K-Dense-AI/scientific-agent-skills / skills/exa-search
exa-search
VerifiedSearches 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.2 KB |
| references/web-extract.md | markdown | 3.4 KB |
| references/web-search.md | markdown | 6.5 KB |
| scripts/exa_extract.py | script | 4.4 KB |
| scripts/exa_search.py | script | 6.4 KB |
scripts/exa_extract.py
View on GitHub#!/usr/bin/env python3
# /// script
# requires-python = ">=3.11"
# dependencies = ["exa-py>=2.23.0,<3"]
# ///
"""Fetch and extract content from URLs using Exa's /contents endpoint.
Example:
uv run exa_extract.py \\
https://arxiv.org/abs/2401.04088 \\
https://www.nature.com/articles/s41586-024-07566-y \\
--text \\
-o extracted.json
"""
from __future__ import annotations
import argparse
import json
import os
import sys
from dataclasses import asdict, dataclass, field
from typing import Any
try:
from exa_py import Exa
except ImportError:
print(
"exa_py not installed. Run: uv pip install exa-py (or invoke with: uv run --with exa-py)",
file=sys.stderr,
)
sys.exit(2)
EXA_INTEGRATION_HEADER = "k-dense-ai--scientific-agent-skills"
@dataclass
class ExtractedDocument:
"""Typed view of a single extracted document for JSON export."""
url: str
id: str | None
title: str | None
author: str | None
published_date: str | None
text: str | None = None
highlights: list[str] = field(default_factory=list)
def _build_contents(text: bool, highlights: bool) -> dict[str, Any]:
contents: dict[str, Any] = {}
if text:
contents["text"] = True
if highlights:
contents["highlights"] = True
if not text:
# get_contents otherwise inserts default text even with highlights=True.
contents["text"] = False
if not contents:
# Default to full text when the caller doesn't pick anything.
contents["text"] = True
return contents
def _to_typed(item: Any) -> ExtractedDocument:
return ExtractedDocument(
url=getattr(item, "url", ""),
id=getattr(item, "id", None),
title=getattr(item, "title", None),
author=getattr(item, "author", None),
published_date=getattr(item, "published_date", None),
text=getattr(item, "text", None),
highlights=list(getattr(item, "highlights", None) or []),
)
def run(args: argparse.Namespace) -> dict[str, Any]:
if not 1 <= len(args.urls) <= 100:
raise ValueError("Supply 1-100 URLs; split larger lists into separate calls.")
if args.max_age_hours is not None and not -1 <= args.max_age_hours <= 720:
raise ValueError("--max-age-hours must be between -1 and 720.")
api_key = os.environ.get("EXA_API_KEY")
if not api_key:
print("EXA_API_KEY environment variable is not set.", file=sys.stderr)
sys.exit(2)
client = Exa(api_key=api_key)
client.headers["x-exa-integration"] = EXA_INTEGRATION_HEADER
contents = _build_contents(args.text, args.highlights)
if args.max_age_hours is not None:
contents["max_age_hours"] = args.max_age_hours
response = client.get_contents(urls=args.urls, **contents)
typed = [_to_typed(item) for item in getattr(response, "results", []) or []]
return {
"urls": list(args.urls),
"num_results": len(typed),
"results": [asdict(doc) for doc in typed],
"statuses": [
{key: getattr(status, key, None) for key in ("id", "status", "source")}
for status in getattr(response, "statuses", None) or []
],
}
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(description="Extract content from URLs with Exa.")
parser.add_argument("urls", nargs="+", help="One or more URLs to extract.")
parser.add_argument("--text", action="store_true", help="Return full-text content.")
parser.add_argument("--highlights", action="store_true", help="Return extracted highlight snippets.")
parser.add_argument("--max-age-hours", type=int, default=None,
help="Cache age limit (-1 to 720): 0 fetches fresh; -1 uses cache only; omitted uses API fallback policy.")
parser.add_argument("-o", "--output", default=None, help="Write JSON to this file (default: stdout).")
return parser
def main(argv: list[str] | None = None) -> int:
parser = build_parser()
args = parser.parse_args(argv)
try:
payload = run(args)
except ValueError as exc:
parser.error(str(exc))
text = json.dumps(payload, indent=2, ensure_ascii=False)
if args.output:
with open(args.output, "w", encoding="utf-8") as fh:
fh.write(text)
print(f"Wrote {len(payload['results'])} documents to {args.output}")
else:
print(text)
return 0
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |