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-description-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-description-skill)<a href="https://agentmods.dev/skills/yanliudesign/offer-toolkit-skill/job-description-skill"><img src="https://agentmods.dev/badge/skills/yanliudesign/offer-toolkit-skill/job-description-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-description-skill"><img src="https://agentmods.dev/badge/skills/yanliudesign/offer-toolkit-skill/job-description-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 | $0.00150 | $0.03409 |
| Opus 5 | $0.00075 | $0.01705 |
| Sonnet 5 | $0.00030 | $0.00682 |
| Haiku 4.5 | $0.00015 | $0.00341 |
Grade A, and why
job-description-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 11d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Description Skill
把一份 JD 从「招聘话术」翻译成「你能用的求职情报」，一次性产出一份单文件 HTML Offer Strategy Report，自动在浏览器打开。
下游可一键接 Resume Skill（拿着 Gap / Tailor 结果继续打磨简历）和 BQ Skill（拿着预测题目去练故事），形成完整求职链路。
整个 skill 只有 3 步
Step 1 · 贴 JD
开场只说一句话：
"把你想分析的 Job Description 链接或全文 贴给我。链接抓不到内容就直接粘贴 JD 文本。"
收到后：
- 链接 → 尝试抓取；抓不到 → 让用户粘全文，别根据公司名瞎猜 JD。
- 同时确认 公司名 / 岗位 / Level（JD 没明写就追问一次）。
- 先查 jd-bank/_index.md — 同公司同岗位半年内分析过，告诉用户"上次解码过，要不要直接复用"。
Step 2 · 给简历或 LinkedIn
三选一，明牌列出来：
"为了算匹配度 / 出 Gap / 预测面试题，需要了解你。三选一：
- 🅰️ 上传 / 粘贴简历全文（PDF / Word / 文本都行）— 强烈推荐，结果最准
- 🅱️ 粘贴你的 LinkedIn 全文（不是只给 URL，要全文）
- 🅲️ 简略介绍一下自己（还没有简历的情况）"
如果用户选 🅲️，一次问一个问题，别一次列 6 个：当前 Title + 年限 → 行业 → 近 2-3 段经历（公司 + 负责什么 + 1 个最亮成果）→ 最强 1-2 个技能 → 想往哪个方向走。
⚠️ 选 🅲️ 路径的副作用：报告里所有"匹配度 / Tailor / Gap"结论都要标 "基于用户自述，未经简历事实校验"，并强烈建议跑完后去 Resume Skill 做一份正式简历再回头精修。
Step 3 · 生成 HTML 并自动打开
收齐 JD + 简历后，不要再分别请示用户跑 Decode / Match / Predict / Should I Apply — 一口气在后台跑完 5 条流程（prompts/ 下的 5 份文件），把结果直接组装成一份 HTML Offer Strategy Report：
- 在内存里跑 Decode → Match → Predict → Should I Apply（Tailor（简历定向调整） 只取关键 diff，简历整体打磨交给 Resume Skill）。
- 按 frameworks/offer-strategy-report.md 的规格 + examples/offer-strategy-template.html 的骨架组装一份 10 节报告（TL;DR · 关键指标 · 1-10）。
- ⛔ 品牌 footer 是强制项，不是装饰。 报告结尾必须原样包含
<footer>里的JD SKILL.brand mark +Created by Dreameryanyan副标题 + LinkedIn / X / 小红书三个社交按钮（含对应 CSS：.brand-block/.brand-mark/.socials/.foot-meta）。这是作者署名，无论报告多长、数据多少都不许删或简化。生成时直接从 frameworks/offer-strategy-report.md 末尾「📌 强制 Footer 区块」整段抄过去。
- ⛔ 品牌 footer 是强制项，不是装饰。 报告结尾必须原样包含
- 写到
~/Desktop/Claude skills/offer-strategy-<company>-<role>-<YYYYMM>.html。- 写完后跑两道自检，任一道失败 = 报告不合格，必须重写这几块再继续（不要跳过校验直接宣称“已生成”）：
- ① Footer 自检 — 文件里必须能搜到
Dreameryanyan、brand-mark、yanliudreamer、xiaohongshu四个关键词，缺任一 = footer 被丢了。 - ② 双语自检 —
<html lang="en">必须默认为en（不允许zh/zh-CN），且grep -c 'data-lang="en"'与grep -c 'data-lang="zh"'数量相等且 ≥ 80。少于 80 = 模型又把内文写成了单语，已知失败模式，参见铁律四。双语 span 对的写法与适用范围见 frameworks/offer-strategy-report.md。
- ① Footer 自检 — 文件里必须能搜到
- 写完后跑两道自检，任一道失败 = 报告不合格，必须重写这几块再继续（不要跳过校验直接宣称“已生成”）：
- 自动打开：跑
open "<完整路径>"（macOS）/xdg-open(Linux) /start(Windows)，让 HTML 直接在浏览器弹出来。 - 同步 jd-bank/：按 jd-bank/_jd-template.md 写一份
<slug>.md，更新 jd-bank/_index.md，文件末尾加一行> 📊 HTML 报告：~/Desktop/Claude skills/offer-strategy-<slug>.html。
What ships with it
28 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.
- .gitignore 360 B
- docs/en/.gitkeep 126 B
- docs/en/demo.mp4 15615 KB
- docs/en/openai-report.png 576 KB
- docs/en/preview.gif 1077 KB
- docs/report-preview-en-v2.png 2672 KB
- docs/report-preview-en.png 576 KB
- docs/report-preview-zh-v2.png 2378 KB
- docs/report-preview-zh.png 398 KB
- docs/zh/.gitkeep 110 B
- docs/zh/demo.mp4 14261 KB
- docs/zh/openai-report.png 615 KB
- docs/zh/preview.gif 1314 KB
- examples/offer-strategy-template.html 52 KB
- frameworks/decode-patterns.md 6.1 KB
- frameworks/go-no-go.md 5.6 KB
- frameworks/match-rubric.md 5.3 KB
- frameworks/offer-strategy-report.md 23 KB
- frameworks/resume-tailoring.md 7.4 KB
- jd-bank/_index.md 4.0 KB
- jd-bank/_jd-template.md 2.8 KB
- prompts/interview-predictor.md 5.1 KB
- prompts/jd-decoder.md 5.9 KB
- prompts/match-score.md 5.0 KB
- prompts/resume-tailor.md 5.5 KB
- prompts/should-i-apply.md 6.7 KB
- README.md 9.3 KB
- README.zh.md 8.7 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.
- 11d ago First seen · 161 lines · 150 tokens per session scan A 3fd961c57356
job-description-skill is a skill published in the GitHub repository yanliudesign/offer-toolkit-skill (425 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 3,409 once invoked, about $0.0007 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
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
exam-ingest
A workspace setup tool for exam preparation. It reads PDFs, Word documents, presentations, spreadsheets, images, text files, and Markdown, then creates chapter notes, a question bank, and tracked preparation data.
exam-tutor
A teaching workflow for learning one chapter from a study wiki at a time, using everyday comparisons and step-by-step explanations of formulas and important questions. TDD is not involved here; the material concerns guided study and exam preparation.
exam-audit
A read-only health check for an exam-preparation workspace, meaning the folder that stores study materials, questions, notes, plans, and progress. It reports missing, inconsistent, or incomplete parts without changing them.
exam-cram-coach
A structured last-minute exam study workflow that turns course materials or a syllabus into chapter notes, practice questions, grading, and progress tracking.
exam-review
Clear recorded mistakes/confusions before the exam. Replay only existing records; teach no new chapter and invent no question.