exa-search

Name: exa-search
Author: K-Dense-AI

675installs3.1kforks

How to install exa-search?

k-dense-ai/scientific-agent-skills/exa-search

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill exa-search

Installs into the current project.

Summary

Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filt

Files · 1

View on GitHub

SKILL.md

1	# Exa Web Toolkit
2
3	A skill for web-powered research tasks backed by [Exa](https://exa.ai): 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.
4
5	## Routing — pick the right capability
6
7	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.
8
9	\| User wants to... \| Capability \| Where \|
10	\|---\|---\|---\|
11	\| Look something up, research a topic, find current info \| Web Search \| `references/web-search.md` \|
12	\| Fetch content from a specific URL (webpage, article, PDF) \| Web Extract \| `references/web-extract.md` \|
13	\| Install or authenticate \| Setup \| Below \|
14
15	### Decision guide
16
17	- 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.
18	- 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.
19
20	### Academic source priority
21
22	For technical or scientific queries, prefer academic and scientific sources:
23	- Peer-reviewed journal articles and conference proceedings over blog posts or news
24	- Preprints (arXiv, bioRxiv, medRxiv) when peer-reviewed versions aren't available
25	- Institutional and government sources (NIH, WHO, NASA, NIST) over commercial sites
26	- Primary research over secondary summaries
27
28	Two levers to steer Exa toward scholarly content:
29	1. `--category "research paper"` biases retrieval toward scholarly sources.
30	2. `--include-domains` with a scholarly allowlist (arxiv.org, nature.com, pubmed.ncbi.nlm.nih.gov, etc.) restricts the domain pool.
31
32	Combine both for strictly academic results. See `references/web-search.md` for the full pattern.
33
34	When citing academic sources, include author names and publication year where available (e.g., [Smith et al., 2025](url)) in addition to the standard citation format. If a DOI is present, prefer the DOI link.
35
36	---
37
38	## Setup
39
40	This skill uses the [`exa-py`](https://github.com/exa-labs/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:
41
42	```bash
43	uv run --with exa-py python "$SKILL_PATH/scripts/exa_search.py" --help
44	```
45
46	If you prefer a persistent install:
47
48	```bash
49	uv pip install "exa-py>=1.14.0"
50	```
51
52	### Authentication
53
54	All commands read the API key from the `EXA_API_KEY` environment variable. Get your Exa API key at [dashboard.exa.ai/api-keys](https://dashboard.exa.ai/api-keys).
55
56	First, check if a `.env` file exists in the project root and contains `EXA_API_KEY`. If so, load it:
57
58	```bash
59	dotenv -f .env run -- uv run --with exa-py python "$SKILL_PATH/scripts/exa_search.py" "your query"
60	```
61
62	If `dotenv` isn't available, install it: `pip install python-dotenv[cli]` or `uv pip install python-dotenv[cli]`.
63
64	If there's no `.env`, export the key for the session:
65
66	```bash
67	export EXA_API_KEY="your-key"
68	```
69
70	Verify by running any script with `--help` — it will exit cleanly if the key is set and auth-check runs only when a real query is made.
71
72	### Tracking header
73
74	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.
75
76	---
77
78	## Files in this skill
79
80	- `SKILL.md` — this file (routing and setup)
81	- `references/web-search.md` — detailed web search reference with academic strategy

People who liked this also viewed

6 picks

Type

exa-search

675installs3.1kforks

View on GitHub

How to install exa-search?

k-dense-ai/scientific-agent-skills/exa-search

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill exa-search

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Exa Web Toolkit
2
3	A skill for web-powered research tasks backed by [Exa](https://exa.ai): 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.
4
5	## Routing — pick the right capability
6
7	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.
8
9	\| User wants to... \| Capability \| Where \|
10	\|---\|---\|---\|
11	\| Look something up, research a topic, find current info \| Web Search \| `references/web-search.md` \|
12	\| Fetch content from a specific URL (webpage, article, PDF) \| Web Extract \| `references/web-extract.md` \|
13	\| Install or authenticate \| Setup \| Below \|
14
15	### Decision guide
16
17	- 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.
18	- 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.
19
20	### Academic source priority
21
22	For technical or scientific queries, prefer academic and scientific sources:
23	- Peer-reviewed journal articles and conference proceedings over blog posts or news
24	- Preprints (arXiv, bioRxiv, medRxiv) when peer-reviewed versions aren't available
25	- Institutional and government sources (NIH, WHO, NASA, NIST) over commercial sites
26	- Primary research over secondary summaries
27
28	Two levers to steer Exa toward scholarly content:
29	1. `--category "research paper"` biases retrieval toward scholarly sources.
30	2. `--include-domains` with a scholarly allowlist (arxiv.org, nature.com, pubmed.ncbi.nlm.nih.gov, etc.) restricts the domain pool.
31
32	Combine both for strictly academic results. See `references/web-search.md` for the full pattern.
33
34	When citing academic sources, include author names and publication year where available (e.g., [Smith et al., 2025](url)) in addition to the standard citation format. If a DOI is present, prefer the DOI link.
35
36	---
37
38	## Setup
39
40	This skill uses the [`exa-py`](https://github.com/exa-labs/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:
41
42	```bash
43	uv run --with exa-py python "$SKILL_PATH/scripts/exa_search.py" --help
44	```
45
46	If you prefer a persistent install:
47
48	```bash
49	uv pip install "exa-py>=1.14.0"
50	```
51
52	### Authentication
53
54	All commands read the API key from the `EXA_API_KEY` environment variable. Get your Exa API key at [dashboard.exa.ai/api-keys](https://dashboard.exa.ai/api-keys).
55
56	First, check if a `.env` file exists in the project root and contains `EXA_API_KEY`. If so, load it:
57
58	```bash
59	dotenv -f .env run -- uv run --with exa-py python "$SKILL_PATH/scripts/exa_search.py" "your query"
60	```
61
62	If `dotenv` isn't available, install it: `pip install python-dotenv[cli]` or `uv pip install python-dotenv[cli]`.
63
64	If there's no `.env`, export the key for the session:
65
66	```bash
67	export EXA_API_KEY="your-key"
68	```
69
70	Verify by running any script with `--help` — it will exit cleanly if the key is set and auth-check runs only when a real query is made.
71
72	### Tracking header
73
74	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.
75
76	---
77
78	## Files in this skill
79
80	- `SKILL.md` — this file (routing and setup)
81	- `references/web-search.md` — detailed web search reference with academic strategy

People who liked this also viewed

6 picks

Type