extract-page-copy-3e84d8 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited extract-page-copy-3e84d8 (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.
Strip all markup, scripts, and styles from an HTML file and output only the text a visitor would read — grouped by semantic role. This reduces token usage by up to 98% compared to passing raw HTML.
Read the HTML source (from a file or URL), then apply these rules in order:
Strip completely — do not include any text from:
<script>, <style>, <svg>, <template>, <noscript> elements and all their contents<!-- ... -->)display:none or visibility:hidden stylesExtract and group by role:
<meta name="description" content="..."> value<h1> through <h6> text, always include regardless of length<p>, <li>, <td>, <th>, <blockquote> text (≥25 characters)<button> text and <a> link text (keep even when short)<nav>, <header>, <footer> (shorter minimum, ≥10 characters)alt attribute values on <img> tags (it's copy)Deduplication: Skip any string already seen (case-insensitive exact match).
META DESCRIPTION
----------------
[meta description text]
HEADINGS
--------
[h1] ...
[h2] ...
BODY COPY
---------
...
CTAS
----
...
NAV / HEADER / FOOTER
---------------------
...
IMAGE ALT TEXT
--------------
...Output all extracted text in top-to-bottom document order, prefixed with its type:
[h1] ...
[p] ...
[cta] ...
[h2] ...<div class="nav">) are not grouped as nav — only semantic <nav>, <header>, <footer>For JavaScript-rendered pages, get the live DOM: open browser DevTools → Elements → right-click <html> → Copy → Copy outerHTML → save to a file, then extract from that.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.