← Back to Skills Marketplace
scrape
by
TobeyRebecca
· GitHub ↗
· v1.0.0
· MIT-0
65
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install toby-scrape
Description
Legal web scraping with robots.txt compliance, rate limiting, and GDPR/CCPA-aware data handling. Supports both direct HTTP scraping and managed scraping via...
Usage Guidance
This skill appears to implement a legitimate scraper and a managed scraping option via api.skillbossai.com, but there are a few things to check before installing:
- Metadata mismatch: the registry says no env vars are required but SKILL.md and code read SKILLBOSS_API_KEY. Do not provide any API key until the publisher corrects the metadata or you verify the key's intended use.
- Third-party endpoint: the skill will send requests and scraped content to https://api.skillbossai.com when you use the managed path. Verify who operates SkillBoss, what data they retain, and the key's scope and revocation process.
- Data exposure: if you use the SkillBoss path, scraped page content (including any inadvertently collected PII) will be transmitted to that external service. Only run against data you are authorized to process, and test with non-sensitive pages first.
- Least privilege: if you must provide SKILLBOSS_API_KEY, create a key with minimal privileges and the ability to revoke it quickly.
- Source provenance: the skill's homepage and source are unknown. Prefer skills with verifiable source repositories or vendor pages. Ask the publisher for a homepage/source and an explanation for the metadata mismatch.
If you cannot verify the publisher or the SkillBoss service, run the direct-http code locally in an isolated environment (no real credentials) and avoid using the managed SkillBoss path until you've confirmed safety.
Capability Analysis
Type: OpenClaw Skill
Name: toby-scrape
Version: 1.0.0
The 'toby-scrape' skill provides a well-documented framework for ethical web scraping, emphasizing compliance with robots.txt, rate limiting, and data privacy (GDPR/CCPA). The code in code.md implements standard best practices for polite fetching and integrates with a managed scraping service (api.skillbossai.com) using an API key. No malicious behaviors, obfuscation, or data exfiltration attempts were identified.
Capability Tags
Capability Assessment
Purpose & Capability
The SKILL.md and code clearly implement a scraper and an optional integration with a 'SkillBoss API Hub' (api.skillbossai.com) which requires SKILLBOSS_API_KEY — that fits the described purpose. However the registry metadata says 'Required env vars: none' while SKILL.md and code require SKILLBOSS_API_KEY, an inconsistency that should be resolved before trusting the skill.
Instruction Scope
The runtime instructions focus on robots.txt, ToS checks, rate limiting, PII handling, and using either direct HTTP or the SkillBoss API Hub. The code examples only reference scraping-related files, HTTP requests, and the declared SKILLBOSS_API_KEY; there is no unrelated file/system access or vague 'gather context' language.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to be executed by the platform. That minimizes install-time risk.
Credentials
Functionality legitimately needs a single API credential (SKILLBOSS_API_KEY) for the managed scraping path — that's proportionate. The concern is the metadata mismatch: the registry lists no required env vars while the SKILL.md and code access SKILLBOSS_API_KEY. Also the SkillBoss API is a third-party endpoint; users should confirm the trust model and key scope before providing credentials.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system-wide privileges. It is user-invocable and allows autonomous invocation (platform default), which is expected for skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install toby-scrape - After installation, invoke the skill by name or use
/toby-scrape - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Scrape skill v1.0.0 — initial release with robust legal compliance and managed scraping features:
- Enforces robots.txt compliance, terms of service checks, and rate limiting for ethical web scraping.
- Includes guidelines for GDPR/CCPA-aware data handling and strict personal data protection.
- Supports both direct HTTP-based scraping and managed scraping via SkillBoss API Hub.
- Provides a comprehensive pre-scrape checklist and legal boundaries for safe operation.
- Requires SKILLBOSS_API_KEY for SkillBoss-managed scraping with automatic anti-bot protection.
Metadata
Frequently Asked Questions
What is scrape?
Legal web scraping with robots.txt compliance, rate limiting, and GDPR/CCPA-aware data handling. Supports both direct HTTP scraping and managed scraping via... It is an AI Agent Skill for Claude Code / OpenClaw, with 65 downloads so far.
How do I install scrape?
Run "/install toby-scrape" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is scrape free?
Yes, scrape is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does scrape support?
scrape is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created scrape?
It is built and maintained by TobeyRebecca (@tobeyrebecca); the current version is v1.0.0.
More Skills