yanliudesign/offer-toolkit-skill / job-description-skill
job-description-skill
VerifiedJob Description 解码器 + Offer 策略系统。把任何 JD 翻译成「这家公司到底在招什么人 / 我的匹配度 / Gap 在哪 / 为什么投/不投 / 面试会问什么 / 下一步怎么走」。只有 3 步:贴 JD → 给简历 → 自动生成并打开一份 HTML Offer Strategy Report。是整个求职链路的入口,向下衔接 Resume Skill 和 BQ Skill。关键词:job description, JD, 职位描述, 匹配度, ATS, resume tailor, 简历定制, 招聘经理, 投不投, should I apply, 面试预测, offer strategy。
jd-bank/_index.md
View on GitHub# JD Bank · Index
每份分析过的 JD 的反查表。**每次新增 / 更新 JD 文件,必须同步更新这里。**
文件命名规则:`<company-slug>-<role-slug>-<YYYYMM>.md`
例:`openai-product-designer-202606.md`
---
## 按状态汇总
| Status | 含义 |
|---|---|
| `decoded` | 仅做了 JD 解码 |
| `matched` | 跑了 Match Score |
| `tailored` | 简历已 tailor |
| `applied` | 已投递 |
| `interview` | 在面试流程中 |
| `offer` | 拿到 offer |
| `closed` | 决定不投 / reject / 关闭 |
---
## All JDs(按状态分组)
### 🔍 Decoded(已解码,未决定)
> 暂无
### 📊 Matched(已算匹配度)
| 文件 | 公司 | 岗位 | Match | ⭐ | 候选人 |
|---|---|---|---|---|---|
| [linear-principal-product-designer-202606.md](linear-principal-product-designer-202606.md) | Linear | Principal Product Designer | 70–80% | 3.5/5 | Yan Liu |
| [xai-exceptional-designer-202606.md](xai-exceptional-designer-202606.md) | xAI | Exceptional Designer | 78–85% | 4/5 | Yan Liu |
| [anthropic-product-designer-claude-code-202606.md](anthropic-product-designer-claude-code-202606.md) | Anthropic | Product Designer, Claude Code | 80–88% | 4.5/5 | Yan Liu |
| [openai-product-design-lead-growth-codex-202609.md](openai-product-design-lead-growth-codex-202609.md) | OpenAI | Product Design Lead, Growth - Codex | 84–90% | 4.5/5 | Yan Liu |
| [openai-product-designer-chatgpt-202609.md](openai-product-designer-chatgpt-202609.md) | OpenAI | Product Designer, ChatGPT | 86–92% | 4.5/5 | Yan Liu |
<!--
| 文件 | 公司 | 岗位 | Match | 下一步 |
|---|---|---|---|---|
-->
### ✍️ Tailored(简历已改)
> 暂无
### 📤 Applied(已投)
> 暂无
<!--
| 文件 | 公司 | 投递日期 | 渠道 | 当前阶段 |
|---|---|---|---|---|
-->
### 🎤 Interview(面试中)
> 暂无
### 🎉 Offer
> 暂无
### 📁 Closed
> 暂无
---
## 按公司聚合(同公司多份 JD 可复用 Hidden Signal)
### OpenAI
- [openai-product-designer-chatgpt-202609.md](openai-product-designer-chatgpt-202609.md) — Product Designer, ChatGPT (Senior/Staff IC inferred, SF HQ)
- [openai-product-design-lead-growth-codex-202609.md](openai-product-design-lead-growth-codex-202609.md) — Product Design Lead, Growth - Codex (Design Lead / Manager, SF HQ)
### xAI
- [xai-exceptional-designer-202606.md](xai-exceptional-designer-202606.md) — Exceptional Designer (Mid→Principal IC, Palo Alto on-site · Grok + X)
### Anthropic
- [anthropic-product-designer-claude-code-202606.md](anthropic-product-designer-claude-code-202606.md) — Product Designer, Claude Code (Senior/Staff IC, SF hybrid · dev tool)
### Linear
- [linear-principal-product-designer-202606.md](linear-principal-product-designer-202606.md) — Principal Product Designer (Principal IC, Remote)
---
## 按岗位类型聚合(同类岗位 must-have 类似,可参考)
### AI Product Designer (Consumer)
- [openai-product-designer-chatgpt-202609.md](openai-product-designer-chatgpt-202609.md) — OpenAI / ChatGPT
- [xai-exceptional-designer-202606.md](xai-exceptional-designer-202606.md) — xAI / Grok + X(社交 × AI 双线)
- [anthropic-product-designer-claude-code-202606.md](anthropic-product-designer-claude-code-202606.md) — Anthropic / Claude Code(AI 编码 dev tool)
### AI Product Design Leadership / Growth
- [openai-product-design-lead-growth-codex-202609.md](openai-product-design-lead-growth-codex-202609.md) — OpenAI / Codex + ChatGPT Business(增长 × 开发者产品 × 管理)
<!--
### AI Product Designer
- [openai-product-designer-202606.md](openai-product-designer-202606.md)
-->
---
## 维护规则
1. **新增 JD 文件**:必须同时在「按状态」「按公司」「按岗位类型」三处登记。
2. **状态变更**:从一个 section 移到另一个(如 Matched → Tailored),不要重复列。
3. **关闭一份**:移到 Closed,并在文件里补上"复盘"section。
4. **半年清理一次**:closed 超过 6 个月可以归档到 `jd-bank/archive/`。
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: 323k | 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: 323k | 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: 323k | Updated | Claude CodeCodex | Verified | Install |