Remove 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.
Security Analysis
high confidenceThe skill is an instruction-only text-editing tool whose declared requirements and instructions match its stated purpose; it requests no credentials, installs, or unusual system access—though a couple of minor inconsistencies and a broad allowed-tools list are worth noting.
The name, description, README, and SKILL.md all describe the same task (detect and rewrite AI-imal writing patterns). The skill is instruction-only and does not request binaries, environment variables, or installs, which is appropriate for a text-editing utility. Minor inconsistency: registry metadata shows version 1.0.0 while the SKILL.md header lists version 2.1.1 (version mismatch between metadata and the embedded manifest).
SKILL.md contains detailed, task-focused runtime instructions (identify patterns, rewrite while preserving meaning, add voice). The manifest lists allowed-tools including Read, Write, Edit, Grep, and Glob — these enable file-system operations. The instructions themselves do not direct reading arbitrary system files or environment variables, but the allowed-tools broaden what an agent could do if invoked with file access. Recommend requiring explicit user confirmation before the agent opens or modifies files or runs on system documents.
No install spec and no code files (instruction-only). This is the lowest-risk model: nothing is downloaded or written to disk by default.
No environment variables, credentials, or config paths are requested. Nothing asks for unrelated service keys or secrets; requested capabilities are proportional to a text-editing skill.
always is false and the skill does not request persistent system configuration or elevated privileges. Autonomous invocation is allowed (default) but that is expected for skills; there is no indication the skill self-enables or writes to other skills' configs.
Guidance
This skill appears internally consistent and low-risk: it only provides instructions for editing text and asks for no credentials or installs. Before installing, note the small metadata mismatch (version numbers differ) and that the skill's allowed-tools include file read/write/grep/glob — which could let an agent open or edit documents. If you plan to use it on sensitive files, require the agent to ask you before accessing or modifying files and try it first on non-sensitive sample text. Also prefer skills with a known source/homepage; consider verifying the humanizer's origin or testing outputs to ensure it preserves meaning and tone appropriately.
Latest Release
v1.0.0
Initial release - Remove AI writing patterns based on Wikipedia's Signs of AI Writing guide. Detects 24 patterns including inflated symbolism, AI vocabulary, em dash overuse, and more.
More by @biostartechnology
Published by @biostartechnology on ClawHub
