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.

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 publication 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 publication 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 to narrow the source pool; verify publication type and peer-review status on each source. 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.

Setup

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 "$SKILL_PATH/scripts/exa_search.py" --help

If you prefer a persistent install:

uv pip install "exa-py>=2.23.0,<3"

Authentication

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 "$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

The extractor accepts 1–100 URLs per POST https://api.exa.ai/contents call and exports each SDK status (id, status, source). It rejects larger batches. Use --max-age-hours 0 to request fresh content, -1 for cache only, or a positive age up to 720 hours. Omission uses Exa's cache/fallback policy. published_date is estimated publication metadata, not retrieval time. The tested SDK drops per-URL error details, so report failures without inventing a cause. See URL Extraction.

Verified API and SDK scope

Reviewed the Search API, Contents API, and Exa changelog on 2026-09-30. Both routes use JSON POST requests and x-api-key authentication (the SDK sets this header). Search is POST https://api.exa.ai/search; its SDK kwargs use snake_case and

…