humanizer

humanizer is a skill for Claude Code from crealwork/ai-marketing-kit. It costs 98 tokens per session (1,430 once invoked), scanned A, original, MIT.

A writing guide for making text sound like it was written by a person rather than generated by an AI system. It applies to copy such as marketing text, emails, articles, social posts, and newsletters.

In plain words
What is it for?
It helps rewrite drafts, remove filler and repeated patterns, vary sentence rhythm, add concrete detail, and briefly explain the main changes.
Why use it?
It identifies common AI writing patterns and replaces them with clearer, more specific language while keeping the original meaning. It also checks the result by reading it for a formal or artificial tone.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-marketing-kit plugin — 26 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/crealwork/ai-marketing-kit/humanizer
Any agent
npx skills add crealwork/ai-marketing-kit --skill humanizer
Clone the repo
git clone --depth 1 https://github.com/crealwork/ai-marketing-kit

Made for: Claude Code.

Or install ai-marketing-kit, the plugin that ships this one along with the rest of its 26 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for humanizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/humanizer.svg)](https://agentmods.dev/skills/crealwork/ai-marketing-kit/humanizer)
Your own site
<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/humanizer"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/humanizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.01430
Opus 5 $0.00049 $0.00715
Sonnet 5 $0.00020 $0.00286
Haiku 4.5 $0.00010 $0.00143

Measured 6d ago against content hash da477f9a6f58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

humanizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/humanizer/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanizer

AI 초안을 사람 글로 바꾼다. 원칙: 문장을 예쁘게 다듬는 게 아니라, AI 특유의 패턴을 제거하고 구체성을 주입하는 것. 코드 주석은 대상이 아니다.

Process

  1. 진단 — 아래 금지 목록과 대조해 문제 구절을 전부 표시한다 (고치기 전에).
  2. 재작성 — 패턴 제거 + 구체성 주입. 의미 보존, 길이는 보통 10–20% 줄어든다.
  3. 소리 내어 읽기 테스트 — 머릿속으로 읽어서 보도자료처럼 들리면 다시 쓴다.
  4. 유저에게 무엇을 왜 바꿨는지 2–3줄로 보고 (전체 diff 나열 금지).

Universal rules (언어 공통)

  • 문장 길이에 리듬을 — 짧게 친다. 그리고 숨이 긴 문장이 따라온다. 전부 같은 길이로 앉아 있으면 AI다.
  • 헤지 제거: "generally", "typically", "often", "it's worth noting", "arguably" — 그냥 말해라.
  • 한 문장 한 아이디어. 쉼표로 절 세 개 쌓지 않는다.
  • 형용사 삼단 나열 금지 ("fast, reliable, and scalable") — 하나만 고르거나 다시 써라.
  • 목 가다듬기 오프닝 제거: "In today's world", "As we all know", "It's important to understand".
  • 모든 문장이 완벽하게 대구를 이루면 오히려 티가 난다 — 일부러 흐트러뜨린다.

English — AI tells (DO NOT USE)

  • "It's not just X, it's Y" / "X isn't just Y — it's Z" 구문
  • "delve", "nuanced", "multifaceted", "robust", "seamless", "leverage"(동사), "unlock", "elevate", "empower", "navigate the complexities"
  • "In the realm of", "In the world of", "At its core", "That said,"
  • Em-dash 남용 — 문단에 하나 넘으면 마침표나 쉼표로 바꾼다
  • 연속 문단을 "I'll" / "Let's" / "Here's"로 시작
  • "Dive into", "unpack", "explore"를 필러 동사로
  • "Whether you're X or Y, [product] has you covered"로 마무리

Korean — AI tells (DO NOT USE)

  • 번역투: "~것이다", "~인 것입니다", "~할 수 있습니다" 남발 → 상황에 맞게 "~예요", "~해요", "~합니다"로 자연화
  • "매우", "정말", "굉장히" 같은 빈 강조부사 → 빼거나 구체적 수치로
  • "흥미롭게도", "주목할 만한 점은", "다시 말해" 같은 메타 전환구
  • 과도한 "귀하", "저희" 반복 — 한 번 쓰고 생략
  • 영어 직역 느낌: "~에 있어서", "~라는 측면에서", "~을 통해"
  • 존댓말·반말 혼용 — 한 글 안에서 톤 고정

Instead, aim for

  • 영어는 축약형 (it's, don't, you're) — 격식 문서 제외
  • 한국어는 구어체 허용 (SNS·이메일 오프닝): "이거 진짜 괜찮아요" 같은 리듬
  • 추상 대신 구체: "saves significant time" → "saves 4 hours/week"
  • 구체적 동사: "ship", "cut", "fix" — not "implement", "reduce", "address"

Before / After

EN before: "Our robust platform leverages cutting-edge AI to seamlessly empower your team, unlocking unprecedented productivity gains." EN after: "Your team ships twice as fast. The AI handles the busywork — scheduling, follow-ups, reports — so people don't have to."

Read the full file on GitHub · 87 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 87 lines · 98 tokens per session scan A da477f9a6f58

Subscribe to this mod's changes

humanizer is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,430 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens