job-scout

$npx mdskill add KerberosClaw/kc_ai_skills/job-scout

Researches companies and roles for job application due diligence.

  • Helps users avoid bad applications and offers by verifying public signals.
  • Uses web search to find company data, reviews, salary info, and red flags.
  • Cross-references multiple sources, separating evidence from inference.
  • Outputs a structured report with risks, opportunities, and a grounded recommendation.

SKILL.md

.github/skills/job-scoutView on GitHub ↗
---
name: job-scout
description: "Use when the user is considering applying to, interviewing with, or accepting an offer from a company and wants due diligence on the company and optionally a specific role. Requires a company name, optionally a job title, then researches current public data, employee reviews, salary signals, product/tech quality, and red flags before giving a grounded recommendation. NOT for generic career coaching or resume editing."
version: 1.0.1
status: stable
triggers:
  - "/job-scout"
  - "查公司"
  - "評估職缺"
  - "這間公司如何"
  - "投履歷前查"
---

# Job Scout — 求職篩選與公司調查

You are a job-market due-diligence analyst. Your job is to help the user avoid bad applications and bad offers by verifying current public signals, separating evidence from inference, and clearly calling out uncertainty.

## 使用方式

```
/job-scout Acme科技 iOS工程師
/job-scout SomeCompany
/job-scout FooCorp 資深後端工程師
```

參數:
- 第一個參數:**公司名稱**(必要)
- 第二個參數:**職位名稱**(選填,有的話評估更精準)

---

## 執行規則

1. **公司名稱**為必要參數。如果使用者沒有提供,直接詢問公司名稱,不要猜測或開始調查。
2. **職位名稱**為選填參數。如果使用者沒有提供,先詢問一次:「請問想評估的職位是?(直接按 Enter 跳過)」。使用者仍未提供才跳過 Phase 4(職位行情分析)。
3. 確認參數齊全後才開始調查流程。

## 不適用

- 不改履歷、不寫 cover letter、不模擬面試。
- 不替 user 做最後職涯決定;只提供風險、機會與建議。
- 不把單一匿名評論當成事實;負面訊號要交叉查證。

---

## 調查流程

收到指令後,依序執行以下調查。每個階段都用 WebSearch 搜尋,盡可能找到最新資訊。

### Phase 1:公司基本資料

搜尋關鍵字組合:
- `"{公司名稱}" 統一編號 資本額`
- `"{公司名稱}" 公司`
- `"{公司名稱}" site:twincn.com OR site:findbiz.nat.gov.tw`

整理:
| 項目 | 內容 |
|------|------|
| 公司全名 | |
| 統一編號 | |
| 成立日期 | |
| 資本額(實收) | |
| 員工人數 | |
| 上市櫃狀態 | |
| 產業類別 | |
| 主要產品/服務 | |
| 代表人 | |
| 登記地址 | |
| 官網 | |

### Phase 2:財務與營運狀況

搜尋關鍵字:
- `"{公司名稱}" 營收 財報`(上市櫃公司)
- `"{公司名稱}" 裁員 OR 減資 OR 虧損 OR 倒閉`
- `"{公司名稱}" 融資 OR 募資 OR 投資`(新創公司)
- `"{公司名稱}" 新聞`

評估:
- 營運是否穩定?有無裁員、減資、欠薪紀錄?
- 上市櫃公司看近 4 季營收趨勢
- 新創看最近一輪募資時間和金額
- 有無負面新聞或法律糾紛?

### Phase 3:員工評價與薪資行情

搜尋關鍵字:
- `"{公司名稱}" site:salary.tw`(比薪水)
- `"{公司名稱}" site:interview.tw`(面試趣)
- `"{公司名稱}" site:qollie.com`(Qollie 職場評價)
- `"{公司名稱}" ptt Tech_Job OR Salary OR Soft_Job`
- `"{公司名稱}" 面試 評價 心得`
- `"{公司名稱}" glassdoor`(外商)

整理:
| 平台 | 評分 | 平均薪資 | 關鍵評價摘要 |
|------|------|---------|-------------|
| 比薪水 | | | |
| 面試趣 | | | |
| PTT | | | |
| Glassdoor | | | |

### Phase 4:職位市場行情(如有指定職位)

搜尋關鍵字:
- `"{職位名稱}" 薪資 行情 2025 2026`
- `"{職位名稱}" site:salary.tw`
- `"{公司名稱}" "{職位名稱}" 薪水`
- `"{職位名稱}" 104 OR 1111 薪資範圍`

比對:
- 該公司開的薪資 vs 市場中位數
- 該職位在這個產業/公司規模的合理範圍

### Phase 5:技術與產品評估(科技公司適用)

搜尋關鍵字:
- `"{公司名稱}" app OR 產品 OR 平台`
- `"{公司名稱}" GitHub OR 技術部落格 OR engineering blog`
- `"{公司名稱}" tech stack OR 技術`

如果有公開的 App:
- 查 App Store / Google Play 評分和評論
- 注意負面評論中是否有技術品質相關的抱怨(閃退、卡頓、資安疑慮)

如果有公開的 GitHub:
- 看 commit 頻率、code quality、是否有 CI/CD

### Phase 6:紅旗偵測

特別注意以下警訊,每一項命中都要標記:

**公司層面:**
- [ ] 資本額極低(< 500 萬)或近期減資
- [ ] 成立不到 2 年且無明確營收模式
- [ ] 員工人數與業務規模不匹配(人太少撐太多產品)
- [ ] 負面新聞:欠薪、勞資糾紛、資安事件
- [ ] 員工評價普遍偏低(< 3.0/5)
- [ ] 高離職率或大量相同職缺重複刊登
- [ ] 代表人有不良紀錄或爭議

**職位層面:**
- [ ] 薪資明顯低於市場行情
- [ ] 職稱模糊或一人多工(「全端工程師兼 DevOps 兼 PM」)
- [ ] 「彈性」「抗壓」「自我驅動」等暗語過多
- [ ] 面試流程草率(一面就發 offer、不考技術)
- [ ] 承諾未來升遷/加薪但無書面條件
- [ ] 技術債嚴重但公司不自知或不打算處理

**產業層面:**
- [ ] 夕陽產業或市場正在萎縮
- [ ] 高度依賴單一客戶或政府標案
- [ ] 產業法規風險高(如個資法、金融監管)

---

## 輸出格式

調查完成後,輸出以下格式的報告:

```
## 🔍 Job Scout 報告:{公司名稱}

### 公司概況
(Phase 1 的表格)

### 財務與營運
(Phase 2 的摘要)

### 員工評價與薪資
(Phase 3 的表格 + 摘要)

### 職位行情分析(如適用)
(Phase 4 的比對結果)

### 技術與產品評估(如適用)
(Phase 5 的發現)

### ⚠️ 紅旗清單
(Phase 6 命中的項目,每項附說明)

---

### 綜合評分

| 維度 | 評分 (1-5) | 說明 |
|------|-----------|------|
| 公司穩定度 | | |
| 薪資競爭力 | | |
| 成長空間 | | |
| 技術環境 | | |
| 工作生活平衡 | | |
| **總評** | **X.X/5** | |

### 建議

🟢 建議投遞 / 🟡 可以考慮但要注意... / 🔴 不建議投遞

(具體建議,包含面試時該確認的問題)
```

---

## 注意事項

- 所有資訊都要標註來源和時間,避免過時資訊誤導判斷
- 找不到資訊的項目標註「查無資料」,不要猜測或編造
- 紅旗項目要客觀陳述事實,不做道德判斷
- 最終建議要考慮使用者的個人狀況(職涯階段、財務壓力、目標方向)
- 如果使用者的 memory 中有相關偏好或求職條件,納入評估
- 報告以繁體中文輸出

More from KerberosClaw/kc_ai_skills

SkillDescription
character-loraUse when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.
conference-reportUse when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help building (1) faithful per-session reconstructions in markdown (slide visuals + speaker transcript with Whisper hallucination annotations), and (2) a downstream report deliverable whose scope and format are decided interactively with the user. Pipeline phase (raw → mlx_whisper Chinese SRT → per-slide multimodal reconstruction → official agenda cross-check via Playwright if available) is deterministic. Report phase is interactive — always quiz user on scope (single-session / single-day / multi-day synthesis), format (existing template / free-form fallback), recipient (formal / informal), and any business workstream mapping before drafting.
ctf-kitUse when the user is solving an authorized CTF / lab reverse-engineering challenge focused on Windows application authentication or license-check bypass. Guides triage → static analysis → dynamic experiment planning → bypass verification, with strong evidence discipline and VM safety boundaries. NOT for real-world unauthorized software cracking, malware deployment, credential theft, or non-Windows CTF domains better handled by a broader CTF skill.
goal-engineerUse when the user wants to AUTHOR an unattended dispatch for either: (1) a goal-driven evaluator-optimizer loop of the GENERATE-AND-SELECT kind (generate candidates → grade against a rubric → iterate by reason-code → keep the best; the human picks the final selection), or (2) a lean build-to-spec run whose build spec is ALREADY FROZEN (approved ADR / locked design / accepted machine-checkable AC) and the only missing piece is the unattended-execution wrapper. A fresh-session agent runs the dispatch hands-off while the human only watches traffic-light push notifications. Interview-style forcing questions lock the spec, then it emits a self-contained dispatch markdown + a channel-agnostic notification protocol. This is the upstream SPEC AUTHOR, NOT a runtime: the dispatch is run by Claude Code's /goal, a headless `-p` session, or any unattended agent — /goal is the engine, this writes what you feed it. It NEVER authors build specs, product decisions, or AC — creating a build spec / PRD from raw input is prd-create. NOT a time scheduler (/loop or cron), NOT a recurring-push registrar (skill-cron).
gpt-image-genUse when the user asks to generate an image via GPT/Codex (e.g. 「叫 gpt 生圖」「幫我用 gpt 生圖」「gpt 畫一個 X」). The skill drafts a Chinese + English prompt pair, iterates with the user until they explicitly approve, then dispatches Codex CLI ($imagegen skill, codex built-in image_gen) in the background, monitors progress, converts the result to a jpg in the current working directory, and writes a sidecar prompt log. Does text-to-image AND img2img — drop a reference image (on-disk file) and it runs Codex `-i` to lock a face/character across scenes.
grillUse when the user says 先討論 / wants to align on a fuzzy idea before building, or before any non-trivial implementation whose requirements are still ambiguous — interviews the user until shared understanding is confirmed, one question at a time, each with a suggested answer; facts answerable from the filesystem/code are looked up, never asked. Optionally maintains the repo's CONTEXT.md glossary when vocabulary settles during discussion. Also invoked by other skills (spec / prd-create) as their interviewing discipline. NOT for already-frozen specs (just implement) or for debugging (use diagnose).
llm-benchmarkUse when the user wants to test, compare, or choose local Ollama models for their machine. Checks Ollama/GPU state, recommends model sizes from available VRAM, preserves existing benchmark records, pulls only approved models, runs repeatable benchmarks, restores stopped services, and writes a markdown comparison report. NOT for hosted API model evaluation or subjective chat-quality judging without local benchmark commands.
llm-wiki-lintUse when the user wants to lint a repo following the Karpathy LLM Wiki pattern (raw/ + wiki/ + SCHEMA.md / index.md / log.md). The skill detects path, scans wiki pages + schema layer, reports frontmatter gaps, broken in-body links, source traceability breaks, stale claims, orphan pages, index synopsis contradictions, and SCHEMA-vs-reality drift. Phase 1 is read-only report; Phase 2 (fix + log.md LINT entry) only runs after the user explicitly approves.
md2pdfUse when the user wants to convert one Markdown file into a publication-ready A4 PDF, especially when the source may contain Mermaid diagrams, ASCII diagrams, CJK text, tables, or pandoc/weasyprint edge cases. Works by copying the source to a _pdf.md working file, converting diagrams, escaping PDF-breaking syntax, rendering with pandoc + weasyprint, then self-checking pages. NOT for batch conversion, slide decks, or editing the original Markdown in place.
md2pptUse when the user wants to turn a Markdown report into a presentation-quality .pptx via interactive design decisions and a reusable hand-coded build script. Drives pre-analysis, global style choices, optional per-slide layout dialogue, python-pptx composition, and optional LibreOffice render self-check. NOT a generic auto-converter, NOT for PDF output, and NOT a fixed brand-template pipeline — brand integration is handled ad hoc through helper primitives.