Humanizer-Text AI写作痕迹去除
v2.1.1Remove signs of AI-generated writing from text. Detects and fixes: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, e...
⭐ 0· 16·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, README and SKILL.md all describe the same capability (detect and rewrite AI-like phrasing). There are no unrelated env vars, binaries, or config paths requested.
Instruction Scope
SKILL.md simply asks the agent to accept input text and return a 'humanized' rewrite; it does not instruct reading files, accessing system config, or posting to external endpoints. Note: any text you send will be processed by the agent/LLM, so do not submit secrets or sensitive PII if privacy is a concern.
Install Mechanism
No install spec and no code files — instruction-only skills have minimal filesystem footprint and nothing is downloaded or executed.
Credentials
The skill requests no environment variables, credentials, or config paths. This is proportionate for a text-rewriting skill.
Persistence & Privilege
always is false and there is no indication the skill modifies other skills or system settings. It does not request persistent privileges.
Assessment
This skill appears coherent and low-risk in structure, but it will process any text you send — avoid submitting secrets, private data, or regulated content. Test on non-sensitive examples first, review rewritten output for accuracy and missing context, and confirm your agent's privacy/retention policy if you need guarantees about data handling.Like a lobster shell, security has layers — review code before you run it.
latestvk9782rthat69bsny0eszkqfzw184pfqq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.