OpenParable
Skip to content
← Back to skills

URL

Research
url

URL is an Agent Skill for research published in the axoviq-ai/synthadoc repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Fetch and extract text from web URLs

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/axoviq-ai/synthadoc/blob/HEAD/synthadoc/skills/url/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/url, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

URL Skill

Fetches a web URL using httpx, strips navigation/script/style tags with BeautifulSoup, and returns clean body text. PDF URLs are extracted with pypdf (primary) and pdfminer.six (fallback).

Setup

pip install httpx beautifulsoup4

# Optional — needed only if you ingest PDF URLs:
pip install pypdf pdfminer.six

Standalone usage

import asyncio
from synthadoc.skills.url.scripts.main import UrlSkill

skill = UrlSkill()

async def main():
    result = await skill.extract("https://example.com/article")
    print(result.text)          # clean body text
    print(result.metadata)      # {"url": "https://..."}

asyncio.run(main())

DomainBlockedException is raised when the site returns HTTP 401, 403, or 429. Catch it to log and skip the domain:

from synthadoc.skills.base import DomainBlockedException

try:
    result = await skill.extract(url)
except DomainBlockedException as e:
    print(f"Blocked: {e.domain} (HTTP {e.status_code})")

When this skill is used

  • Source starts with https:// or http://
  • User intent contains: fetch url, web page, website