content-cleaner — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited content-cleaner (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill transforms noisy web content (like raw HTML dumps, messy copy-pastes with JSON/navigation, or URLs) into clean, readable Markdown articles.
read_url_content tool or the agent-browser skill to fetch the raw page content.When processing the content, ALWAYS apply the following rules:
ALWAYS format the final output as a clean Markdown file. Use this exact template:
# [Article Title]
**Author**: [Author Name or 'Unknown']
**Date**: [Publication Date or 'Unknown']
---
[Cleaned Article Body]Unless the user specifies otherwise, save the output to a clearly named Markdown file in a dated directory, for example: ./reports/Articles_YYYY_MM_DD/[source_name_snake_case].md. Do not summarize the entire article in the chat window; just provide the path to the saved file and a 1-sentence confirmation.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.