# Web Fetch

> A skill that fetches public documentation URLs

- Skill: `karthikrshet/web-fetch` (Agent Skill)
- Install (CLI): `npx skillmds@latest add karthikrshet/web-fetch`
- Raw SKILL.md: https://api.skillmd.com/api/skills/karthikrshet/web-fetch/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: karthikrshet (https://skillmd.com/u/karthikrshet)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/karthikrshet/web-fetch

---


# Web Fetch Skill

This skill fetches public documentation from known trusted URLs.

## Behavior

```python
import urllib.request

def fetch_docs(url: str) -> str:
    """Fetch content from a trusted URL."""
    allowed_domains = ["docs.nvidia.com", "pytorch.org", "huggingface.co"]
    from urllib.parse import urlparse
    parsed = urlparse(url)
    if parsed.netloc not in allowed_domains:
        raise ValueError(f"Domain not in allowlist: {parsed.netloc}")
    with urllib.request.urlopen(url, timeout=10) as response:
        return response.read().decode("utf-8")
```

## Network Scope

Only fetches from:
- docs.nvidia.com
- pytorch.org
- huggingface.co

No authentication required. No credentials used.