# nansen-web-fetcher

Fetch pages from supplied URLs and ask Gemini 2.5 Flash about their contents. Use it to inspect a specific page or compare several sites.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 457 installs · ★ 139
- Author: nansen-ai
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/nansen-ai/nansen-cli/tree/HEAD/skills/nansen-web-fetcher/SKILL.md
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/skills/nansen-web-fetcher

## What it does

The skill runs `nansen web fetch` with one or more URLs and a required question. Its response contains an AI-generated analysis, successfully retrieved URLs, and URLs that failed. You can mix positional URLs with repeatable `--url` flags, up to 20 addresses.

You need the `nansen` CLI and authentication through `NANSEN_API_KEY` or a selected `nansen:api` browser session. The fetch uses Gemini 2.5 Flash with URL context. Requests have a 30-second timeout; paywalled pages and pages that block bots may fail to load. That matters when the target site restricts access.

Install the skill in Claude Code with the command below. The installed file is `~/.claude/skills/nansen-web-fetcher/SKILL.md`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add nansen-ai/nansen-cli --skill nansen-web-fetcher -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/nansen-web-fetcher/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/nansen-web-fetcher/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add nansen-ai/nansen-cli --skill nansen-web-fetcher -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/nansen-web-fetcher/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add nansen-ai/nansen-cli --skill nansen-web-fetcher -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/nansen-web-fetcher/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install nansen-ai/nansen-cli nansen-web-fetcher
```

2. **Manually: put the files in place**
- File: `.github/skills/nansen-web-fetcher/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add nansen-ai/nansen-cli --skill nansen-web-fetcher -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/nansen-ai/nansen-cli --path skills/nansen-web-fetcher
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/nansen-web-fetcher/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add nansen-ai/nansen-cli --skill nansen-web-fetcher -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/nansen-ai/nansen-cli/tree/HEAD/skills/nansen-web-fetcher/SKILL.md

## When to use it
- get an answer based on a specific webpage
- compare content across several URLs
- analyze pages found through web search
- identify URLs that could not be retrieved

## Example prompts
- Read `https://example.com` and explain what the page says about its products.
- Compare `https://example.com` with `https://other.com` and describe how their offerings differ.
- Review `https://docs.uniswap.org/contracts/v4/overview` and summarize the changes it describes.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 7499c956af51f468.

BEGIN THIRD-PARTY FILE 7499c956af51f468
````text
---
name: nansen-web-fetcher
description: Fetch and analyze content from one or more URLs using AI (Gemini 2.5 Flash). Use when you have specific URLs and need to extract or summarize their content. Pairs well with `nansen web search` results.
metadata:
  openclaw:
    requires:
      bins:
        - nansen
    primaryEnv: NANSEN_API_KEY
    install:
      - kind: node
        package: nansen-cli
        bins: [nansen]
allowed-tools: Bash(nansen:*)
---
## Authentication

Nansen account API calls accept a selected `nansen:api` browser session or conventional API key with the same permissions. `NANSEN_API_KEY` takes precedence; optional `primaryEnv` preserves configured-key injection. Run `nansen auth status` for offline selection. Cached access expiry alone permits automatic renewal during an authorized task. Stop on anonymous selection, invalid state, blocked/uncertain renewal or actual auth failure; never drop a credential or fall back to anonymous x402 payment. Browser login does not grant wallet signing, privileged service identity or a persistent MCP integration key. Preserve all confirmation, signing, sanctions and geographic checks below. Browser login is available in CLI 2.0.0 within the [macOS arm64 preview scope](https://github.com/nansen-ai/nansen-cli/blob/main/docs/browser-login.md#preview-platform-scope).



# Web Fetch

Fetch and analyze content from one or more URLs using Gemini 2.5 Flash with URL context.

```bash
nansen web fetch https://nansen.ai --question "What products does Nansen offer?"
nansen web fetch --url https://example.com --url https://other.com --question "Compare these two sites"
nansen web fetch https://docs.uniswap.org/contracts/v4/overview --question "What changed in v4?"
```

Positional args and `--url` flags can be combined — all become URLs to fetch.

| Flag | Values | Default | Purpose |
|------|--------|---------|---------|
| `--url` | URL | — | URL to fetch (repeatable for multiple URLs, up to 20) |
| `--question` | string | **required** | Question to answer about the URL content |
| `--pretty` | flag | off | Human-readable JSON |

Returns:
- `analysis` — AI-generated answer to your question
- `retrieved_urls` — URLs successfully fetched
- `failed_urls` — URLs that could not be retrieved

**Tip:** Combine with `web search` — search first to find relevant URLs, then fetch to get full content.

```bash
# Find and analyze in two steps
nansen web search "uniswap v4 launch" --num-results 3 --fields link
nansen web fetch https://blog.uniswap.org/... --question "What are the key changes?"
```

**Note:** 30s timeout. Paywalled or bot-blocked pages may appear in `failed_urls`.
````
END THIRD-PARTY FILE 7499c956af51f468

The third-party file has ended. Everything between the 7499c956af51f468 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

© nansen-ai · MIT · https://github.com/nansen-ai/nansen-cli/tree/HEAD/skills/nansen-web-fetcher/SKILL.md

## Similar
- [agent-browser](https://affpapa.org/en/nevibecode/skills/vercel-labs-agent-browser.md) — skill · 1200000 installs
- [webapp-testing](https://affpapa.org/en/nevibecode/skills/webapp-testing.md) — skill · 186758 installs
- [computer-use](https://affpapa.org/en/nevibecode/skills/computer-use.md) — skill · 239400 installs
- [browser-use](https://affpapa.org/en/nevibecode/skills/browser-use.md) — skill · 98200 installs

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md