← Back to Skills Marketplace
85
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install toby-browser
Description
Renders web pages and extracts clean, readable text content using SkillBoss API Hub's headless browsing and scraping capabilities.
Usage Guidance
This skill itself appears to implement a legitimate remote scraping workflow, but the registry metadata is incomplete: index.js and the README require SKILLBOSS_API_KEY while the skill entry declares no required env vars and provides no homepage. Before installing, verify the author and the remote host (api.heybossai.com / SkillBoss): ask the publisher to correctly declare SKILLBOSS_API_KEY and provide documentation and a homepage. Understand that using the skill will send the URLs (and the rendered page data as processed by the remote service) to that third-party API — do not use it with sensitive or private URLs unless you trust the service and its privacy policy. If you prefer not to send data externally, consider a local headless-browser alternative (e.g., Puppeteer) or request clearer metadata from the maintainer.
Capability Analysis
Type: OpenClaw Skill
Name: toby-browser
Version: 1.0.0
The skill is a straightforward implementation of a web scraping tool that interfaces with the SkillBoss API Hub (api.heybossai.com). The code in index.js uses the built-in fetch API to send a URL to the external service and returns the resulting markdown content. There is no evidence of malicious behavior, data exfiltration of local sensitive files, or prompt injection attempts in the documentation.
Capability Tags
Capability Assessment
Purpose & Capability
The skill's stated purpose (headless rendering/scraping via SkillBoss API Hub) matches the code behavior (POST to a /v1/pilot scraper endpoint). However the registry metadata lists no required credentials while the code and README both require SKILLBOSS_API_KEY. The code targets https://api.heybossai.com/v1 which is not named in the registry or SKILL.md; missing/incorrect metadata is incoherent with the stated purpose.
Instruction Scope
SKILL.md describes using a '/v1/pilot' SkillBoss API but doesn't document the need for an API key or the full host. The runtime code will send the requested URL (and indirectly requested page content processed by the remote service) to the third-party API — this is expected for a remote scraper but the documentation/metadata omission means users may not realize data (URLs and derived content) leave their environment.
Install Mechanism
There is no install spec and only a small Node.js script (index.js). No archives or external installers are fetched by the skill itself. Node 18+ (fetch) is required as stated in the README — install mechanism is minimal and consistent.
Credentials
The code requires a single environment variable SKILLBOSS_API_KEY (README and index.js). The registry metadata did not declare any required env vars or primary credential — a mismatch. Requiring an API key for the remote scraping service is proportionate to the skill's function, but the missing declaration and lack of a homepage/owner contact is a transparency/privilege concern. Also note: supplying the key gives the remote service ability to process arbitrary URLs you send.
Persistence & Privilege
always is false, the skill has no install hooks, doesn't request system config paths, and does not modify other skills or agent-wide settings. No persistent elevated privileges are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install toby-browser - After installation, invoke the skill by name or use
/toby-browser - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the toby-browser skill.
- Enables agents to render web pages and extract readable content using SkillBoss API Hub.
- Supports headless web browsing and automation.
- Provides the read command to fetch and return text content from specified URLs.
Metadata
Frequently Asked Questions
What is Browser?
Renders web pages and extracts clean, readable text content using SkillBoss API Hub's headless browsing and scraping capabilities. It is an AI Agent Skill for Claude Code / OpenClaw, with 85 downloads so far.
How do I install Browser?
Run "/install toby-browser" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Browser free?
Yes, Browser is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Browser support?
Browser is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Browser?
It is built and maintained by KirkRaman (@kirkraman); the current version is v1.0.0.
More Skills