Topic · Writing & Content

Best Humanizing AI text skills for Claude Code, Codex and other agents.

Skills that strip robotic, AI-sounding phrasing from drafts so text reads naturally.
skills
314
official
5

Humanizing AI text skills, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

Humanizing AI text skills, ranked
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1
1.HumanizerOfficial

Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

Azure-Samples/interview-coach-agent-framework17237 repos~5.8kAutomated safety check: PassMIT6 days ago
2

Audit and rewrite content to remove AI writing patterns ("AI-isms").

conorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMITtoday
3

Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

guillaumemeyer/watermarks-remover23k—~3.5kAutomated safety check: PassMITyesterday
4

Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

trycompai/crm11k1 repo~881Automated safety check: PassMIT26 days ago
5

Remove AI writing patterns from prose. An agent skill from Xe/site.

Xe/site7318 repos~423Automated safety check: PassMIT2 days ago
6

Strips AI provenance marks from text and files: invisible Unicode, statistical text watermarks via rewriting, and C2PA, EXIF or XMP metadata across common formats.

guillaumemeyer/watermarks-remover23k—~4.9kAutomated safety check: PassMITyesterday
7

Communicate clearly in every response, progress update and agent-authored document.

databasus/databasus8.8k—~3.9kAutomated safety check: PassMIT14 days ago
8

Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.

op7418/Humanizer-zh19k—~2kAutomated safety check: PassMIT14 days ago
9

Improve the clarity and voice of AI-assisted academic writing (papers, theses, rebuttals) and funding proposals (NSF Project Summary/Description, NIH Specific Aims): preserve scholarly conventions…

AIScientists-Dev/academic-humanizer1.8k1 repo~4.2kAutomated safety check: PassMIT3 mo ago
10

「說人話」:繁體中文的去 AI 味改寫 skill。審查與改寫文字,去除 AI 味道、校正中國用語與半形標點,讓文字讀起來像真人寫的。

Raymondhou0917/speak-human-tw1k1 repo~2.2kAutomated safety check: PassMITtoday
11

Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.

coji/natural-japanese1.9k—~2.1kAutomated safety check: PassMIT1 mo ago
12

Makes AI-generated content sound genuinely human — not just cleaned up, but alive.

olivomarco/github-copilot-token-optimization1672 repos~3.5kAutomated safety check: PassNo licence2 mo ago
13

Anti-slop frontend skill for landing pages, portfolios, and redesigns.

caorushizi/oss-client11322 repos~22kAutomated safety check: PassNo licence29 days ago
14

Audits and rewrites formulaic, AI-sounding prose while keeping facts, voice and format, using a local Python scorer and inspect-only, rewrite or embedded-gate modes.

iflytek/skillhub5.2k—~1.5kAutomated safety check: PassMIT6 days ago
15

Make AI-generated writing read as human-written, in fiction and in professional prose.

Nanako0129/sepia3k—~3.6kAutomated safety check: PassMITyesterday
16

Diagnoses and rewrites Korean text that reads as AI-generated, fixing translationese and mechanical parallelism across 85 patterns in 10 categories, with light to heavy passes.

epoko77-ai/im-not-ai5.9k—~1.2kAutomated safety check: PassMIT11 days ago
17

Review or de-slop concrete changes in ccch1mneyyy/dsh-TUI at maintainer level: PR numbers or URLs, branches, commit ranges, patch files, staged or unstaged worktrees, and scoped repository-hygiene…

ccch1mneyyy/dsh-TUI4.1k—~1.3kAutomated safety check: PassMITtoday
18

A skill your agent uses when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local detector result when…

conorbronsdon/avoid-ai-writing4.9k—~1.3kAutomated safety check: PassMITtoday
19

Removes AI writing tells from prose through an audit-first flow, routing to a two-pass rewrite, a report-only cleanup, voice teaching or mimicry depending on the sub-command used.

theclaymethod/unslop509—~1.7kAutomated safety check: PassMIT29 days ago
20

Reduces the AI-text detection rate of academic papers by scanning for templated phrasing and making small deterministic edits that keep citations, data and terminology.

xiaofenggan01/aigc-reduce612—~1.5kAutomated safety check: PassMIT3 mo ago
21

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写. An agent skill from OUBIGFA/De-AI-Prompt-Enhancer-Writer-Booster-SKILL.

OUBIGFA/De-AI-Prompt-Enhancer-Writer-Booster-SKILL8518 repos~5.9kAutomated safety check: PassNo licence20 days ago
22

Write copy that converts and doesn't sound like a robot. An agent skill from mikiarlo3/ai-copywriter.

mikiarlo3/ai-copywriter1.2k—~12kAutomated safety check: PassMIT2 mo ago
23

Edit drafts into natural prose, inspect AI-sounding patterns, or review how a specified audience might respond passage by passage.

manavmishra/ZeroSlop1321 repo~16kAutomated safety check: PassMITyesterday
24

Simplify and refine recently modified code while preserving functionality.

millionco/react-doctor15k—~1.2kAutomated safety check: PassUnknowntoday
25

Design and build complete web experiences from scratch — award-level product and marketing pages, cinematic scroll-directed sites where the page is directed like a film, and multi-screen products…

agiwhitelist/auteur1k—~5kAutomated safety check: PassMIT2 mo ago
26

Remove signs of AI-generated writing from prose, and keep it out of a repo.

aashaexo/soundshuman2981 repo~6.9kAutomated safety check: PassMIT2 mo ago
27

A skill your agent uses when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code, frontmatter, quotes…

conorbronsdon/avoid-ai-writing4.9k—~1.7kAutomated safety check: PassMITtoday
28

按用户要求审稿或去 AI 味,支持中英文;保留事实、术语与责任主体,支持只标问题. An agent skill from MrGeDiao/shuorenhua.

MrGeDiao/shuorenhua2k—~757Automated safety check: PassMITyesterday
29

Rewrites Korean text written by AI so it reads like a human wrote it, detecting translationese and other AI patterns while leaving the content untouched.

epoko77-ai/im-not-ai5.9k—~4.5kAutomated safety check: PassMIT11 days ago
30

Review writing for its intended reader, check common AI writing patterns, revise, request a second pass from a different model family, and check again.

ItsssssJack/SlopMonster622—~1.5kAutomated safety check: PassMIT11 days ago
31

Remove AI-writing patterns ("AI-isms") from text using the avoid-ai-writing catalog (conorbronsdon/avoid-ai-writing).

pchalasani/claude-code-tools2k—~1.4kAutomated safety check: PassMIT2 days ago
32

Deslop, simplify, or review low-value tests and prose only when explicitly requested for a branch or diff.

marin-community/marin3.9k—~1.1kAutomated safety check: PassApache-2.0today
33

人味儿写作 - 打磨、润色、改写别人的文字时,保住文字背后那个人的存在感. An agent skill from orange2ai/renwei-writing.

orange2ai/renwei-writing1.1k—~684Automated safety check: PassProprietary3 mo ago
34

Audit and rewrite Chinese or English content to remove AI tone, then pull it toward a target human voice.

lynote-ai/humanize-text-skill241—~1.9kAutomated safety check: PassMIT3 mo ago
35

Remove AI tells from LinkedIn posts/comments: 2026 vocabulary density, reveal bridges, staccato fragments, stacked triads, performed sincerity.

sergebulaev/linkedin-skills4.3k1 repo~5kAutomated safety check: PassMITtoday
36

Rewrites AI-sounding Chinese web novel text so it reads naturally, changing as little as possible and keeping plot, names and numbers intact.

zenstory-ai/oh-story-claudecode7.3k1 repo~2.6kAutomated safety check: PassMIT4 days ago
37

Rewrite and humanize Simplified Chinese while preserving facts, meaning, evidence strength, register, and authorial voice.

LifelongLazyLearner/qu-ai-wei626—~1.2kAutomated safety check: PassMIT27 days ago
38

降低中文学术写作(论文、期刊文章、毕业论文等)AIGC检测率的专项 skill. An agent skill from redbaronyyyyy-eng/humanizer-zh-academic.

redbaronyyyyy-eng/humanizer-zh-academic3041 repo~1.8kAutomated safety check: PassMIT7 mo ago
39

Edits Russian text to remove signs of AI generation, bureaucratic phrasing and filler while keeping facts, with a lint script and a detect-only mode.

smixs/humanizer-ru186—~3.9kAutomated safety check: PassMIT14 days ago
40

Rewrites code review comments so they read like a human teammate wrote them.

MohamedAbdallah-14/unslop1533 repos~980Automated safety check: PassMIT2 days ago
41

A skill your agent uses when the user wants to humanize text, trim slop, de-AI or de-slop writing, remove AI tells, fix robotic or ChatGPT-sounding prose, or make writing sound human and natural.

seyedehsanhadi/sloptrim212—~5.2kAutomated safety check: NotesApache-2.02 days ago
42

Strips the cues that make prose read as AI-generated and forces a deliberate human voice instead of the model's default register.

JCarterJohnson/vibecoded-design-tells508—~3.5kAutomated safety check: PassUnknown3 mo ago
43

A skill your agent uses when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation, verification, or when the user invokes Avoid AI Writing…

conorbronsdon/avoid-ai-writing4.9k—~1.8kAutomated safety check: PassMITtoday
44

Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest…

NulightJens/humanizer-stack326—~2.2kAutomated safety check: PassUnknown2 mo ago
45

Humanize AI-generated text by detecting and removing patterns typical of LLM output.

brandonwise/humanizer127—~2.2kAutomated safety check: PassMIT1 mo ago
46

Remove AI writing patterns from prose so it reads like a person wrote it.

every-app/open-seo23k—~602Automated safety check: PassMITtoday
47

Качество русского текста для агента. An agent skill from ilyautov/humanizer-ru.

ilyautov/humanizer-ru416—~4kAutomated safety check: PassMIT4 days ago
48

Rewrites already-written Korean text to remove AI-sounding rhythm and translationese while keeping its meaning, register, facts and protected terms untouched.

beefiker/superloopy1111 repo~1.7kAutomated safety check: PassMITtoday

Questions, answered from the data.

What is the best Humanizing AI text skill?

Humanizer (official) from Azure-Samples/interview-coach-agent-framework ranks first of the 314 Humanizing AI text skills listed here, with the highest score: its repository has 172 GitHub stars, 37 other GitHub owners carry a copy, its SKILL.md loads about 5.8k tokens and it passes the automated safety check with no findings. Next come Avoid AI Writing and User-Facing Text Cleanup.

Which Humanizing AI text skills are official?

5 of the 314 Humanizing AI text skills are official, published by the vendor's own GitHub organization: Humanizer, Deslop, AI Tells, Finnish Humanizer and Humanizer.

How are these skills ranked?

By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.