humanizer_academic
Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written. Based on Wikipedia's "Signs of AI writing" guide, adapted for medical literature. Detects and fixes patterns including: inflated significance claims, superficial -ing analyses, vague attributions, AI vocabulary words, copula avoidance, excessive hedging, generic conclusions, informal word choices (linked/beyond/via/where/yield), overly assertive causal claims, and artificially condensed expressions. Preserves legitimate acade
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill 44-matsuikentaro1-humanizer_academic --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill edits academic medical writing to remove signs of AI-generated text. It identifies AI-writing patterns such as excessive hedging, vague attributions, -ing phrases, overly assertive claims, and puffery, and rewrites sections to use precise, concrete academic language. It preserves legitimate academic phrases and citations, maintains formal tone, and preserves data and data provenance during rewriting.
How it works
The skill scans the input for AI-pattern indicators listed in its CONTENT PATTERNS and LANGUAGE PATTERNS (e.g., -ing endings, vague attributions, overclaims, and AI vocabulary). It then rewrites problematic sections to:
- replace AI-like phrasing with precise academic language and data-backed claims,
- remove promotional or sensational wording,
- keep original meaning and data intact,
- maintain the formal, objective style of medical journals,
- ensure that attribution phrases remain when followed by citations or concrete data. It also enforces style guidelines such as replacing em dashes with appropriate punctuation, using sentence-level copulas plainly, and applying standard academic transitions when preserving legitimate phrases.
When to use it
Use when editing or reviewing manuscripts where AI-writing patterns are detected or likely to appear, to make prose sound more natural and professionally written while preserving scientific content and citations.
What it can touch
It operates on textual content within the manuscript and adjusts phrasing. It recognizes and aims to preserve legitimate academic transitions and attribution phrases that are supported by citations or data. It does not alter specific data values, results, or cited findings beyond presenting them in a clearer, more conventional form.
Caveats
It requires careful review to ensure data integrity and citation accuracy are intact after edits. It avoids stating outcomes not present in the original text and does not introduce new data or claims. License and tool constraints are defined by the skill metadata (NOASSERTION license; allowed-tools include Read, Write, Edit, Grep, Glob, AskUserQuestion).
# Humanizer Academic: Remove AI Writing Patterns from Medical Papers You are a medical writing editor that identifies and removes signs of AI-generated text to make academic manuscripts sound more natural and professionally written. This guide is based on Wikipedia's "Signs of AI writing" page, adapted for medical and scientific literature. ## Your Task When given text to humanize: 1. **Identify A
What does the humanizer_academic skill do?
Remove signs of AI-generated writing from academic medical papers. Use when editing or reviewing manuscripts to make them sound more natural and professionally written. Based on Wikipedia's "Signs of AI writing" guide, adapted for medical literature. Detects and fixes patterns including: inflated significance claims, superficial -ing analyses, vague attributions, AI vocabulary words, copula avoidance, excessive hedging, generic conclusions, informal word choices (linked/beyond/via/where/yield), overly assertive causal claims, and artificially condensed expressions. Preserves legitimate acade
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill 44-matsuikentaro1-humanizer_academic --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.