humanize
Skill5 starsChanged 4 months agoApache-2.0View on GitHub
Score and rewrite social captions and marketing copy so they don't read as AI-generated. A pre-review quality pass: run it on every caption batch before showing drafts to the user. Use when the user says "this sounds like AI", "make it sound human", "de-slop this", "humanize", "rewrite this caption", or asks why their posts feel generic. Every creation skill (plan-social-content, create-post-*) runs this pass automatically before its approval gate. The user's own caption rules (in the workspace's strategy doc) always outrank this skill.
74 other projects use a version of this.
Adopted by
Most recently taken up by
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 8, 2026
- jmusick/skillstheir own version, first seen Nov 8, 2026
- Nossie/humanizetheir own version, first seen Nov 8, 2026
- droxey/skillstheir own version, first seen Nov 8, 2026
- lalulali/vespyrtheir own version, first seen Nov 6, 2026
- angusfretwell/skillstheir own version, first seen Nov 4, 2026
Used with
Projects with it also use humanize-redo, humanize-korean and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dawn840705Skillhumanize-redo
가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능. humanize-korean 의 윤문 콜을 기존 run_id 에 재실행해 잔존 finding 을 처리한다. 트리거 — "$humanize-redo". **명시적 슬래시 호출 전용** — 자연어 후속 요청은 `humanize-korean` 오케스트레이터가 받는다.
Also in 5 projects that use this
mskim8717Skillhumanize-korean
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 40+ AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI 탐지·윤문", "AI 글 사람처럼", "번역투 제거", "영어 인용 많은 글 윤문", "AI 글 티 안 나게", "휴머나이저", "humanize Korean", "AI detector bypass 한글". 후속 작업 — "특정 카테고리만 다시", "윤문 강도 조정", "장르 바꿔서", "이 문단만", "2차 윤문" 도 모두 이 스킬. 단순 맞춤법·오탈자 교정은 직접 처리, 번역은 번역 스킬, 내용 추가·삭제를 동반한 재작성은 별도 집필 스킬.
Also in 3 projects that use this
CoralGameSkillperf-profile
Structured performance profiling workflow. Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings.
Also in 3 projects that use this
Rayan55050Skillcontent
Создание контента: посты, статьи, тексты
Also in 3 projects that use this
luischanciSkillproofread
Run the proofreading protocol on manuscript files. Checks grammar, typos, overflow, consistency, and academic writing quality. Produces a report without editing files.
Also in 3 projects that use this
insight68Skillpricing
Help figure out pricing for a product or service using minimalist entrepreneur principles. Use when someone is setting prices, considering price changes, or struggling with what to charge.
Also in 3 projects that use this
Other versions74 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 74
- epoko77-ai/im-not-ai★ 6ksame name
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- PolyArch/humanize★ 1.5ksame name
- cwinvestments/memstack★ 425same name
- Mathews-Tom/armory★ 340same name
- whawkinsiv/solo-founder-skills★ 260same name
- whawkinsiv/claude-code-skills★ 258same name
- c-kick/hnl-agent-skills★ 56same name
- tzengyuxio/skills★ 45same name
- amondnet/yoonmoon★ 17same name
64 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- build-brand-kitSkill
- create-post-carouselSkill
- create-post-clipsSkill
- create-post-countdownSkill
- create-post-from-imageSkill
- create-post-graphicSkill
- create-post-variationsSkill
- create-post-videoSkill
- get-startedSkill
- manage-librarySkill
- marky-apiSkill
- plan-social-contentSkill
- review-performanceSkill
- schedule-postsSkill
- suggest-topicsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 64 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
If a brand rule says "always use emojis", emojis stay.
- Distinctive: line 37
Start at 100, deduct per hit (same pattern stacks up to 2x its penalty).
“Common” is measured: kept by at least 6 in 10 of the 64 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Humanize
Score a draft against the AI-writing patterns below, fix what it flags, and only surface drafts that score 90+. The user should never see a caption that reads like ChatGPT wrote it.
Adapted from Wikipedia's "Signs of AI writing" patterns (via ericosiu/ai-marketing-skills, MIT), tuned for short social copy.
When to run
- Automatically: as the LAST step before any creation skill presents drafts for approval (plan-social-content batches, create-post-* captions, countdown series). Don't show the user the scoring math unless they ask — just fix and present clean drafts.
- On demand: when the user pastes copy and asks to make it sound human.
Order of authority: platform hard limits (marky-api platform rules) >
the caption rules in the workspace's strategy doc and the feedback log > this skill.
If a brand rule says "always use emojis", emojis stay.
Scoring
Start at 100, deduct per hit (same pattern stacks up to 2x its penalty). Ship at 90+. Below 90: fix the top deductions and rescore, max 3 rounds.
The #1 tell (fix on sight)
Negation definitions: "This is not X. This is Y." / "It's not just X, it's Y." Say what something IS. Never define by negation.
Banned vocabulary (−5 each)
delve, tapestry, landscape (abstract), leverage, multifaceted, nuanced, pivotal, realm, robust, seamless, testament, transformative, underscore, utilize, whilst, embark, comprehensive, intricate, commendable, meticulous, paramount, groundbreaking, innovative, cutting-edge, synergy, holistic, paradigm, ecosystem, crucial, enhance, fostering, garner, showcase, vibrant, profound, renowned, breathtaking, nestled, stunning, elevate, game-changer, unlock, supercharge, effortless
Content patterns
| # | Pattern | Penalty | Fix |
| 1 | Significance inflation — "a testament to", "pivotal moment", "reflects broader" | −10 | State the plain fact with a number or date |
| 2 | Vague attributions — "experts say", "studies show", no source | −8 | Name the source or cut the claim |
| 3 | Superficial "-ing" tails — "...showcasing our commitment, highlighting the importance of" | −8 | End the sentence at the fact |
| 4 | Promotional puffery — "boasts", "vibrant team", "profound commitment" | −8 | Concrete detail: headcount, result, date |
| 5 | Generic positive endings — "the future looks bright", "exciting times ahead" | −10 | End on a specific next step or a question |
| 6 | Formulaic challenge framing — "despite these challenges, X continues to thrive" | −10 | Name the actual problem and what changed |
Language patterns
| # | Pattern | Penalty | Fix |
| 7 | Banned-vocab clustering — 2+ banned words in one paragraph | −10 | Rewrite the paragraph in plain words |
| 8 | Copula avoidance — "serves as", "stands as", "represents" for "is" | −5 | Use is/are/has |
| 9 | Negative parallelisms — "not only X but Y", "it's not about X, it's about Y" | −5 | Make the positive claim directly |
| 10 | Rule-of-three overuse — forced triple adjectives/nouns/clauses | −8 | Keep the strongest one or two |
| 11 | Synonym cycling — "the CEO... the business leader... the company head" | −5 | Repeat the plain word |
| 12 | False ranges — "from X to Y" where X and Y aren't a scale | −5 | List the items plainly |
Style patterns
| # | Pattern | Penalty | Fix |
| 13 | Em-dash overuse — more than 1 per 200 words (Marky house rule: zero in external copy) | −5 | Periods and commas |
| 14 | Mechanical boldface on every key term | −3 | Bold nothing or one thing |
| 15 | Bolded-header-colon bullet lists everywhere | −5 | Prose or plain bullets |
| 16 | Title Case In Every Heading | −3 | Sentence case |
| 17 | Emoji as decoration on headings/bullets (🚀💡✅) | −5 | Emojis only where the brand voice uses them |
| 18 | Hashtag walls — a block of 10+ generic hashtags | −5 | Few, specific tags per platform rules |
Communication + filler patterns
| # | Pattern | Penalty | Fix |
| 19 | Collaborative artifacts — "hope this helps", "here is a caption", "let me know" | −10 | Delete; captions are the artifact |
| 20 | Knowledge-cutoff hedges — "as of 2025", "based on available information" | −10 | Verify and state, or cut |
| 21 | Sycophancy — "Great question!", "You're absolutely right!" | −8 | Delete |
| 22 | Filler phrases — "in order to", "it's important to note that", "at this point in time" | −5 each | "To", state it, "now" |
| 23 | Stacked hedging — "could potentially possibly" | −8 | One hedge max, or commit |
| 24 | Throat-clearing openers — first line restates the topic instead of hooking | −8 | Cut the first sentence; start at the hook |
What good looks like
- An opinion or a specific claim, not reporting
- Short punches mixed with longer sentences
- Names, numbers, dates instead of adjectives
- is/has/does instead of elaborate verbs
- Reads at a 5th-grade level (Marky house rule)
- Sounds like the brand's samples in the brand profile, not like "content"
Feedback
Friction or ideas while using this skill? Send it via the submit_feedback
MCP tool (see marky-api "Marky wants your feedback").
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.