scrapling-skill

An agent skill by daymade, from daymade/claude-code-skills. Tags: cli, markdown, scraping, troubleshooting, web.

What it does

Install, troubleshoot, and use Scrapling CLI to extract HTML, Markdown, or text from webpages. Use this skill whenever the user mentions Scrapling, `uv tool install scrapling`, `scrapling extract`, WeChat/mp.weixin articles, browser-backed page fetching, or needs help deciding between static and dynamic extraction.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill scrapling-skill

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/scrapling-skill ~/.claude/skills/scrapling-skill

Safety box score

Grade B, low risk: 21 of 100 risk points, rated 2026-10-17. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a thin wrapper around the Scrapling CLI: it diagnoses the local install, optionally installs Playwright/Chromium, and fetches page content from user-supplied URLs. The main risks are outbound network access to arbitrary sites, browser-runtime downloads into the user’s home cache, and an explicit `--no-verify` path that weakens TLS checks.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It runs external programs via `subprocess.run(...)` in `scripts/diagnose_scrapling.py` and invokes `scrapling ...` commands during diagnosis and smoke tests.
Network access	2 (moderate)	The skill fetches arbitrary URLs with `scrapling extract get/fetch/stealthy-fetch` and can download browser runtimes with `scrapling install`, so it sends data off-machine and retrieves remote content.
Filesystem reach	2 (moderate)	It writes extraction output files and checks browser caches under the user’s home directory, including `~/Library/Caches/ms-playwright/` and `~/.cache/ms-playwright/`.
Secrets & credentials	0 (none)	No credential stores, tokens, key files, browser sessions, or `.env` paths are referenced.
Privilege & persistence	0 (none)	There is no sudo use, service registration, shell startup editing, or other privileged system change; installs are user-level `uv tool`/`scrapling install` operations.
Instruction hijack surface	0 (none)	The files do not instruct the agent to ignore higher-level rules, hide actions, or follow remote instructions; `--no-verify` is a transport-security flag, not prompt injection.
Irreversible actions	0 (none)	The skill does not publish, post, deploy, pay, book, or delete anything on the user’s behalf.
Transparency	0 (none)	All shipped content is plain-text Markdown and Python; there are no binaries, minified blobs, or opaque remote installers in the skill itself.

Before installing

Read `scripts/diagnose_scrapling.py`; it shells out to `scrapling` and writes a temp output file.
Confirm you’re okay with browser caches under `~/.cache/ms-playwright` / `~/Library/Caches/ms-playwright`.
Decide in advance whether you want `--no-verify`; it disables TLS certificate checks for static fetches.

Rated 2026-10-17 by an automated review of 3 files from the skill's repository.

Source

Repository: daymade/claude-code-skills (all skills from this repository)
Path: scrapling-skill/SKILL.md
Branch: main
Updated: 2026-09-20

agents-debug — Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes.
aws-networking — Routes AWS networking requests to the correct service skill for implementation.
burpsuite-project-parser — Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns.
chrome-mcp-troubleshooting — Diagnose and fix Claude in Chrome MCP extension connectivity issues.
gh-cli — Enforces authenticated gh CLI workflows over unauthenticated curl, WebFetch, and MCP fetch patterns.
seo-firecrawl — Full-site crawling, scraping, and site mapping via Firecrawl MCP.