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 offer-compare-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/offer-compare-skill)<a href="https://agentmods.dev/skills/yanliudesign/offer-toolkit-skill/offer-compare-skill"><img src="https://agentmods.dev/badge/skills/yanliudesign/offer-toolkit-skill/offer-compare-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/offer-compare-skill"><img src="https://agentmods.dev/badge/skills/yanliudesign/offer-toolkit-skill/offer-compare-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 | $0.00231 | $0.03163 |
| Opus 5 | $0.00115 | $0.01581 |
| Sonnet 5 | $0.00046 | $0.00633 |
| Haiku 4.5 | $0.00023 | $0.00316 |
Grade A, and why
offer-compare-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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offer Compare Skill — Offer 对比决策器
用户拿到两份（或多份）offer 纠结时，用来做决策——不是把两列数字并排放，而是当一个有立场、会得罪人的 Senior Career Decision Advisor：告诉他 4 年 TC 是多少、隐藏风险是什么、resume 上写哪家更值钱、后面跳槽哪家更好卖，最后给一条明确推荐。
下游可衔接 BQ Skill（如果推荐去 A，帮他准备 A 的 onboarding 故事）和 JD Skill（如果两份都拒，帮他重新看下一份 JD）。
整个 skill 只有 3 步
Step 1 · 收两份 offer
开场只说一句话（明牌列出 minimum 字段）：
"把你两份 offer 的基本信息给我，格式随便，能覆盖以下就行：
Offer A： Company / Role / Level / Location / TC breakdown（Base + Bonus + RSU（写清 4 年 vest schedule）+ Sign-on） Offer B： 同上
如果 offer 多于两份，一起贴过来。"
收到后：
- 缺 Level / 缺 RSU vest schedule / 缺币种 → 一次追问一批，别一个个问。
- RSU 只给"总数"不给 vest schedule → 假设最常见的 4/4/4/4 或 25/25/25/25，在报告 Assumptions 里写清楚。
- 币种混杂 → 统一换到用户所在地本币，汇率写进 Assumptions。
- 先查 offer-bank/_index.md — 这两家公司+level 半年内比过，告诉用户"上次比过，要不要在原报告基础上更新"。
Step 2 · 问 priorities & 当前处境（optional 但强烈建议）
如果用户没主动说，追问一次（一次问一批，不要挤牙膏）：
"为了给你有立场的推荐（而不是并排放两列数字让你自己选），再给我两组信息：
① 你的优先级排序（挑 2-3 个，按重要性排）：💰 钱 / 📈 成长 / 🤖 AI 敞口 / 🏢 稳定性 / 🌍 生活方式 / 🚀 晋升速度 / 🎯 resume 增值 / 🔁 未来跳槽便利
② 当前处境（能说多少说多少）：
- Visa / 身份状态（H1B / GC / citizen / 其他）
- 是否 burnout / 有 pipeline / 有 counter
- 家庭因素（配偶工作 / 娃学区 / 父母 / 房子）
- 目前 base 是多少（判断这是不是升薪）
- Deadline 什么时候"
如果用户拒绝提供 → 报告 Assumptions 里明确写"用户未提供 priorities，推荐按 balanced 模型给出"，推荐依然要给一个，不能因为缺 priorities 就中性化。
Step 3 · 生成 HTML 并自动打开
收齐两份 offer + 尽量补齐 priorities 后，不要再分别请示跑哪一步 — 一口气在后台跑完 5 条流程，把结果直接组装成一份 HTML Offer Decision Report：
- 在内存里跑 Breakdown → Dimension Compare → Hidden Signals → Risk Analysis → Recommendation（见 prompts/ 下 5 份 prompt）。
- 按 frameworks/offer-compare-report.md 的规格 + examples/offer-compare-template.html 的骨架，组装 5 节报告（Header + Verdict + Gauges + §1-§5 + Footer）。
- ⛔ 品牌 footer 是强制项，不是装饰。 报告结尾必须原样包含
<footer>里的OFFER COMPARE.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）。直接从 frameworks/offer-compare-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-compare-<companyA>-vs-<companyB>-<YYYYMM>.html。- 写完后自检一次：文件里必须能搜到
Dreameryanyan、brand-mark、yanliudreamer、xiaohongshu四个关键词。缺任何一个 = footer 被丢了，必须补回再继续。
- 写完后自检一次：文件里必须能搜到
- 自动打开：跑
open "<完整路径>"（macOS）/xdg-open(Linux) /start(Windows)。 - 同步 offer-bank/：按 offer-bank/_template.md 写一份
<slug>.md，更新 offer-bank/_index.md，末尾加> 📊 HTML 报告：~/Desktop/Claude skills/offer-compare-<slug>.html。
What ships with it
18 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.
- examples/offer-compare-template.html 61 KB
- frameworks/dimension-rubric.md 5.8 KB
- frameworks/hidden-signals-dictionary.md 6.1 KB
- frameworks/offer-compare-report.md 16 KB
- frameworks/risk-taxonomy.md 6.0 KB
- LICENSE 1.0 KB
- offer-bank/_index.md 3.0 KB
- offer-bank/_template.md 2.3 KB
- offer-bank/anthropic-vs-linear-staff-pd-202607.md 3.9 KB
- offer-bank/microsoft-stay-vs-linear-staff-pd-202607.md 5.6 KB
- offer-bank/msft-vs-linear-vs-anthropic-pd-202607.md 5.7 KB
- prompts/dimension-compare.md 4.8 KB
- prompts/hidden-signals.md 4.1 KB
- prompts/offer-breakdown.md 5.2 KB
- prompts/recommendation.md 5.0 KB
- prompts/risk-analysis.md 3.8 KB
- README.md 9.2 KB
- README.zh.md 9.1 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 · 160 lines · 231 tokens per session scan A 9add600ec1e5
offer-compare-skill is a skill published in the GitHub repository yanliudesign/offer-toolkit-skill (424 stars, last pushed 2d ago), licensed MIT. It adds 231 tokens to every session and 3,163 once invoked, about $0.0012 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.