372 KB
- examples/en/job-search-01.png 304 KB
- examples/en/job-search-02.png 480 KB
- examples/en/job-search-03.png 500 KB
- examples/en/job-search-04.png 471 KB
- examples/en/job-search-05.png 368 KB
- README.md 5.7 KB
- README.zh.md 5.5 KB
- references/evidence-ranking.md 2.2 KB
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.
- 12d ago First seen · 179 lines · 167 tokens per session scan A 478df5f417a5
job-hunt-skill is a skill published in the GitHub repository yanliudesign/offer-toolkit-skill (425 stars, last pushed yesterday), licensed MIT. It adds 167 tokens to every session and 1,960 once invoked, about $0.0008 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.
Other skills, from other repositories
vitaecontext-build
Build, normalize, and maintain the user's Career Context file so downstream platform outputs stay factual and consistent. Use when the user wants an agent to consolidate CV data, LinkedIn exports, GitHub history, project summaries, bio facts, achievements, or positioning into one professional source of truth before…
yc-job-tracker
Track and filter YC startup job listings for AI/ML engineering roles. Builds a daily-refreshed local database of relevant jobs with scoring and alerts for new postings.
kochab
Kochab, a personalized resume-based job-search assistant that runs a recurring scan and everything downstream of it. Use when the user wants to start or run a job search, shares a resume, or says "set up my job scan," "find roles that fit my resume," or "what should I apply to." Also use to tailor a resume, draft a…
life-designer-pro
Guide a private, adaptive life-design conversation and create an integrated Life Designer Pro Blueprint covering work, relationships and professional network, health, learning, creativity, community, finances, future paths, experiments, reviews, a visual life map, and optional image prompts. Use when a user asks to…
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".