academic-humanizer

Featured

Draft, audit, or minimally revise English- or Chinese-language academic prose to reduce formulaic, vacuous, mechanically repetitive, or process-leaking language while preserving claims, evidence strength, logical relations, manuscript-wide terminology identity, document-level pattern variation, and scholarly register. Use for papers, abstracts, grants, cover letters, and reviewer responses when the user asks to de-AI, humanize, audit AI-like phrasing, or rewrite text without changing meaning. English is primary; Chinese is supported. Not for detector evasion, policy circumvention, pure translation, non-academic copy, or adding facts, citations, examples, or author experiences that the source does not contain.

AI & Automation 725 stars 60 forks Updated 2 weeks ago MIT

Install

View on GitHub

Quality Score: 89/100

Stars 20%
95
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Academic Humanizer Improve academic prose by removing observable writing defects, not by imitating imperfection or optimizing an authorship detector. Preserve the author's facts, argument, uncertainty, and disciplinary voice. This skill does not guarantee how any reader or detector will classify a text. ## Portability This skill is agent-agnostic. Its core behavior is defined by `SKILL.md` and `references/`; Python is optional and supports reproducible diagnostics. - Resolve `<skill-dir>` from the directory containing this `SKILL.md`. - Let `<python>` mean an available Python 3 launcher, such as `python3`, `py -3`, or `python`. - Let `<input-file>` mean a user-authorized local text file. Quote paths that contain spaces and use the host shell's path separator. - Do not assume a fixed skill root, home directory, shell, operating system, agent name, or path separator. - `agents/openai.yaml` is optional interface metadata. Core behavior does not depend on a particular agent runtime. - If Python is unavailable, skip the scripts and apply the same contracts directly. ## Load the operating references Read these before drafting or editing: 1. [Semantic contract](references/semantic-contract.md) for claim preservation, locked spans, deletion safety, and the internal claim ledger. 2. [Terminology contract](references/terminology-contract.md) for canonical terms, declared aliases, coined names, intentional distinctions, and the internal terminology ledger. Al...

Details

Author
dongshuyan
Repository
dongshuyan/compass-skills
Created
2 months ago
Last Updated
2 weeks ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

humanizer

Use when the user wants to humanize, de-AI, de-slop, or un-ChatGPT a piece of text — strip AI-isms and add real voice. Scans for 29 documented AI-writing patterns (Wikipedia's "Signs of AI writing") and produces a draft → self-audit → final rewrite. Optional voice-calibration from a user-provided writing sample. Adapted from Hermes Agent / blader/humanizer.

0 Updated 1 months ago
fabioc-aloha
Data & Documents Listed

humanizer

Audit, rewrite, or draft text so it carries zero AI-writing tells and makes only honest, sourced, self-consistent claims. Built from Wikipedia's "Signs of AI writing" (WikiProject AI Cleanup), open-source detector heuristics, and a writing-integrity contract. Use for ALL writing and editing tasks (blogs, LinkedIn, Quora, PR, case studies, emails, landing pages, executive ghostwriting) even when the user doesn't say "humanize". Also trigger when asked to detect AI patterns, de-AI a draft, audit claims, or check whether text would pass as human. Applies to everything except code and raw data.

0 Updated 1 months ago
Aparnabuilds
AI & Automation Listed

humanizer-pro

Use when editing, reviewing, or self-auditing text to remove signs of AI writing and make it read as human: "humanize this," de-slop a draft, "sounds too AI," "check this," "score this," "audit only," "AI check," "do not rewrite," style edit, Elements of Style pass, wiki/article rewrite, Wikipedia-style or encyclopedic article draft, neutral tone, wikitext, citations, source-bound writing, or cleaning up chatbot residue. Covers prose tells (significance and promotional inflation, vague attribution, superficial -ing phrases, AI vocabulary, syntactic tells, verbosity and padding, rhetorical formulas, binary contrasts, rule of three, em-dash overuse, formatting), wiki-specific neutrality/source risks, and mechanical artifact leakage (citeturn0search0, contentReference, oaicite, oai_citation, grok_card, web/attached_file tags, roleplay markers, AI-referrer URL params like utm_source=chatgpt.com or utm_source=claude.ai, zero-width/homoglyph bypass characters) plus unfilled placeholders ([Your Name], 2025-XX-XX, IN

3 Updated yesterday
eddyplolz