investment-research-briefs

作者: tavily-ai

編寫簡明的投資研究简报、公司備忘錄、行業概覽、投資組合監控更新、財報/新聞摘要、風險與催化劑简报等……

npx skills add https://github.com/tavily-ai/use-case-skills --skill investment-research-briefs

Investment Research Briefs

Workflow

Use search and extract for quick investor briefs and source checks, research for full investment memos, and map or crawl only for large known source collections. Keep this skill focused on research design, source selection, verification, and synthesis; execution mechanics should come from companion endpoint skills.

Treat the guidance below as base guidance; adapt it to the user's request when appropriate.

  • Define the target, investor lens, geography, timeframe, asset type, and desired depth.
  • For quick briefs, split into short subqueries under 400 characters: business overview, market position, financial/operating signals, recent developments, competitors, risks, catalysts, and valuation/comps if requested.
  • Prefer filings, investor relations pages, earnings materials, company pages, regulators, exchanges, reputable financial media, and market sources.
  • For deeper memos, provide a clear research goal, known context, constraints, target market, and desired output shape.
  • Verify specific metrics, quotes, management claims, filings, and high-impact assertions against original or authoritative sources.
  • Separate sourced facts, inferred interpretation, and open diligence questions.

Research Budget

  • Start with a small focused search set covering business context, recent developments, financial/operating signals, and risks/catalysts.
  • Extract only the strongest sources before drafting a concise brief.
  • Add more searches only for named gaps, such as missing filing evidence, missing earnings context, or missing competitor context.
  • Do not use map unless a known investor-relations, filing, transcript, or presentation library has buried pages.
  • Do not use research unless the user asks for a full memo, sector landscape, or multi-source thesis.

Capability Guidance

  • Use search for fast discovery across companies, sectors, filings, news, competitors, and market context.
  • Use extract to verify metrics, quotes, filings, management claims, transcripts, and other high-impact assertions.
  • Use research for full investment memos, sector landscapes, or multi-source thesis work.
  • Use map or crawl only for large investor-relations, filing, transcript, or presentation libraries.

Query And Source Guidance

  • Use company legal name, ticker, product names, segment names, geography, competitor names, and reporting period in queries.
  • For public companies, prioritize original filings, earnings calls, investor presentations, regulator pages, and exchange notices.
  • For private companies, triangulate from company pages, funding announcements, customer stories, hiring, product documentation, and credible press.
  • For recent developments, make the timeframe explicit in the query.
  • For competitor or sector work, build separate subqueries for category, demand drivers, pricing, regulation, customer adoption, and risks.
  • Include known assumptions or prior context in broad research requests to avoid rediscovering what is already known.
  • Report failed or unavailable sources when they affect filings, transcripts, IR pages, market data, or cited claims.

Output Template

Use this markdown structure and adapt sections to the user's mandate:

# Investment Brief: <company/sector/theme>

## Executive Summary
<concise bullets with the main investor-relevant takeaways>

## Business And Market Context
- Business model:
- Customers/segments:
- Market position:
- Competitors:

## Recent Developments
- <dated development with source>

## Signals
- Financial or operating signals:
- Product, customer, hiring, or partnership signals:
- Regulatory or macro signals:

## Risks
- <risk>: <evidence and uncertainty>

## Catalysts And Watch Items
- <catalyst/watch item>: <why it matters>

## Open Diligence Questions
- <question>

## Sources
- [Source title](URL) - <what it supports>

Do not provide personalized financial advice. State when source coverage is thin, stale, or incomplete.

來自 tavily-ai 的更多技能

research
tavily-ai
針對任何主題進行全面研究,自動收集來源、分析並提供引用。執行多來源網路研究並附上明確引用,適合比較、時事、市場分析及詳細報告。提供三種模型選項:mini 針對單一主題的目標研究(約30秒)、pro 進行全面的多角度分析(約60-120秒),以及 auto 透過 API 驅動的複雜度偵測。透過 Tavily MCP 伺服器以 OAuth 進行驗證,並在...上自動執行基於瀏覽器的登入。
search
tavily-ai
使用LLM優化結果的網路搜尋,具備相關性評分與靈活篩選功能。支援四種搜尋深度模式(極速、快速、基本、進階),可配置延遲與相關性權衡。包含網域篩選、時間範圍限制、日期區間、國家加權及原始內容提取。回傳結果包含標題、網址、內容摘要與相關性評分;可選圖片結果與網站圖示。透過Tavily MCP伺服器或API金鑰配置自動進行OAuth驗證;...
tavily-best-practices
tavily-ai
專為LLM設計的網路搜尋API,具備即時資料存取、內容擷取、網站爬取及AI驅動研究功能。五大核心方法:search()用於搜尋網頁結果、extract()用於擷取URL內容、crawl()用於全站擷取、map()用於URL探索,以及research()用於端到端AI綜合分析。支援Python與JavaScript SDK,提供非同步客戶端以進行平行查詢,並可設定搜尋深度(極速/快速/基本/進階)。Crawl方法接受語意指令,以聚焦於特定內容的擷取...
tavily-cli
tavily-ai
透過 Tavily CLI 進行網路搜尋、內容提取、網站爬取與深度研究。五種指令模式涵蓋搜尋、提取、URL 發現、批量爬取及附引用來源的多來源研究。所有指令皆支援 JSON 輸出與檔案儲存,適用於結構化、代理式工作流程。升級模式引導您從簡單搜尋,逐步進展至提取、映射、爬取,乃至依需求進行的全面研究。需安裝 tavily-cli 並透過 tvly login 進行 API 金鑰驗證。
tavily-crawl
tavily-ai
多頁面網站爬蟲,具備語意過濾與Markdown匯出功能。可透過深度與廣度控制爬取整個網站區塊;依路徑正則表達式、網域或自然語言指令進行過濾,以聚焦結果。透過--output-dir將每個頁面儲存為本機Markdown檔案,或回傳結構化JSON供代理處理。使用語意指令搭配區塊提取,避免將結果餵入LLM時發生上下文膨脹;採用全頁提取進行離線文件下載。支援...
tavily-dynamic-search
tavily-ai
搜尋網路、篩選結果並擷取內容,讓原始搜尋資料絕不進入你的上下文視窗。只有你精心整理的 print() 輸出會回傳。
tavily-extract
tavily-ai
從最多20個URL中提取乾淨的Markdown或純文字,支援JavaScript渲染與查詢聚焦區塊切割。可處理JavaScript渲染頁面,並提供可設定的提取深度(基本模式適用於簡單頁面,進階模式適用於動態SPA與表格)。支援查詢聚焦提取,僅回傳相關內容區塊而非完整頁面。預設回傳經LLM最佳化的Markdown格式,亦可選擇純文字格式與結構化JSON輸出。單次呼叫可處理最多20個URL;...
tavily-research
tavily-ai
全面的AI驅動研究,具備多來源綜合與引用功能。可生成基於網路來源的結構化報告,耗時30-120秒,視模型選擇而定(mini適用於精準查詢,pro適用於複雜比較)。支援多種輸出格式:Markdown報告、自訂架構的JSON,以及可設定的引用格式(數字、MLA、APA、芝加哥)。包含非同步工作流程,可透過--no-wait、status和poll指令進行長時間研究,並支援即時...