stripfeed is a specialized utility that fetches web content and converts it into clean, AI-optimized Markdown while providing precise token counts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install stripfeed
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install stripfeed using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is stripfeed?
stripfeed is a critical tool for developers using Openclaw Skills who need to feed high-quality web data into Large Language Models. It solves the common problem of "noise" in web scraping by automatically stripping out ads, navigation menus, scripts, and headers. By returning only the essential content in a structured Markdown format, it ensures that AI agents can process information more accurately and efficiently.
Beyond simple extraction, this skill provides deep insights into data density, including token counts and savings percentages. This allows developers to manage context windows effectively and monitor the costs associated with AI processing. Whether you are building a research agent or a documentation reader, stripfeed provides the clean text foundation required for modern AI workflows.
stripfeed Use Cases
- Extracting clean documentation for AI-driven coding assistance.
- Reducing token overhead by removing boilerplate HTML from web articles.
- Automating research tasks that require fetching content from multiple URLs.
- Monitoring and limiting token usage for LLM prompts to control costs.
- Integrating high-quality web-to-text conversion into automated data pipelines.
How stripfeed Works
- The skill receives a target URL and authenticates via the STRIPFEED_API_KEY environment variable.
- A request is dispatched to the stripfeed API with optional parameters like format, selectors, or token limits.
- The service fetches the webpage, removes non-essential HTML elements, and converts the remainder to Markdown.
- Token usage is calculated for both the raw and the stripped versions to measure efficiency.
- The refined content and associated metadata are returned to the user or agent for immediate consumption.
stripfeed Setup
To start using this skill within the Openclaw Skills framework, you must first configure your authentication.
- Obtain an API key from stripfeed.dev.
- Set the environment variable in your terminal or configuration file:
export STRIPFEED_API_KEY="your_api_key_here"
- Verify the installation by fetching a URL:
curl -s "https://www.stripfeed.dev/api/v1/fetch?url=https://example.com" \
-H "Authorization: Bearer $STRIPFEED_API_KEY"
stripfeed Data Schema & Taxonomy
The skill provides structured responses, particularly when using the format=json parameter. The data is organized as follows:
| Property | Description |
|---|---|
markdown |
The primary content extracted and converted to Markdown format. |
tokens |
The number of tokens in the cleaned Markdown version. |
originalTokens |
The number of tokens in the original, unstripped HTML. |
savingsPercent |
The percentage of data reduced by the stripping process. |
cached |
A boolean indicating if the response was retrieved from the cache. |
fetchMs |
The time taken in milliseconds to fetch the external resource. |
stripfeed Advanced Features
- CSS Selector Support: Target specific page elements like
articleor.main-contentto further refine data extraction. - Batch Processing: Pro users can fetch up to 10 URLs in a single request for high-throughput applications.
- Token Budgeting: Use the
max_tokensparameter to truncate output automatically to fit specific LLM context windows. - Custom Cache Control: Adjust TTL or bypass the cache entirely to ensure real-time data accuracy.
- Model-Specific Tracking: Specify an AI model ID to get cost tracking aligned with specific LLM providers.
SKILL.md
Loading
Related Openclaw Skills
Insecure Defaults Detection
Identify and remediate fail-open vulnerabilities, hardcoded secrets, and permissive security settings before they reach production.
Kaspa News
A comprehensive intelligence aggregator for Openclaw Skills providing real-time updates on Kaspa development, community activity, and ecosystem milestones.
IQAir Air Quality Checker
A powerful real-time air quality monitoring skill that retrieves AQI data and pollution levels for any global location via the IQAir API.
Claude Code CLI
A powerful integration that delegates complex coding, refactoring, and codebase exploration tasks to the Claude Code CLI.
OpenClaw Security Action
A specialized GitHub Action that automatically scans agent workspaces and Openclaw Skills for security vulnerabilities like exposed secrets and prompt injection.
Context Optimizer
An intelligent context compression engine that reduces token costs by up to 60% through pruning, deduplication, and summarization.
Featured*
