Kekik Crawler for Openclaw

A deterministic, browserless web crawler built on Scrapling for efficient data extraction and detailed reporting.

keyiflerolsun

v0.1.0-rc1

Feb 26, 2026

Install

Information

Skill.md

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.


                  npx clawhub@latest install kekik-crawler

2. Manual Installation

Copy the skill folder to one of these locations

Global

~/.openclaw/skills/

Workspace

<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.


                  Help me install kekik-crawler 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 Kekik Crawler?

Kekik Crawler is a professional-grade web scraping tool designed to integrate seamlessly with Openclaw Skills. Built on the Scrapling framework, it operates without the overhead of a headless browser, ensuring high-speed data retrieval and deterministic results. The tool is structured with a clean Single Responsibility Principle (SRP) architecture, making it highly maintainable for developers who need reliable extraction workflows.

This skill is particularly effective for users who require structured data outputs like JSONL and comprehensive summary reports. By focusing on a browserless approach, Kekik Crawler reduces resource consumption while maintaining the ability to execute complex research tasks via predefined presets.

Kekik Crawler Use Cases

Conducting automated person research across multiple web sources.
Executing deep research missions using complex search queries.
Generating structured datasets in JSONL format for machine learning or data analysis.
Producing detailed crawl reports to audit web content and extraction status.

How Kekik Crawler Works

The user provides a list of URLs or search queries via the command-line interface.
The system invokes the crawl runner orchestration layer to manage the extraction lifecycle.
Scrapling-based workers fetch and parse the web content without requiring a heavy browser engine.
Data is processed through selected presets which define the extraction logic and depth.
Results are written to the outputs directory as JSONL files along with a final JSON execution report.

Kekik Crawler Setup

To get started with this skill, install the dependencies and run the main entry point as shown below:

pip install -r requirements.txt
python main.py --urls https://example.org

Kekik Crawler Data Schema & Taxonomy

Kekik Crawler organizes its data within the outputs/ directory. The following table describes the primary file types generated by this skill for Openclaw Skills usage:

Output Type	Format	Description
Raw Data	.jsonl	Line-delimited JSON containing the extracted data objects for each target page.
Summary Report	.json	A high-level overview of the crawl, including success rates and metadata.
Checkpoints	Internal	State management to track progress and handle interruptions.

Kekik Crawler Advanced Features

Specialized research presets such as person-research and deep-research for targeted data gathering.
Deterministic crawling logic that ensures consistent output across different runs.
Orchestration managed by core/crawl_runner.py for reliable task handling.
Native support for JSONL which is ideal for large-scale data processing in Openclaw Skills environments.