scrapling-skill
PassAudited by ClawScan on May 1, 2026.
Overview
This is a coherent web-scraping instruction skill, but users should be aware it recommends anti-bot scraping tools and third-party package/browser setup commands.
Before installing or using this skill, confirm you are allowed to scrape the target site, use throttling and delays for crawls, and review or pin the Scrapling dependency before running the recommended setup commands.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may help scrape sites that use anti-bot protections, which can create legal, terms-of-service, or operational risk if used on unauthorized targets.
The skill explicitly guides the agent toward anti-bot-resistant scraping workflows. This is aligned with the stated scraping purpose, but it is a capability users should apply only to authorized, lawful targets.
Use this skill whenever the user asks to scrape a website, extract structured data from web pages, handle anti-bot/Cloudflare pages... / `StealthyFetcher`: Best default when anti-bot checks likely exist.
Use this skill only for sites you are permitted to scrape, avoid login bypass or private data collection, and keep request rates reasonable.
Running the setup may download and execute third-party code or browser components on the local machine.
The recommended setup installs an unpinned third-party package and runs a package-provided installer for browser-based fetchers. This is central to the skill's purpose but introduces normal dependency provenance risk.
D:\clawtest\.venv\Scripts\python -m pip install "scrapling[fetchers]" D:\clawtest\.venv\Scripts\scrapling install
Run setup in the suggested isolated virtual environment, consider pinning package versions, and review the Scrapling package source/provenance before installation in sensitive environments.
Stored selector fingerprints could affect later extraction results if the target page changes or if prior saved state is stale.
The template uses Scrapling's adaptive selector feature, which stores page-layout fingerprints and reuses them later. This is useful and purpose-aligned, but it is persistent extraction context that can influence future runs.
# First run stores fingerprints:
products = page.css(".product-card", auto_save=True)
# Future run can recover after layout drift:
products = page.css(".product-card", adaptive=True)Use adaptive saving only when helpful, keep it scoped to the intended project, and clear or regenerate saved selector state when changing targets.