loadpage
v1.0.0Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
⭐ 2· 1.6k·1 current·1 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 (remove AI-writing signs and humanize text) align with the actual contents: an instruction-only editor based on Wikipedia guidance. It requires no binaries, env vars, or installs, which is proportionate.
Instruction Scope
SKILL.md provides detailed, scoped editing guidance (identify patterns, rewrite, preserve meaning, add personality). It does not instruct the agent to read system config or exfiltrate data. Note: allowed-tools list includes Read/Write/Edit/Grep/Glob which could be used to operate on files; the instructions themselves only address editing provided text — avoid supplying sensitive file paths unless you intend the agent to read them.
Install Mechanism
No install spec and no code files — instruction-only skill, so nothing is downloaded or written to disk during install.
Credentials
Requires no environment variables, credentials, or config paths. The declared requirements match the skill's purpose.
Persistence & Privilege
always is false and the skill does not request persistent or elevated platform privileges. It does not modify other skills or agent-wide settings.
Assessment
This is an instruction-only writing assistant that edits text to remove AI-like phrasing and add personality; it asks for nothing sensitive (no keys, installs, or external endpoints). Before using: 1) avoid pasting any secrets or private files unless you explicitly want the agent to read them (the allowed-tools list could permit file operations if you direct it); 2) review edits for factual accuracy and any injected opinions or first-person voice (the skill explicitly encourages adding 'soul' and opinions); 3) if you plan to run this automatically on many documents, spot-check outputs to ensure the tone and meaning are preserved.Like a lobster shell, security has layers — review code before you run it.
latestvk9769ya9m757kwd7mqkftz94t1802n3a
License
MIT-0
Free to use, modify, and redistribute. No attribution required.