humanize
Skill4 starsChanged 17 days agoMITView on GitHub
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
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 repository17 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ask-firstSkill
- claude-project-rulesSkill
- compact-markdownSkill
- pr-reviewSkill
- empty-commitSkill
- github-issue-creatorSkill
- git-mergeSkill
- git-worktreeSkill
- handoff-sessionSkill
- html-landing-pageSkill
- offload-taskSkill
- readme-craftSkill
- skill-auditSkill
- study-notesSkill
- visualize-itSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 64 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
If a cleaner sentence changes what the document asserts, leave the sentence unchanged.
- Distinctive: line 21
Do not rewrite code blocks, commands, headings, tables, links, or quoted text unless explicitly asked.
- Very specific: line 27
Cut filler phrases: Remove throat-clearing openers, emphasis crutches, generic transitions, and empty intensifiers.
- Distinctive: line 32
Break formulaic structures: Avoid binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, and false agency when …
- Distinctive: line 36
Prefer active voice: Use it when it improves clarity.
- Distinctive: line 45
Match the reader and register: Use direct instructions for user-facing guidance.
- Very specific: line 57
Keep the register: Never trade a term of art, an API name, or legal phrasing for a livelier word.
- Distinctive: line 88
Use the score as a revision prompt, not a pass/fail gate.
“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
Eliminate predictable AI writing patterns from prose.
Scope
Rewrite phrasing, not meaning. Preserve facts, numbers, file paths, key names, API names, links, claims, uncertainty, scope, modality, and intentional voice. If a cleaner sentence changes what the document asserts, leave the sentence unchanged.
Identify the document type before editing. Prose, marketing copy, technical docs, policies, changelogs, licenses, and agent instructions need different levels of compression and different registers.
Do not rewrite code blocks, commands, headings, tables, links, or quoted text unless explicitly asked. Preserve intentional fragments, repetition, parallel structure, and rhetorical phrasing when they improve navigation or emphasis.
Core Rules
- Cut filler phrases. Remove throat-clearing openers, emphasis crutches,
generic transitions, and empty intensifiers. Keep adverbs that carry a fact,
such as
locally,manually,asynchronously, oroptionally. See references/phrases.md. - Break formulaic structures. Avoid binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, and false agency when they add no meaning. See references/structures.md.
- Prefer active voice. Use it when it improves clarity. Keep passive voice when the actor is unknown, irrelevant, intentionally omitted, or required by technical, legal, or privacy wording. Avoid inanimate objects performing human actions ("the complaint becomes a fix").
- Be specific. Replace vague declaratives ("The reasons are structural")
with the specific fact. Keep precise qualifiers such as
every,always, andneverwhen the claim requires them. - Match the reader and register. Use direct instructions for user-facing guidance. Use the established technical, legal, or product register for specialized documents. Do not force conversational "you" into policies, API docs, or agent instructions.
- Vary rhythm where the format allows it. Mix sentence lengths and avoid repetitive paragraph endings. Keep consistent structure in tables, lists, changelogs, and reference material.
- Trust readers. State facts directly. Remove softening, justification, and hand-holding unless the context requires an explanation or warning.
- Keep the register. Never trade a term of art, an API name, or legal
phrasing for a livelier word. "The extension clears history" holds because
the code calls it
clearHistory; "wipes" is punchier and wrong. Keep "was preferred" over "won" and "manually" over "by hand". This rule outranks every style rule in privacy policies, licenses, security notes, API docs, and reviewer-facing material.
Quick Checks
Before delivering prose:
- Any filler, empty intensifier, or generic transition? Cut it.
- Did any edit change a fact, number, path, key name, link, claim, scope, or qualifier? Restore the original meaning.
- Did a rewrite alter a term of art, API name, or legal phrase? Put it back.
- Does active voice improve the sentence? Use it. Otherwise keep accurate passive voice.
- Is an inanimate thing doing a human action? Name the actor or use a precise system verb.
- Any vague declarative ("The implications are significant")? Name the specific implication.
- Any "here's what/this/that" throat-clearing? Cut to the point.
- Any "not X, it's Y" contrast that adds no distinction? State Y directly.
- Did the edit damage intentional structure in a list, table, heading, quote, changelog, policy, or reference section? Restore it.
- Did the final text preserve the document's register and intended audience?
- Did the final fact check preserve names, numbers, claims, examples, links, and code terms?
Scoring
Use the score as a revision prompt, not a pass/fail gate. Rate 1–10 on each:
| Dimension | Question |
| Directness | Does each sentence reach its point quickly? |
| Rhythm | Does the prose avoid a metronomic pattern? |
| Trust | Does it respect reader intelligence? |
| Authenticity | Does it fit the document's voice? |
| Density | Does each phrase carry useful information? |
Examples
See references/examples.md for before/after transformations.
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.

