Is humanizer-zh safe to install?

No critical findings, some security notes. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.

How was this score calculated?

Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.

Is this report current?

It was made from commit f4518a8 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.

I wrote this skill. Can I fix the score or have the page removed?

Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.

Scan reports · op7418/Humanizer-zh

humanizer-zh: scan report

编辑中文文章、评论和文档中的空话、重复及模板化表达，让文字更自然，同时保留事实、确定程度和作者声音。适用于润色已有文本，不用于判断作者身份或保证通过 AI 检测器。 An automated scan of this public skill from op7418/Humanizer-zh: security, token cost, spec and clarity, with every finding and its fix.

Result

Verdict

humanizer-zh

77/100 · grade C

op7418/Humanizer-zh at f4518a8

Spec 25 · Efficiency 16 · Clarity 16 · Security 20 (each out of 25)

Always loaded 24 tokens · on trigger 1,957 · on demand 2,350

eff/description-trigger warn · SKILL.mddescription doesn't say *when* to use the skill ("Use when …"). Agents decide from this line alone.
clarity/examples warn · SKILL.mdNo examples or code blocks. One concrete input → output example improves consistency more than extra rules.
sec/undocumented-script warn · SKILL.mdBundles scripts that SKILL.md never explains. Say what each script does and when it runs.
clarity/output warn · SKILL.mdDoesn't say what the result should look like. Add an Output section.
eff/orphan-file info · tests/fixtures/structure.mdtests/fixtures/structure.md is never mentioned in SKILL.md, so the agent won't know to read it.
eff/nested-refs info · tests/fixtures/structure.mdtests/fixtures/structure.md is nested deeply; keep references one level below SKILL.md.

Where it comes from

Source

Fact	Value
Repository	op7418/Humanizer-zh
Skill folder	(repo root)
Stars	20,049
License	MIT
Commit scanned	f4518a8
Scanned	2026-10-19
Files	7

ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.

For maintainers

Badge for the README

If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.

[![ProSkills scan 77/100](https://proskills.dev/badge?score=77)](https://proskills.dev/reports/op7418-humanizer-zh)

FAQ

Questions

Is humanizer-zh safe to install?: No critical findings, some security notes. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
How was this score calculated?: Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
Is this report current?: It was made from commit f4518a8 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.
I wrote this skill. Can I fix the score or have the page removed?: Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.

Keep reading

Free tool

Scan your own skill

Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.

Open the Skill Scanner

Want a skill that already passes? Start with a free one.