# Skim Clean Reader

> Skim Clean Reader is a paid API for AI agents from skim402.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-15).

Fetches a web page URL and returns agent-ready clean markdown with structured metadata, stripping ads and clutter.

## Facts

- Endpoint: GET https://skim402.com/api/v2/read
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/skim402-com-6feffb86
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UyIEiwrE51A2XKFwVScNW

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability skim402-com-6feffb86
```

Example prompt: Can you fetch this article and give me a clean, readable version with no ads or navigation clutter: https://www.example.com/some-long-article?

## When to prefer this

Use this endpoint when you need to feed web page content into an AI pipeline and want clean, structured markdown free of navigation, ads, and boilerplate. Prefer it over raw HTTP fetching when the destination page is content-heavy and noisy, or when downstream processing requires well-structured markdown rather than raw HTML.

## Known failure modes

- URL is unreachable or returns a non-200 HTTP status
- URL points to a non-HTML resource (PDF, image, video) that cannot be converted
- Paywalled or login-required page returns empty or partial content
- Malformed or missing URL parameter returns a validation error
- Rate limit or payment failure results in 402 response

## How this service works

Skim: clean reader — URL to agent-ready markdown + structured metadata, ~4x smaller than raw HTML.

## Output

Returns clean markdown text of the page's main content along with structured metadata (title, author, date, etc.), ready for an AI agent to process or summarize.

## Example request

```json
{
 "input": {
  "type": "http",
  "method": "GET",
  "queryParams": {
   "url": "https://www.wikipedia.org/wiki/Artificial_intelligence"
  }
 }
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "The URL of the web page to clean and convert to markdown."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/article",
  "mode": "basic",
  "text": "Example Article\n\nClean markdown extracted from the page...",
  "finalUrl": "https://example.com/article",
  "markdown": "# Example Article\n\nClean markdown extracted from the page, with headings, lists, and links preserved.",
  "metadata": {
   "lang": "en",
   "title": "Example Article",
   "siteName": "Example Site",
   "publishedAt": "2025-01-01T00:00:00Z"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/skim402-com-6feffb86/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from skim402.com](https://www.zero.xyz/host/skim402.com/llms.txt)