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 nickolaslin33/agent-skills --skill stock-article-digestgit clone --depth 1 https://github.com/nickolaslin33/agent-skillsWrote 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/nickolaslin33/agent-skills/stock-article-digest)<a href="https://agentmods.dev/skills/nickolaslin33/agent-skills/stock-article-digest"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/stock-article-digest/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/nickolaslin33/agent-skills/stock-article-digest"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/stock-article-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00259 | $0.03072 |
| Opus 5.5 | $0.00104 | $0.01229 |
| Sonnet 5.5 | $0.00052 | $0.00614 |
| Haiku 4.5 | $0.00026 | $0.00307 |
Grade A, and why
stock-article-digest scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 有些 Python 安裝沒接上系統憑證庫，HTTPS 會驗證失敗，腳本會自動改用 `curl` 抓，不會關掉憑證驗證。 How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
股市文章摘要
把一篇股市文章變成一份格式固定的 Markdown 檔，存起來。格式固定是為了之後能寫程式整批掃：哪些文章提過 TWO:3324、上個月有幾篇在講 HBM。
這份 skill 的規則多半在防同一件事：股市資料最怕模型自己編。編出來的 EPS、記錯的代號，混在真資料裡就再也挑不出來。所以能交給程式查的就交給程式，查不了的就標清楚是誰說的。
流程
1. 抽內容
輸入是網址或存下來的網頁原始碼，都交給 extract.py：
python3 scripts/extract.py <網址或 HTML 檔>
它回傳 JSON：標題、發布日期、正文、留言、圖片說明，以及 warnings。使用者直接貼純文字就跳過這步，自己讀。
published是 null 的話，正文裡有明寫日期（像 PTT 的「時間 Tue Oct 13 18:44:51 2026」）就用它，date_from寫text；正文也沒有就寫unknown。不要填今天，處理日期另外記在processed，兩個混在一起之後就分不出哪篇是舊文。comments是空的就照warnings講的，在留言段落寫「原文未附留言」，並在回覆裡告訴使用者：要留言就在瀏覽器展開後另存網頁原始碼。不要從正文推測留言區在說什麼。
2. 判斷模式
使用者的訊息有「完整轉換」就是 full，否則是 digest。
digest：核心摘要 3 到 5 點，其他段落精簡。full：核心摘要不限點數，並在核心摘要後面多一段## 逐段整理，照原文順序把每個論點、數字、舉例都留下來。
3. 查代號
把文章提到的每家公司，連同你打算補充的公司，一次查完：
python3 scripts/tickers.py lookup 台積電 雙鴻 NVDA 美律
美股清單只有英文名，「美光」要查成 Micron 或 MU。
照查詢結果寫代號，不要憑記憶。台股代號模型常常記錯，上市（TW）、上櫃（TWO）、興櫃（TWE）也容易搞混，例如雙鴻是上櫃的 TWO:3324。
| 狀況 | 代號寫法 | verified |
|---|---|---|
| 查到唯一一筆 | 照查詢結果，例如 TW:2330、興櫃的 TWE:3097 |
listed |
| 查到多筆 | 依文章脈絡挑一筆；挑不出來就問使用者 | listed |
已下市（查詢結果有 delisted 日期，或你確定它下市前的代號） |
寫下市前的代號，例如 TW:2325（矽品） |
delisted |
| 查不到（含未上市公司） | TW:?（市場照你的判斷） |
not-found |
| 日股、韓股、港股、台股 ETF | 依格式寫，例如 KR:005930、JP:8035、TW:0050 |
format-only |
查詢會一併搜終止上市的清單，但上櫃公司下櫃沒有公開清單。上櫃下櫃的公司要寫代號，得有可靠的出處，查不到就寫 ?。官方簡稱常寫「臺」（臺慶科），name 照官方簡稱寫。
台股的 industry 照查詢結果的官方產業別填。官方分類很粗（奇鋐是散熱廠，官方卻是「電腦及週邊設備業」），所以它只能擋掉離譜的錯，例如把食品股當成散熱股。
4. 寫摘要
照下面的「輸出格式」寫。幾條規則和它們的理由：
- 財務數字只收原文寫的。 每一列都要在「原文依據」貼一小段原文。原文沒有的季度、沒有的 EPS 就不要寫，就算你記得也不要。整篇沒有數字就寫「本文未提及」。這張表會被程式讀去做比較，一個記憶裡的數字混進來，整張表就不能信了。
- 補充的公司要標。 概念股表可以補原文沒提的公司，但「來源」欄要寫
補充，front matter 的origin也寫補充。補之前先查代號，看看官方產業別合不合理。這樣之後寫程式時，才能只挑原文提到的公司。 - 只整理原文，不加自己的東西。 不要自己出題自答、不要寫投資建議、不要附延伸閱讀或搜尋關鍵字。這份檔案是文章的紀錄，混進你的分析，之後就分不清哪些是作者說的。唯一的例外是概念股表的
補充，因為有標記。 - 圖片只能推測。 只能根據
extract.py給的圖片說明和上下文推測，段落標題寫「推測」，不要描述你沒看到的圖表數字。 - 標籤用固定清單。
sectors和tags只能用references/tag-vocabulary.md裡的字。清單裡沒有合適的，可以用新標籤，但要同時列進new_tags。 - 語氣：專業、客觀、直接。不要寒暄、不要免責聲明、不要在結尾問「還需要什麼」。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 154 lines · 259 tokens per session scan A ed44841522f0
stock-article-digest is a skill published in the GitHub repository nickolaslin33/agent-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 259 tokens to every session and 3,072 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
recipe-daily-pnl-report
Generate a daily profit and loss summary from trades and balances.