TopRank Skills

Home / Claw Skills / Data Analysis / stripfeed
Official OpenClaw rules 36%

stripfeed

Fetch any URL as clean, AI-ready Markdown with token counts and caching. Strip ads, nav, scripts, and noise from web pages.

Stars

0

Installs

0

Status

ACTIVE

Visibility

PUBLIC

安装方式

直接复制以下提示词,发送给你的 AI 助手即可完成安装。

请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 stripfeed 技能。 若已安装,则直接安装 stripfeed 技能。

Overview

Skill Key
atlasopenclaw/stripfeed
Author
atlasopenclaw
Source Repo
openclaw/skills
Version
1.0.0
Source Path
skills/atlasopenclaw/stripfeed
Latest Commit SHA
ee8a85d749fc51775324c88136c4c38baed50d77

Extracted Content

SKILL.md excerpt

# StripFeed

Convert any URL to clean Markdown optimized for LLM consumption. Strips ads, navigation, scripts, and noise. Returns token counts so you know exactly how much context you're using.

## When to use this skill

Use StripFeed whenever you need to read a web page, article, documentation, or any URL content. It produces much cleaner output than raw HTML fetching and tells you the token cost.

## Authentication

All requests require the `STRIPFEED_API_KEY` environment variable. Pass it as a Bearer token:

```
Authorization: Bearer $STRIPFEED_API_KEY
```

Get a free API key at https://www.stripfeed.dev (200 requests/month, no credit card).

## Fetch a single URL

```bash
curl -s "https://www.stripfeed.dev/api/v1/fetch?url=URL_HERE" \
  -H "Authorization: Bearer $STRIPFEED_API_KEY"
```

This returns clean Markdown directly as the response body (Content-Type: text/markdown).

### Parameters

| Parameter    | Required | Description                                                                               |
| ------------ | -------- | ----------------------------------------------------------------------------------------- |
| `url`        | Yes      | The URL to fetch (must be http or https)                                                  |
| `format`     | No       | Output format: `markdown` (default), `json`, `text`, `html`. Pro only except markdown.    |
| `selector`   | No       | CSS selector to extract specific content (e.g. `article`, `.content`, `#main`). Pro only. |
| `cache`      | No       | Set to `false` to bypass cache and force a fresh fetch                                    |
| `ttl`        | No       | Cache TTL in seconds (default: 3600, max: 86400 for Pro)                                  |
| `max_tokens` | No       | Truncate output to fit within this token budget                                           |
| `model`      | No       | AI model ID for cost tracking (e.g. `claude-sonnet-4-6`, `gpt-4o`)                        |

### JSON f...

Related Claw Skills