AI Stock Report Generator
台股「一鍵財務模型 + 投資簡報」生成器。使用者輸入任何台股代號(如 6116、2330、0050)並加上 //ai-stock-report-generator,或沿用舊觸發詞 //model-up,或說「建立財務模型」「Excel 財務模型」「估值模型」「幫我做 XXXX 的估值和簡報」「XXXX 財務模型整理成 PPT」「model up XXXX / ai stock report XXXX」時,必須立即使用此技能。技能會即時搜尋最新公開財務數據與近期日線資料,產出核心檔案:(1) 完整 Excel 財務模型(假設可調、三情境預測、P/B 與 P/S 估值、敏感度表、財務指標、KD/MACD 技術指標、K 線型態資料、風險矩陣,全部以公式或可稽核計算連動、零公式錯誤);(2) 投資分析 PPTX(有數據、有圖表:歷史財務、營運動能、成長動能、估值、KD/MACD、K 線型態、風險、結論);必要時另附可下載的 K 線 HTML/PNG 圖表。即使使用者只丟出「代號 //ai-stock-report-generator」也必須執行完整流程,不得僅用文字回覆。
Install
npx skills add yangchunyi0814/ai-stock-report-generator --skill ai-stock-report-generatorgit clone --depth 1 https://github.com/yangchunyi0814/ai-stock-report-generator.git /tmp/ai-stock-report-generator
mkdir -p ~/.claude/skills
cp -r /tmp/ai-stock-report-generator/skills/ai-stock-report-generator ~/.claude/skills/ai-stock-report-generatorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# ai-stock-report-generator:台股財務模型 + 投資簡報生成器
輸入:台股代號(4-6 位數字)。核心輸出:`{代號}_{名稱}_財務模型.xlsx` + `{代號}_{名稱}_投資分析簡報.pptx`。若已產生 K 線型態圖,另輸出 `{代號}_{名稱}_K線型態圖表.html` 與 `{代號}_{名稱}_K線型態圖表.png`。全部存至 `/mnt/user-data/outputs/` 或當前專案 `outputs/`,並以 present_files 或本機連結交付。
**執行前必讀**:本技能依賴內建 `xlsx` 與 `pptx` 技能的規範。開工前先閱讀:
- `/mnt/skills/public/xlsx/SKILL.md`(色碼規範、recalc.py 驗證)
- `/mnt/skills/public/pptx/SKILL.md` 與 `pptxgenjs.md`(設計規範、視覺 QA)
## 流程總覽
```
代號 → ①資料蒐集(web_search + 日線資料) → ②Excel模型(財務 + 技術指標) → ③K線型態圖(HTML/PNG) → ④PPTX(財務 + 技術圖表 + QA) → ⑤交付
```
---
## 第 1 步:資料蒐集(web_search,3-5 次搜尋)
必須即時搜尋,不可依賴訓練記憶。建議查詢組合({N}=代號、{名}=公司名):
1. `{N} {名} 全年財報 EPS 營收` — 近三年年度營收、EPS
2. `{名} {N} 股價 今日 每股淨值` — 最新收盤價、股淨比/每股淨值
3. `{名} {N} 股價 大漲/展望 產業` — 題材、成長動能、法人觀點
4. (選配)`{N} 財報分析 季度` — 最新季度損益細節(營業利益率、ROE/ROA、FCF、現金轉換循環)
**必蒐集清單**(缺項時以已知數據回推並明確標注「估計」):
- 最新收盤股價與日期、股本/股數、市值
- 近 3 年:營收、EPS、(可得則加 ROE/ROA/FCF)
- 近 5 季:季度 EPS
- 今年月營收與年增率、累計營收
- 每股淨值(BVPS);虧損股沒有本益比時改以股淨比推算
- 成長題材與 3-7 項具體風險(含觀察指標)
**資料誠信規則**:
- 每個硬編碼數字都要在 Excel 備註欄標注來源與日期(格式:`來源: {網站}, {日期}`)
- 推算值(如以年增率回推前一年營收)必須註明推算方式
- 引用新聞觀點以改寫轉述,勿逐字複製
### 第 1.5 步:近期技術資料與 K 線型態資料
必須補抓近期日線資料,至少 60 個交易日;若交易所 API 無法一次取得足夠資料,要按月份回補。台股優先使用 TWSE / TPEx 官方日成交資訊。
技術資料至少包含:
- 日期、開盤、最高、最低、收盤、成交量
- MA5、MA10、MA20
- BB(20,2):中軌、上軌、下軌
- KD:RSV(9)、K(9,3)、D(9,3),K/D 初始值可用 50,但須註明
- MACD:EMA12、EMA26、DIF、MACD/Signal(9)、柱狀體
**台股圖表色彩硬性規範**:
- 台灣股票圖表必須使用台股慣例:**紅色 = 上漲 / 正值 / 偏多,綠色 = 下跌 / 負值 / 偏空**。
- K 線實體、影線、成交量柱必須紅漲綠跌;不得使用美股常見的綠漲紅跌。Details
- Skill name
ai-stock-report-generator- Repository
- yangchunyi0814/ai-stock-report-generator
- Path
skills/ai-stock-report-generator/SKILL.md- Repo updated
- 5 July 2026
FAQ
What does the AI Stock Report Generator skill do?
台股「一鍵財務模型 + 投資簡報」生成器。使用者輸入任何台股代號(如 6116、2330、0050)並加上 //ai-stock-report-generator,或沿用舊觸發詞 //model-up,或說「建立財務模型」「Excel 財務模型」「估值模型」「幫我做 XXXX 的估值和簡報」「XXXX 財務模型整理成 PPT」「model up XXXX / ai stock report XXXX」時,必須立即使用此技能。技能會即時搜尋最新公開財務數據與近期日線資料,產出核心檔案:(1) 完整 Excel 財務模型(假設可調、三情境預測、P/B 與 P/S 估值、敏感度表、財務指標、KD/MACD 技術指標、K 線型態資料、風險矩陣,全部以公式或可稽核計算連動、零公式錯誤);(2) 投資分析 PPTX(有數據、有圖表:歷史財務、營運動能、成長動能、估值、KD/MACD、K 線型態、風險、結論);必要時另附可下載的 K 線 HTML/PNG 圖表。即使使用者只丟出「代號 //ai-stock-report-generator」也必須執行完整流程,不得僅用文字回覆。
How do I install the AI Stock Report Generator skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add yangchunyi0814/ai-stock-report-generator --skill ai-stock-report-generator. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Stock Report Generator popular?
It lives in yangchunyi0814/ai-stock-report-generator, which has 43 GitHub stars and 12 forks.
Related skills
Clarificar
100adriannoes/awesome-agentic-ai
Use for a GRILLING SESSION — a relentless interview that turns diffuse intent into shared understanding before building. It walks the decision tree ONE question at a time, resolving dependencies between choices, always with a recommended answer; it explores the codebase/docs instead of asking when the answer already exists. Ideal at the spec gate (testable ACs / Definition of Ready) and the design gate (hard-to-reverse decision). It produces an understanding summary that feeds product.md/design.md/spec.md. Called by /nova-feature, /kickoff, /roadmap, and /validar, or trigger directly with /cla
Stock Quote
132OctagonAI/skills
Retrieve real-time stock quotes using Octagon MCP. Use when you need current price, day range, 52-week range, volume, market cap, and moving averages for any publicly traded stock.
Investigating Insider Threat Indicators
100adriannoes/awesome-agentic-ai
Investigates insider threat indicators including data exfiltration attempts, unauthorized access patterns, policy violations, and pre-departure behaviors using SIEM analytics, DLP alerts, and HR data correlation. Use when SOC teams receive insider threat referrals from HR, detect anomalous data movement by employees, or need to build investigation timelines for potential insider threats.
Stock Price Change
132OctagonAI/skills
Retrieve stock price change statistics across multiple time periods using Octagon MCP. Use when analyzing short-term and long-term returns, comparing performance across timeframes, and evaluating momentum and historical growth.
Investigating Ransomware Attack Artifacts
100adriannoes/awesome-agentic-ai
Identify, collect, and analyze ransomware attack artifacts to determine the variant, initial access vector, encryption scope, and recovery options.
Stock Performance
132OctagonAI/skills
Retrieve stock price data and performance metrics using Octagon MCP. Use when analyzing daily closing prices, trading volume, price trends, historical performance, and comparing stock movements over specific time periods.
Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.