academic-humanizer
FeaturedDraft, 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.
Install
Quality Score: 89/100
Skill Content
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
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.
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.
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