返回 Skills 目錄
來源：Scientific Agent Skills
🌐

Exa Search

📝學術寫作與文獻

以 Exa 進行偏重科學與技術內容的網路搜尋與網址內容擷取（含論文類別與學術網域篩選）。

安裝方式原始 SKILL.md

安裝教學

選擇你使用的 AI coding agent，複製指令到終端機執行

一鍵安裝（需要 Node.js）
npx skills add K-Dense-AI/scientific-agent-skills --skill exa-search -g -a claude-code -y
手動安裝（不使用 npx）
clone 後複製到 skills 目錄
git clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills.git
mkdir -p ~/.claude/skills
cp -r scientific-agent-skills/skills/exa-search ~/.claude/skills/exa-search

Skills 會以 agent 的完整權限執行，安裝前請先閱讀原始 SKILL.md。安裝後重新啟動 agent 即可使用。

使用教學

Exa Web Toolkit

A skill for web-powered research tasks backed by Exa: web search and URL extraction. Exa's index combines high-quality keyword and semantic retrieval, which makes it well-suited to scientific, technical, and conceptual queries.

Routing — pick the right capability

Read the user's request and match it to one of the capabilities below. Read the corresponding reference file for detailed instructions before running commands.

User wants to...CapabilityWhere
Look something up, research a topic, find current infoWeb Searchreferences/web-search.md
Fetch content from a specific URL (webpage, article, PDF)Web Extractreferences/web-extract.md
Install or authenticateSetupBelow

Decision guide

  • Default to Web Search for topic lookups, research questions, or "what is X?" queries. When the topic is scientific or technical, pass --category "research paper" to bias toward scholarly sources, and/or an academic --include-domains allowlist. See references/web-search.md for the two-pass academic strategy.
  • Use Web Extract when the user provides a URL or asks you to read/fetch a specific page. Prefer this over the built-in WebFetch for batch extraction (multiple URLs in one call) and for academic PDFs.

Academic source priority

For technical or scientific queries, prefer academic and scientific sources:

  • Peer-reviewed journal articles and conference proceedings over blog posts or news
  • Preprints (arXiv, bioRxiv, medRxiv) when peer-reviewed versions aren't available
  • Institutional and government sources (NIH, WHO, NASA, NIST) over commercial sites
  • Primary research over secondary summaries

Two levers to steer Exa toward scholarly content:

  1. --category "research paper" biases retrieval toward scholarly sources.
  2. --include-domains with a scholarly allowlist (arxiv.org, nature.com, pubmed.ncbi.nlm.nih.gov, etc.) restricts the domain pool.

Combine both for strictly academic results. See references/web-search.md for the full pattern.

When citing academic sources, include author names and publication year where available (e.g., Smith et al., 2025) in addition to the standard citation format. If a DOI is present, prefer the DOI link.

設定

This skill uses the exa-py Python SDK. The scripts in scripts/ declare their dependencies via PEP 723 inline metadata, so you can run them directly with uv run without a separate install step:

uv run --with exa-py python "$SKILL_PATH/scripts/exa_search.py" --help

If you prefer a persistent install:

uv pip install "exa-py>=1.14.0"

身份驗證

All commands read the API key from the EXA_API_KEY environment variable. Get your Exa API key at dashboard.exa.ai/api-keys.

First, check if a .env file exists in the project root and contains EXA_API_KEY. If so, load it:

dotenv -f .env run -- uv run --with exa-py python "$SKILL_PATH/scripts/exa_search.py" "your query"

If dotenv isn't available, install it: uv pip install python-dotenv[cli].

If there's no .env, export the key for the session:

export EXA_API_KEY="your-key"

Use --help to verify installation and CLI parsing; it does not require an API key or validate authentication. Authentication is checked only when a real query is made.

Extraction limits and freshness

For /contents, split requests into batches of at most 100 URLs. The bundled extractor makes one call and does not split oversized batches. Its JSON preserves requested URLs and returned results, but drops the API's per-URL status details; compare requested and returned URLs and report missing content without guessing the failure cause. Cached content is possible: published_date is not retrieval time, and this CLI exposes no freshness control. If current-page verification is required, use the documented API freshness option or a direct page fetch and record when it was retrieved. See the Contents API.

Tracking header

Every script in this skill sets the x-exa-integration request header to k-dense-ai--scientific-agent-skills so Exa can attribute usage from the K-Dense AI scientific-agent-skills repo to this integration. Do not remove or rename this header when adapting the scripts.

Files in this skill

  • SKILL.md — this file (routing and setup)
  • references/web-search.md — detailed web search reference with academic strategy
  • references/web-extract.md — URL content extraction reference
  • scripts/exa_search.py — CLI wrapper around client.search_and_contents
  • scripts/exa_extract.py — CLI wrapper around client.get_contents
回到頁首