Menu

Individual skill

verify-watermark-removal

0upvotes

Verify that a watermark-removal or "humanizer" step actually removed a statistical text watermark, by measuring a sample whose key the user holds. Use after any tool, script or service claims to have cleaned a text, or when the user asks whether such a tool works, which one to trust, or how to test one. Reports a detector score against fixed thresholds plus what the run cost in meaning, facts, verbatim overlap and length. This skill only measures and never removes a mark.

plugins/all-skills/skills/verify-watermark-removal/SKILL.md

Read pinned source

Source commit 82ce2112b080810c6b72939201d6a53876116e12

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
3,735
Repository last updated
Nov 9, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Verify Watermark Removal

A tool says it removed a watermark from a text. This skill checks whether it did,
by measuring rather than by trusting the tool's own report.

The check works because the mark is planted first, with a key the user holds. A
detector that knows the key is the strongest detector that can exist for that
text, so its score is a ceiling rather than a guess. What the key buys is a scale
of the user's own; what keeps a tool from recognising the sample is something
else, namely that a freshly generated private sample is a text nobody has seen
before. The samples shipped with the tool are published together with their key,
so those can be recognised, and the repository says so in `samples/README.md`.
The skill also reports what the rewrite cost the text, because a mark that
disappeared together with half the meaning is not a result anyone wants.
Back to top