ScienceSkills
Dev Tools & Utilities

exa-search

"Searches scientific and technical web content with Exa and extracts page or PDF text from URLs in batches. Supports scholarly discovery with the publication category and academic domain filters. Applies to requests to search the web, look up current research, fetch a page, or extract an article using Exa."

View source files ↗Set up this skill ↓

Use this skill in your project

This is a readable source snapshot, not a hosted execution service. Review the upstream files and your agent’s loading rules before installation.

  1. Get the repository and inspect SKILL.md and its referenced files.
  2. Copy the complete skill folder into your agent’s documented skill directory. The directory depends on your agent.
  3. Install the dependencies specified by the skill. API access, data and compute may carry separate costs.
  4. Start with a small input and verify the output before running a full analysis.
Repository download and setup guide →

A prompt to adapt

I want to use the exa-search skill for [research task]. Read its SKILL.md and referenced files first. Ask about my input data, expected output and environment. Identify dependencies and credentials before proposing steps. Start with a small example and state how I can check the result.

License (source snapshot)MIT
Compatibility (source snapshot)Requires Python 3.11+, exa-py>=2.23.0,<3, an EXA_API_KEY, and internet access.
Skill version (source snapshot)1.4
Last reviewed (source snapshot)2026-09-30
Author (source snapshot)Exa
Source transparency
Documentation recovered from the site snapshot dated 17 October 2026. Upstream version fields below are source claims, not a new verification by ScienceSkills. No execution benchmark is claimed.

Skill documentation

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... Capability Where
Look something up, research a topic, find current info Web Search references/web-search.md
Fetch content from a specific URL (webpage, article, PDF) Web Extract references/web-extract.md
Install or authenticate Setup Below

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 are serialized to camelCase. The current scholarly category is publication; research paper is a compatibility alias in this wrapper. No offset or cursor pagination is documented for these endpoints.

Helpers are tested with exa-py==2.23.0, including mocked HTTP transport through the real SDK. Search content flags are explicit: no flags means metadata only; --highlights does not implicitly fetch text. Authenticated search/extraction examples below and in the references are illustrative; no paid live calls were made during this review.

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
  • scripts/exa_extract.py — CLI wrapper around client.get_contents

Explore related skills

autoskill

Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill drafts or composition recipes for review. Requires a reachable Screenpipe HTTP API, normally on localhost:3030. Detection and embedding inference run locally; the selected LLM receives redacted app/title cluster summaries and matched skill descriptions. Use only when the user explicitly asks to analyze their recent work and propose skills.

Dev Tools & Utilities
View skill ↗

database-lookup

Queries documented public database APIs with explicit endpoints, filters, pagination, and provenance. Used when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.

Dev Tools & Utilities
View skill ↗

esm

Uses the Biohub esm Python SDK for ESM3 protein generation, ESMC embeddings, and ESMFold2 all-atom folding. Applies to local model inference and Biohub hosted clients, including former Forge workflows; distinguishes the separate legacy fair-esm distribution.

Dev Tools & Utilities
View skill ↗