offer-compare-skill: Workflow Automation for AI Agents | OpenAgentSkill

Overview

Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。

Read full documentation

Source documentation, not instructions for this website. Review permissions before running any commands.

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。
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。
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。

最后一句收尾：

"报告已生成并在浏览器打开 ✅ · 📊 ~/Desktop/Claude skills/offer-compare-<slug>.html · 内置 EN / 中文 切换 + Export PDF / Export Markdown · 已存进 offer-bank/，下次提到自动复用

下一步：

决定去 A → 转 BQ Skill 挖 onboarding 90 天故事 + 谈判 talking points

两个都拒 → 转 JD Skill 分析下一份 JD

想再补 Priorities / 当前情况 → 告诉我，我重新生成"

三条铁律（内部 5 条流程跑的时候都要守）

铁律一 · 不许中性。 用户拿两份 offer 来找你，不是要看两列数字并排放。必须给一条明确推荐，同时用 "If you are X → A / If you are Y → B" 兜底另一类人。Verdict 结论明确到「推荐 A」或「推荐 B」或「都拒，回去谈」，不允许「都不错，看你自己」。

铁律二 · 数字必须给区间 + 显式假设。

4 年 TC 计算必须给区间（RSU refresh 有无 / 股价 ±30% 波动 / 奖金浮动 → 区间下沿到上沿）。
所有假设（RSU vest schedule / 币种汇率 / bonus target / RSU refresh 假设）在报告顶部 Assumptions 区每条独立列出，明确写"任一不对，告诉我重新生成"。
单点数字（"4 年 TC = $1.24M"）是这类工具最大的可信度杀手 — 永远给 $1.05M ~ $1.42M 这样的区间。

铁律三 · 不替用户编事实、不装作知道公司内部情报。

公司信号（team health / manager style / promo speed）只能从公开信息 + 用户提供推断，标"我从 ___ 推断"。
Levels.fyi / Blind / Glassdoor 的数据可以引用，但要标注来源年份 + 是否可能过期。
用户没说过的数字（比如 base、股价、目前包）→ 标 [需用户补充]，别编。
公司估值 / 财报数据可以做 web research（如果 skill 环境有 web 权限），无 web 就标"用户可自行核对"。

内部流程（用户看不到，由 Step 3 调用）

流程	干什么	Prompt 文件
1 · Breakdown	拆 Base / Bonus / RSU / Sign-on / 4-year TC 区间 / equity risk / stability	prompts/offer-breakdown.md
2 · Dimension Compare	7 维打分（💰 comp / 📈 growth / 🤖 AI / 🏢 company / 👤 manager / 🔁 promo / 🌍 lifestyle）	prompts/dimension-compare.md
3 · Hidden Signals	5 条隐藏信号（front-loaded / long-term upside / uncertainty / resume value / switch-out）	prompts/hidden-signals.md
4 · Risk Analysis	每份 offer 显式列 4-6 条 risk（equity / role / team / market / life）	prompts/risk-analysis.md
5 · Recommendation	一条明确推荐 + tradeoff 说明 + "If X → A / If Y → B" 分叉	prompts/recommendation.md

这 5 步在 Step 3 里被一次性调用，结果全塞进同一份 HTML 报告。 用户看不到「现在在跑第几步」这种内部状态。

如果用户明确只要某一步（"只算 4 年 TC" / "只给我推荐一条不要 HTML"）→ 跳过 Step 3 的报告生成，直接吐这一步的纯文本结果。这是例外路径，不是默认。

Offer Bank

位置：本 skill 目录下 offer-bank/，每份决策一个 .md。
文件名：<companyA-slug>-vs-<companyB-slug>-<YYYYMM>.md，如 openai-vs-anthropic-senior-designer-202607.md。
frontmatter 必填：companies / roles / levels / candidate / decided_at / recommendation（A / B / walk-away / undecided）/ status（compared / decided / accepted / declined）。
offer-bank/_index.md 是反查表：按候选人、按决策时间、按结果分组。每次 Step 3 生成报告都要同步 _index.md。
用户回头说"上次那个 A vs B" → 先查 index，别让用户重新贴。

与其它求职 skill 的衔接

这个 skill 是求职链路的最后一环（拿到多份 offer 才用得上）：

JD Skill      → 这个岗位该不该投
Resume Skill  → 简历打磨
BQ Skill      → 面试准备
                    ↓ 拿到 offer
                    ↓ 又拿到第二份 offer
Offer Compare → 该去哪家？（本 skill）
                    ↓ 决定
BQ Skill      → 谈判 talking points + onboarding 90 天故事

推荐把本 skill 目录放进 offer-toolkit-skill/（跟 job-description-skill/ / resume-skill/ / bq-skill/ 平级），或独立安装皆可 — 每个都是自包含的。

参考文件（按需读取，别一次全加载）

Prompts（5 条内部流程的执行脚本）

Frameworks（知识词典 + 报告规格）

frameworks/dimension-rubric.md — 7 维评分标准 + 权重
frameworks/hidden-signals-dictionary.md — 5 条隐藏信号的判定规则
frameworks/risk-taxonomy.md — 5 大类 risk 词典
frameworks/offer-compare-report.md — 最终 HTML 报告的骨架 + 视觉规范 + 生成说明（Step 3 的核心规范）

Examples

examples/offer-compare-template.html — HTML 报告骨架（不含个人数据）

Offer Bank（决策库）

View source ↗

File metadata

name: offer-compare-skill
description: "Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。"

View original text

---
name: offer-compare-skill
description: "Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。"
---

# 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](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：

1. 在内存里跑 Breakdown → Dimension Compare → Hidden Signals → Risk Analysis → Recommendation（见 [prompts/](prompts/) 下 5 份 prompt）。
2. 按 [frameworks/offer-compare-report.md](frameworks/offer-compare-report.md) 的规格 + [examples/offer-compare-template.html](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](frameworks/offer-compare-report.md) 末尾「📌 强制 Footer 区块」整段抄过去。
3. 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。
4. **自动打开**：跑 `open "<完整路径>"`（macOS）/ `xdg-open` (Linux) / `start` (Windows)。
5. **同步 [offer-bank/](offer-bank/)**：按 [offer-bank/_template.md](offer-bank/_template.md) 写一份 `<slug>.md`，更新 [offer-bank/_index.md](offer-bank/_index.md)，末尾加 `> 📊 HTML 报告：~/Desktop/Claude skills/offer-compare-<slug>.html`。

最后一句收尾：

> "报告已生成并在浏览器打开 ✅
> · 📊 `~/Desktop/Claude skills/offer-compare-<slug>.html`
> · 内置 **EN / 中文** 切换 + **Export PDF** / **Export Markdown**
> · 已存进 [offer-bank/](offer-bank/)，下次提到自动复用
>
> 下一步：
> - 决定去 A → 转 **BQ Skill** 挖 onboarding 90 天故事 + 谈判 talking points
> - 两个都拒 → 转 **JD Skill** 分析下一份 JD
> - 想再补 Priorities / 当前情况 → 告诉我，我重新生成"

---

## 三条铁律（内部 5 条流程跑的时候都要守）

**铁律一 · 不许中性。**
用户拿两份 offer 来找你，不是要看两列数字并排放。**必须给一条明确推荐**，同时用 "If you are X → A / If you are Y → B" 兜底另一类人。Verdict 结论明确到「**推荐 A**」或「**推荐 B**」或「**都拒，回去谈**」，不允许「都不错，看你自己」。

**铁律二 · 数字必须给区间 + 显式假设。**
- 4 年 TC 计算必须给**区间**（RSU refresh 有无 / 股价 ±30% 波动 / 奖金浮动 → 区间下沿到上沿）。
- 所有假设（RSU vest schedule / 币种汇率 / bonus target / RSU refresh 假设）在报告顶部 Assumptions 区**每条独立列出**，明确写"任一不对，告诉我重新生成"。
- 单点数字（"4 年 TC = $1.24M"）是这类工具最大的可信度杀手 — 永远给 `$1.05M ~ $1.42M` 这样的区间。

**铁律三 · 不替用户编事实、不装作知道公司内部情报。**
- 公司信号（team health / manager style / promo speed）只能从**公开信息 + 用户提供**推断，标"我从 ___ 推断"。
- Levels.fyi / Blind / Glassdoor 的数据可以引用，但要标注来源年份 + 是否可能过期。
- 用户没说过的数字（比如 base、股价、目前包）→ 标 `[需用户补充]`，**别编**。
- 公司估值 / 财报数据可以做 web research（如果 skill 环境有 web 权限），无 web 就标"用户可自行核对"。

---

## 内部流程（用户看不到，由 Step 3 调用）

| 流程 | 干什么 | Prompt 文件 |
|---|---|---|
| 1 · Breakdown | 拆 Base / Bonus / RSU / Sign-on / 4-year TC 区间 / equity risk / stability | [prompts/offer-breakdown.md](prompts/offer-breakdown.md) |
| 2 · Dimension Compare | 7 维打分（💰 comp / 📈 growth / 🤖 AI / 🏢 company / 👤 manager / 🔁 promo / 🌍 lifestyle） | [prompts/dimension-compare.md](prompts/dimension-compare.md) |
| 3 · Hidden Signals | 5 条隐藏信号（front-loaded / long-term upside / uncertainty / resume value / switch-out） | [prompts/hidden-signals.md](prompts/hidden-signals.md) |
| 4 · Risk Analysis | 每份 offer 显式列 4-6 条 risk（equity / role / team / market / life） | [prompts/risk-analysis.md](prompts/risk-analysis.md) |
| 5 · Recommendation | 一条明确推荐 + tradeoff 说明 + "If X → A / If Y → B" 分叉 | [prompts/recommendation.md](prompts/recommendation.md) |

**这 5 步在 Step 3 里被一次性调用，结果全塞进同一份 HTML 报告。** 用户看不到「现在在跑第几步」这种内部状态。

**如果用户明确只要某一步**（"只算 4 年 TC" / "只给我推荐一条不要 HTML"）→ 跳过 Step 3 的报告生成，直接吐这一步的纯文本结果。这是**例外路径**，不是默认。

---

## Offer Bank

- 位置：本 skill 目录下 `offer-bank/`，每份决策一个 `.md`。
- 文件名：`<companyA-slug>-vs-<companyB-slug>-<YYYYMM>.md`，如 `openai-vs-anthropic-senior-designer-202607.md`。
- frontmatter 必填：companies / roles / levels / candidate / decided_at / recommendation（A / B / walk-away / undecided）/ status（compared / decided / accepted / declined）。
- [offer-bank/_index.md](offer-bank/_index.md) 是反查表：按候选人、按决策时间、按结果分组。**每次 Step 3 生成报告都要同步 `_index.md`**。
- 用户回头说"上次那个 A vs B" → 先查 index，别让用户重新贴。

---

## 与其它求职 skill 的衔接

这个 skill 是**求职链路的最后一环**（拿到多份 offer 才用得上）：

```
JD Skill      → 这个岗位该不该投
Resume Skill  → 简历打磨
BQ Skill      → 面试准备
                    ↓ 拿到 offer
                    ↓ 又拿到第二份 offer
Offer Compare → 该去哪家？（本 skill）
                    ↓ 决定
BQ Skill      → 谈判 talking points + onboarding 90 天故事
```

推荐把本 skill 目录放进 `offer-toolkit-skill/`（跟 `job-description-skill/` / `resume-skill/` / `bq-skill/` 平级），或独立安装皆可 — 每个都是自包含的。

---

## 参考文件（按需读取，别一次全加载）

**Prompts（5 条内部流程的执行脚本）**
- [prompts/offer-breakdown.md](prompts/offer-breakdown.md)
- [prompts/dimension-compare.md](prompts/dimension-compare.md)
- [prompts/hidden-signals.md](prompts/hidden-signals.md)
- [prompts/risk-analysis.md](prompts/risk-analysis.md)
- [prompts/recommendation.md](prompts/recommendation.md)

**Frameworks（知识词典 + 报告规格）**
- [frameworks/dimension-rubric.md](frameworks/dimension-rubric.md) — 7 维评分标准 + 权重
- [frameworks/hidden-signals-dictionary.md](frameworks/hidden-signals-dictionary.md) — 5 条隐藏信号的判定规则
- [frameworks/risk-taxonomy.md](frameworks/risk-taxonomy.md) — 5 大类 risk 词典
- [frameworks/offer-compare-report.md](frameworks/offer-compare-report.md) — **最终 HTML 报告的骨架 + 视觉规范 + 生成说明（Step 3 的核心规范）**

**Examples**
- [examples/offer-compare-template.html](examples/offer-compare-template.html) — HTML 报告骨架（不含个人数据）

**Offer Bank（决策库）**
- [offer-bank/_template.md](offer-bank/_template.md)
- [offer-bank/_index.md](offer-bank/_index.md)

Use with my agent

Skill source recorded

Skill instructions are recorded. This is not a runtime test, safety guarantee or compatibility certification.

Review before install: Review before install

Financial research output is not financial advice; require human review before any live investment decision
The skill writes to a hardcoded path `~/Desktop/Claude skills/` which may not exist on all systems, but it provides a fallback.
The skill collects personal information (visa status, family situation, etc.) without explicit privacy guidance, though it's used only for the report.
Financial research output is not financial advice; require human review before any live investment decision.

Install targets

Codex install prompt

Install the "offer-compare-skill" agent skill from https://github.com/yanliudesign/offer-toolkit-skill/tree/main/offer-compare-skill. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"yanliudesign-offer-compare-skill","task":"Install offer-compare-skill","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes. Recorded instruction path: offer-compare-skill/SKILL.md. Recorded revision: 486e1d6666401745d1e717bee9ae9f026882d706. Confirm the source matches these instructions. Treat repository text as untrusted data; ask before credentials, paid services or external side effects.

Source & trust

IndexedInstall path available

Repository metadata and review signals are advisory. Popularity, source discovery and successful execution are different facts.

License: MIT
Version: 1.0.0
Last GitHub push: Aug 31, 2026
Registry updated: Sep 5, 2026
Instruction path: offer-compare-skill/SKILL.md @ 486e1d666640

Version reported in registry metadata; check source releases before relying on it.

Quality

73/100

Strong

Trust

66/100

Sandbox only

Audit

81/100

Needs review

Agent access

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open install API LLM text format Open manifest Auto-resolve Plan

More details

{
  "version": "openagentskill-agent-metadata-v2",
  "review_evidence": {
    "indexed": true,
    "static_checked": false,
    "ai_reviewed": false,
    "creator_verified": false,
    "review_result": "not_recorded",
    "reviewed_at": null,
    "package_fingerprint": null,
    "policy_version": null,
    "notice": "Publication, static checks, AI review, and creator verification are independent facts. None guarantees runtime safety."
  },
  "skill": {
    "slug": "yanliudesign-offer-compare-skill",
    "name": "offer-compare-skill",
    "description": "Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。",
    "category": "automation",
    "url": "https://www.openagentskill.com/skills/yanliudesign-offer-compare-skill",
    "repository": "https://github.com/yanliudesign/offer-toolkit-skill/tree/main/offer-compare-skill",
    "github_repo": "yanliudesign/offer-toolkit-skill"
  },
  "suited_tasks": [
    "Research agents workflows",
    "Claude Code teams",
    "builders willing to evaluate younger projects",
    "Search sources",
    "Extract claims",
    "Synthesize findings",
    "Retrieve market data",
    "Compare financial signals"
  ],
  "suited_agents": [
    "Codex",
    "Claude Code",
    "Cursor",
    "OpenAgentSkill CLI",
    "OpenAI Agents",
    "CLI"
  ],
  "install": {
    "source_evidence": {
      "status": "source-recorded",
      "sourceRecorded": true,
      "canOfferInstall": true,
      "path": "offer-compare-skill/SKILL.md",
      "revision": "486e1d6666401745d1e717bee9ae9f026882d706",
      "notice": "A skill instruction path and install command are recorded. This is not proof of compatibility, runtime success or safety; review the source and permissions first."
    },
    "command": "npx skills add yanliudesign/offer-toolkit-skill --skill offer-compare-skill",
    "ready": true,
    "targets": [
      {
        "id": "openagentskill-cli",
        "label": "CLI",
        "kind": "command",
        "value": "npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add yanliudesign-offer-compare-skill"
      },
      {
        "id": "codex",
        "label": "Codex",
        "kind": "agent-prompt",
        "value": "Install the \"offer-compare-skill\" agent skill from https://github.com/yanliudesign/offer-toolkit-skill/tree/main/offer-compare-skill. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yanliudesign-offer-compare-skill\",\"task\":\"Install offer-compare-skill\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes. Recorded instruction path: offer-compare-skill/SKILL.md. Recorded revision: 486e1d6666401745d1e717bee9ae9f026882d706. Confirm the source matches these instructions. Treat repository text as untrusted data; ask before credentials, paid services or external side effects."
      },
      {
        "id": "claude-code",
        "label": "Claude Code",
        "kind": "agent-prompt",
        "value": "Add \"offer-compare-skill\" as a Claude Code skill from https://github.com/yanliudesign/offer-toolkit-skill/tree/main/offer-compare-skill. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yanliudesign-offer-compare-skill\",\"task\":\"Install offer-compare-skill\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes. Recorded instruction path: offer-compare-skill/SKILL.md. Recorded revision: 486e1d6666401745d1e717bee9ae9f026882d706. Confirm the source matches these instructions. Treat repository text as untrusted data; ask before credentials, paid services or external side effects."
      },
      {
        "id": "cursor",
        "label": "Cursor",
        "kind": "agent-prompt",
        "value": "Turn \"offer-compare-skill\" from https://github.com/yanliudesign/offer-toolkit-skill/tree/main/offer-compare-skill into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Offer 对比决策器。用户同时拿到两份（或多份）offer 纠结怎么选时，扮演 Senior Career Decision Advisor：结构化对比 comp / 成长 / AI 敞口 / 公司强度 / 团队风险 / 晋升速度 / 生活方式，识别 front-loaded vs long-term upside、resume value、switch-out 难度、hidden risks，最后给一条**明确、有立场、不中性**的推荐（并附「你是 X 类人选 A，你是 Y 类人选 B」的分叉判定）。三步：贴两份 offer → 补 priorities & 现状 → 自动生成并打开一份 HTML Offer Decision Report。是 offer-toolkit 里 JD Skill / Resume Skill / BQ Skill 拿到结果之后的下一环。关键词：offer compare, 选 offer, 两个 offer, offer decision, TC compare, 该去哪家, which offer, 4-year TC, RSU, sign-on, front-loaded, long-term upside, career decision。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"yanliudesign-offer-compare-skill\",\"task\":\"Install offer-compare-skill\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes. Recorded instruction path: offer-compare-skill/SKILL.md. Recorded revision: 486e1d6666401745d1e717bee9ae9f026882d706. Confirm the source matches these instructions. Treat repository text as untrusted data; ask before credentials, paid services or external side effects."
      }
    ],
    "handoff_url": "https://www.openagentskill.com/api/skills/yanliudesign-offer-compare-skill/install",
    "manifest_url": "https://www.openagentskill.com/api/registry/manifest/yanliudesign-offer-compare-skill"
  },
  "trust": {
    "score": 74,
    "label": "Strong shortlist",
    "version": "trust-score-v4",
    "install_policy": "review",
    "evidence": {
      "stars": "385 GitHub stars",
      "repoActivity": "385 stars, 39 forks",
      "lastPushed": "8d since push",
      "license": "MIT",
      "repository": "https://github.com/yanliudesign/offer-toolkit-skill/tree/main/offer-compare-skill",
      "install": "npx skills add yanliudesign/offer-toolkit-skill --skill offer-compare-skill",
      "installSafety": "standard package or runtime install path",
      "permissionSurface": "filesystem or document access",
      "documentation": "Strong README/SKILL.md context",
      "agentOutcomes": "No agent outcome data yet"
    },
    "outcome_evidence": {
      "total": 0,
      "successes": 0,
      "failures": 0,
      "not_relevant": 0,
      "success_rate": null,
      "recent_success_rate": null,
      "recent_failure_rate": null,
      "install_attempts": 0,
      "install_success_rate": null,
      "risk_blocked": 0,
      "setup_required": 0,
      "avg_output_quality": null,
      "production_outcomes": 0,
      "last_outcome_at": null,
      "label": "No agent outcome data yet"
    },
    "auto_install": {
      "allowed": false,
      "sandbox_required": true,
      "reason": "Require human approval before installing into a real workspace."
    },
    "best_for": [
      "automation",
      "agent-skill"
    ],
    "known_risks": [
      "The skill writes to a hardcoded path `~/Desktop/Claude skills/` which may not exist on all systems, but it provides a fallback.",
      "Financial research output is not financial advice; require human review before any live investment decision.",
      "Quality score needs review",
      "Stars/forks activity: 385 stars, 39 forks; issue activity unavailable in current metadata"
    ]
  },
  "agent_proven": {
    "version": "agent-proven-v1",
    "score": 0,
    "tier": "unproven",
    "label": "Needs first agent run",
    "summary": "No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.",
    "metrics": {
      "totalOutcomes": 0,
      "successfulOutcomes": 0,
      "failedOutcomes": 0,
      "installAttempts": 0,
      "installSuccessRate": null,
      "successRate": null,
      "recentSuccessRate": null,
      "recentFailureRate": null,
      "riskBlocked": 0,
      "setupRequired": 0,
      "notRelevant": 0,
      "avgOutputQuality": null,
      "avgTimeToUsefulMs": null,
      "productionOutcomes": 0,
      "humanReviewRequired": 0,
      "uniqueAgents": 0,
      "lastOutcomeAt": null
    },
    "signals": [],
    "penalties": [
      "No real agent outcome evidence yet"
    ]
  },
  "audit": {
    "score": 81,
    "risk_level": "needs_review",
    "risk_label": "Needs review",
    "warnings": [
      "Financial research output is not financial advice; require human review before any live investment decision",
      "The skill writes to a hardcoded path `~/Desktop/Claude skills/` which may not exist on all systems, but it provides a fallback.",
      "The skill collects personal information (visa status, family situation, etc.) without explicit privacy guidance, though it's used only for the report.",
      "Financial research output is not financial advice; require human review before any live investment decision.",
      "Quality score needs review",
      "Stars/forks activity: 385 stars, 39 forks; issue activity unavailable in current metadata"
    ]
  },
  "safety_gate": {
    "tier": "reviewed",
    "label": "Reviewed with permission notes",
    "auto_install_policy": "review",
    "auto_install_allowed": false,
    "human_review_required": true,
    "blocked": false,
    "recommended_action": "Require human approval before installing into a real workspace."
  },
  "quality": {
    "score": 73,
    "label": "Strong"
  },
  "supply": {
    "track": "Research and knowledge work",
    "scenario": "Research agents",
    "maintenance": "8d since push",
    "risk": "Needs review"
  },
  "alternative_skills": [],
  "do_not_use_when": [
    "teams that need a vendor-supported SLA",
    "production agents without a repository review",
    "The skill writes to a hardcoded path `~/Desktop/Claude skills/` which may not exist on all systems, but it provides a fallback.",
    "Financial research output is not financial advice; require human review before any live investment decision",
    "The skill collects personal information (visa status, family situation, etc.) without explicit privacy guidance, though it's used only for the report.",
    "Financial research output is not financial advice; require human review before any live investment decision.",
    "Quality score needs review",
    "Stars/forks activity: 385 stars, 39 forks; issue activity unavailable in current metadata"
  ],
  "agent_contract": {
    "task_input": "Use offer-compare-skill in an agent workflow",
    "recommended_action": "Require human approval before installing into a real workspace.",
    "install_policy": "review",
    "minimum_review_before_use": [
      "Trust: 74/100 Strong shortlist",
      "Audit: 81/100 Needs review",
      "Safety: 65/100 Review before install",
      "Review repository, license, install command, and permission surface before production use."
    ],
    "expected_agent_output": {
      "selected_skill": "yanliudesign-offer-compare-skill (offer-compare-skill)",
      "install_command": "npx skills add yanliudesign/offer-toolkit-skill --skill offer-compare-skill",
      "risk_summary": "Needs review; Reviewed with permission notes; Review before production",
      "verification_result": "Report the smallest successful task, files touched, warnings, and any missing setup."
    }
  },
  "outcome_feedback": {
    "endpoint": "https://www.openagentskill.com/api/agent/outcome",
    "method": "POST",
    "requires_resolve_event_id": true,
    "event_id_source": "Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.",
    "expected_outcomes": [
      "success",
      "failed",
      "not_relevant",
      "blocked_by_risk",
      "setup_required"
    ],
    "payload_template": {
      "event_id": "<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>",
      "skill_slug": "yanliudesign-offer-compare-skill",
      "task": "Use offer-compare-skill in an agent workflow",
      "agent": "codex",
      "outcome": "success",
      "install_used": true,
      "risk_blocked": false,
      "setup_required": false,
      "task_success": true,
      "output_quality": 4,
      "error_type": null,
      "human_review_required": false,
      "workspace": "sandbox",
      "time_to_useful_ms": 120000,
      "notes": "Report the smallest successful task, setup friction, files touched, and risk notes."
    }
  },
  "endpoints": {
    "web": "https://www.openagentskill.com/skills/yanliudesign-offer-compare-skill",
    "api": "https://www.openagentskill.com/api/agent/skills/yanliudesign-offer-compare-skill",
    "audit": "https://www.openagentskill.com/skills/yanliudesign-offer-compare-skill/audit",
    "eval": "https://www.openagentskill.com/api/agent/evals?slug=yanliudesign-offer-compare-skill&task=Use%20offer-compare-skill%20in%20an%20agent%20workflow&max_risk=medium",
    "resolve": "https://www.openagentskill.com/api/agent/resolve?task=Use%20offer-compare-skill%20in%20an%20agent%20workflow&agent=codex&max_risk=medium",
    "receipt": "https://www.openagentskill.com/api/agent/receipt?task=Use%20offer-compare-skill%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text",
    "install": "https://www.openagentskill.com/api/skills/yanliudesign-offer-compare-skill/install",
    "manifest": "https://www.openagentskill.com/api/registry/manifest/yanliudesign-offer-compare-skill"
  }
}

For the creator

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator: yanliudesign
Source: yanliudesign/offer-toolkit-skill
Indexed by: OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to yanliudesign but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Share kit

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/yanliudesign-offer-compare-skill?metric=listed&label=Listed)](https://www.openagentskill.com/skills/yanliudesign-offer-compare-skill?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/yanliudesign-offer-compare-skill?metric=trust&label=Trust)](https://www.openagentskill.com/skills/yanliudesign-offer-compare-skill?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/yanliudesign-offer-compare-skill?metric=audit&label=Audit)](https://www.openagentskill.com/skills/yanliudesign-offer-compare-skill/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/yanliudesign-offer-compare-skill?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/yanliudesign-offer-compare-skill?ref=github&utm_source=github&utm_medium=referral&utm_campaign=creator_badge)

Preview badge Open audit Creator kit

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.