skills
anthropics
Public repository for Agent Skills
REVIEW SCORECARD
✓ 无Risky检出 · 自动化扫描结果仅供参考,非官方背书
AI DEEP REVIEW
A well-documented, actively maintained skill that solves a common AI-writing pain point with a clear 25-pattern framewor
The README describes a Markdown-only skill with no tests, CI, or code structure visible, so engineering rigor cannot be assessed beyond the install instructions.
No security-relevant details are given beyond an npx install command and a Claude plugin marketplace entry, so a neutral score applies.
The skill targets a widely felt problem, removing detectable AI writing tells, and offers concrete before/after patterns plus voice matching and file-scoped rewriting.
The repository is not archived and was last updated 2026-09-06, indicating recent activity.
The README covers installation across multiple agents, usage examples, voice matching, how it works, and a detailed 25-pattern table with before/after examples.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库INSTALL REFERENCE
npx skills add blader/humanizer --globalThis command comes from an explicit install reference in the README and is provided for reference only — it is never auto-executed by a DSH host.
PROJECT TOPICS
VALIDATION LADDER
FAQ
Agent skill that removes signs of AI-generated writing from text
humanizer has 47,057 stars and 3,838 forks on GitHub, last updated 2026-09-06.
humanizer is distributed under the MIT license.
humanizer is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:agent-skills。