agentleFS
fmindfmind/dot/skills/humanize/SKILL.md

humanize

Skill13 starsChanged yesterdayMITView on GitHub

Turn dense AI drafts into clear, scannable, visually structured human communication for emails, chat, PRs, docs, reports, and slides.

78 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • dawn840705Skill

    humanize-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

  • mskim8717Skill

    humanize-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

  • CoralGameSkill

    perf-profile

    Structured performance profiling workflow. Identifies bottlenecks, measures against budgets, and generates optimization recommendations with priority rankings.

    Also in 3 projects that use this

  • Rayan55050Skill

    content

    Создание контента: посты, статьи, тексты

    Also in 3 projects that use this

  • luischanciSkill

    proofread

    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

  • insight68Skill

    pricing

    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

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 67 edited versions we read keep these.

  • 1

    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
  1. Very specific:

    Before: _"Checked loader.py.

    line 25
  2. Distinctive:

    After: Batch imports are healthy again — approve PR 418 before 17:00 UTC.

    line 27
  3. Very specific:

    HTML reports, newsletters, & email: follow native visual patterns in primitives and start standalone HTML briefs from report.html.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 67 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Humanize

Respect human reading time. Deliver high-signal, scannable, visually structured messages instead of dense unformatted AI text dumps.

Mandatory 3-step cut before drafting

Apply these three filters before writing a word:

  1. Name the one point: finish "After reading this, the reader should know or do ___." If there are two goals, split or demote the secondary one.
  2. Keep 1 to 3 signals: drop setup narration, internal tool mechanics, redundant caveats, and low-value details; every kept fact must change a decision or confirm impact.
  3. Choose one visual structure: pair text with the strongest native visual the medium supports (summary banner, colored highlight, horizontal separator, comparison table, KPI row, diagram, or collapsible drawer).

Before: "Checked loader.py; bumped chunk_size=100_000 and memory=8Gi in infra/main.tf; all 14 pytest cases pass; please review PR #418."

After: Batch imports are healthy again — approve PR 418 before 17:00 UTC. Peak memory now stays well below our 8 GB limit.

Hard rules

  • Zero prose backticks: never put backticks around products, formats, acronyms, metrics, files, branches, or status labels in human copy. Write Python 3.14, JSON, BigQuery, Cloud Run, 42 ms, or the config file — never wrap everyday prose words in code spans. Reserve monospace strictly for literal commands, code snippets, or paths a reader must copy verbatim to run.
  • Zero jargon: translate stack traces, internal flag names, exit codes, and plumbing into business or user outcomes (service restarted cleanly beats OOMKilled exit 137 in ingest-worker).
  • Signal over completeness: state the headline outcome first, round numbers cleanly with a baseline (+18% throughput vs last quarter), and push logs or raw tables into a collapsible drawer, appendix, or speaker note.
  • Visual hierarchy everywhere: break up any block taller than three lines with a bold lead-in, color badge, tinted callout banner, separator line, comparison table, or chart following ~/.agents/DESIGN.md.
  • Keep external voice clean: adopt the user's or audience's language and tone; never expose internal assistant framing (Done, Confidence, Verification, Decisions) in external emails, docs, tickets, PRs, or slides.

Default length budgets

  • Chat & Slack: 80 words or fewer; one headline line, up to three bold-lead bullets, explicit ask.
  • Email, PRs, & issues: 150 words or fewer; bold takeaway, one visual highlight or compact table, collapsible detail if needed, clear decision/date.
  • Docs & reports: one-screen executive banner plus visual sections; secondary mechanics in appendices.
  • Slides: max 30 visible words and one focal visual per slide; context lives in speaker notes.

Choose format by medium

  • HTML reports, newsletters, & email: follow native visual patterns in primitives and start standalone HTML briefs from report.html. Downstream delivery: draft-mail.
  • Docs, memos, PRs, & tickets: select a template structure from outlines (including report.md), pick native Markdown/HTML/ADF visuals from primitives, and inspect rendered pages visually via playwright. Downstream owners: draft-doc, acli, gh, documentation-site, web-frontend, repository-docs.
  • Decks & branded graphics: structure 6–10 slide decision arcs in outlines and render slides or standalone cards via draft-typst-deck (or diagrams-as-code).

Pre-send gate

Read the draft like a busy stakeholder scrolling on a phone: cut any paragraph over three lines, remove every prose backtick and internal jargon word, confirm the key number and next step stand out visually at a glance, and move secondary proof behind a collapse or speaker note.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.