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 Gratia2533/pipe-stock-analysis --skill stock-analysisgit clone --depth 1 https://github.com/Gratia2533/pipe-stock-analysisWrote 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/gratia2533/pipe-stock-analysis/stock-analysis)<a href="https://agentmods.dev/skills/gratia2533/pipe-stock-analysis/stock-analysis"><img src="https://agentmods.dev/badge/skills/gratia2533/pipe-stock-analysis/stock-analysis/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/gratia2533/pipe-stock-analysis/stock-analysis"><img src="https://agentmods.dev/badge/skills/gratia2533/pipe-stock-analysis/stock-analysis.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 | $0.00042 | $0.01809 |
| Opus 5.5 | $0.00017 | $0.00724 |
| Sonnet 5.5 | $0.00008 | $0.00362 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
stock-analysis 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 2mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stock Analysis Skill
Overview
這個 Skill 提供跨市場的股票研究流程。分析框架不因市場而改變,但資料工具與可得欄位必須依市場分流:台股使用 FinMind、TWSE、TPEx、MOPS 與新聞來源;全球股票使用 Finnhub。MCP 只負責唯讀資料與確定性計算,投資論點、衝突處理與風險整合由 Hermes 完成。
When to Use
- 分析台股、美股或其他 Finnhub 可辨識的全球股票。
- 比較同市場或跨市場標的。
- 整理技術面、基本面、事件、多空論點與主要風險。
- 判讀價格異動,但只在資料能支持時描述原因。
不適用於下單、券商帳戶、持倉管理或保證報酬。
Prerequisites
Hermes 必須啟用 finance MCP。全球股票工具需要部署端設定 FINNHUB_API_KEY;若缺少金鑰、方案不支援 endpoint 或回傳空值,必須標示資料缺口,不得把台股資料或模型記憶冒充全球股票資料。
Market Routing
台股
股票代碼用純數字,例如 2330,不要附加 .TW 或 .TWO。完整分析優先使用:
analyze_taiwan_stock_technicalanalyze_taiwan_stock_fundamentalanalyze_taiwan_stock_financial_healthanalyze_taiwan_stock_institutional_flowsanalyze_taiwan_stock_margin_tradingget_taiwan_stock_material_announcementsget_taiwan_stock_news
需要最新官方收盤、市場歸屬或原始資料時,再使用對應 get_taiwan_stock_* 工具交叉驗證。
全球股票
先用 search_global_stock_symbols 確認 symbol;常見美股如 NVDA、AAPL 使用大寫 ticker。完整分析依需求取得:
get_global_stock_quoteget_global_stock_pricesget_global_stock_profileget_global_stock_basic_financialsget_global_stock_financial_reportsget_global_stock_news
Finnhub endpoint 可用性取決於方案。若 K 線或財報 endpoint 被拒絕,不能因此推定公司沒有資料;應寫成「供應商方案或 endpoint 不可用」。
Procedure
1. 確認標的與市場
- 數字代碼預設按台股處理;英文字母 ticker 預設先查 Finnhub。
- 公司名稱或代碼有歧義時先搜尋 symbol,不猜測交易所。
- 多檔比較採相同日期區間、幣別標示與指標定義。
完成條件:每個標的都有明確 symbol、交易所或市場,以及資料來源。
2. 取得價格、公司與事件資料
先取得報價與公司 profile,再平行取得價格歷史、基本財務、財報及新聞。台股另取得法人、融資融券與 MOPS;全球股票不應虛構台灣式籌碼指標。
完成條件:清楚列出每項資料的最新日期、期間、來源與缺漏。
3. 多思維分析
市場差異不應縮減分析維度。依資料可得性執行:
- 技術面:趨勢、動能、區間報酬、波動率、支撐與壓力。
- 基本面:營收與獲利成長、利潤率、資產負債、現金流、估值。
- 產業面:競爭位置、需求週期、供應鏈、替代技術與議價能力。
- 事件面:財報、公司新聞、監管、產品與資本配置。
- 總體面:利率、匯率、關稅、政策、地緣政治與景氣循環。
- 多方研究員:整理資料支持的最強正面論點。
- 空方研究員:整理最強反面論點、反證與失效條件。
- 風險審查員:檢查資料日期、缺漏、指標衝突、估值假設與敘事過度延伸。
完成條件:每個重要論點皆有數據、已確認事件或明確資料缺口對應。
4. 處理衝突與市場差異
不要強迫不同時間尺度得出同一方向。例如短期動能強、但估值高與現金流轉弱,可以同時成立。跨市場比較時必須額外處理:
- 幣別與匯率
- 會計準則與財報期間
- 交易時間與報價日期
- 產業結構與市場估值基準
- 資料供應商欄位定義
完成條件:衝突被保留並解釋,不用單一分數掩蓋不確定性。
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.
- 2mo ago First seen · 146 lines · 42 tokens per session scan A b81093004861
stock-analysis is a skill published in the GitHub repository Gratia2533/pipe-stock-analysis (24 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,809 once invoked, about $0.0002 per session on Opus 5.5. 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.
stock-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stock-analysisGratia2533/pipe-stock-analysis | Skill | 24 | 3mo ago | MIT | A | 42 | Claude Code, Codex |
| factor-researchHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 32 | Claude Code, Codex |
| macro-analysisHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 40 | Claude Code, Codex |
| valuation-modelHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 46 | Claude Code, Codex |
| polymarketNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 18 | Claude Code, Codex |
| crypto-market-ranktradecatlabs/tradecat-public | Skill | 959 | 2mo ago | MIT | A | 85 | Claude Code, Codex |
| simple-earntradecatlabs/tradecat-public | Skill | 959 | 2mo ago | MIT | A | 23 | Claude Code, Codex |