Skip to content
Skills Library
Personal productivity · Writing

write-human

/write-human

Draft or edit writing a person will send or publish as themselves: texts, WhatsApp and DMs, emails, replies, LinkedIn messages, introductions and first approaches, client updates, cover notes, posts and short professional documents, so it sounds like them, not like an AI. Use whenever the user asks to write, reply to, rewrite, polish, shorten or "make this sound less like AI", or asks "what should I say to X". Drafts from the sender's own past messages, leads with the reader, cuts preview lines, stock phrases and research the reader never shared, and checks "tomorrow" and every other time word

Licence
MIT
Last repository change
04.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
2
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 04.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 2 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/draft_lint.py, scripts/test_draft_lint.py

What it does and when to use it

Draft or edit writing a person will send or publish as themselves: texts, WhatsApp and DMs, emails, replies, LinkedIn messages, introductions and first approaches, client updates, cover notes, posts and short professional documents, so it sounds like them, not like an AI. Use whenever the user asks to write, reply to, rewrite, polish, shorten or "make this sound less like AI", or asks "what should I say to X". Drafts from the sender's own past messages, leads with the reader, cuts preview lines, stock phrases and research the reader never shared, and checks "tomorrow" and every other time word

Triggers from the description

make this sound less like AIwhat should I say to Xtomorrow
Original author description

Draft or edit writing a person will send or publish as themselves: texts, WhatsApp and DMs, emails, replies, LinkedIn messages, introductions and first approaches, client updates, cover notes, posts and short professional documents, so it sounds like them, not like an AI. Use whenever the user asks to write, reply to, rewrite, polish, shorten or "make this sound less like AI", or asks "what should I say to X". Drafts from the sender's own past messages, leads with the reader, cuts preview lines, stock phrases and research the reader never shared, and checks "tomorrow" and every other time word

How it works

  1. Start with the reader
  2. Draft in their voice, from their words
  3. What makes it read as a person
  4. What to cut
  5. By kind of writing
  6. Check, then hand over
Original SKILL.md headings · 62 lines, 1,097 words
SKILL.md preview
---
name: write-human
description: Draft or edit writing a person will send or publish as themselves: texts, WhatsApp and DMs, emails, replies, LinkedIn messages, introductions and first approaches, client updates, cover notes, posts and short professional documents, so it sounds like them, not like an AI. Use whenever the user asks to write, reply to, rewrite, polish, shorten or "make this sound less like AI", or asks "what should I say to X". Drafts from the sender's own past messages, leads with the reader, cuts preview lines, stock phrases and research the reader never shared, and checks "tomorrow" and every other time word against the day it is sent. Drafts only; the user sends.
license: MIT
---

# Write human

Write something the user can send as themselves. Natural writing comes from having something specific to say to a specific reader, not from vocabulary bans or deliberate roughness. The user's own wording and edits outrank every default here.

## Start with the reader

Work out who will read it, what they already know, what it must achieve, and where they will read it (a phone notification, an inbox, a printed page). Ask only when a missing fact would change the draft. Pick the form the job needs: a warm reply, a first approach and a technical update are different things.

If the user supplies a draft, keep their meaning, emphasis and good phrasing, and edit at the level they asked for.

Read the live thread before replying when its state matters: a local draft or a sent-items log is not proof of what was actually sent or received.

## Draft in their voice, from their words

The user's voice is in their sent messages, not in a general idea of "friendly" or "professional". For anything personal, ask for (or find, if you have access) three to five of their recent messages **to this person** and draft from those: length, capitals, punctuation, emoji, how they sign off. People write very differently to a grandparent, a colleague and a sibling. If no samples are available, write plainly and briefly, and say which parts are guesses.

When the user adds a line of their own, keep it exactly as written.

## What makes it read as a person

- **Lead with them, not with you.** Open on their news, their question or what they said last time. Your result is often the least interesting part to the reader.
- **Answer the last unanswered thing first.** If they made a joke, pick it up.
- **Say the real thing plainly.** If someone is going through something, ask about it directly and keep it light; don't circle it or get earnest.
- **Hand them the choice.** Offer a loose window and let them pick the time and place.
- **One line about them** where it fits: their news, their work, a bit of praise that is true.
- **Leave out what you found by digging.** A detail from their profile, an event page or another chat reads as surveillance. Use only what they told the sender.
- **Warmth grounded in something real.** Plain stock warmth ("thanks for your patience") is fine when it fits an actual event. Don't invent gratitude, excitement or a favour to thank them for, and never supply a reason, news or an apology the sender did not give.
- **Keep dates short, and check them on the day the draft goes.** In a message that goes the day it is written, a plan for the next day can say "tomorrow". A plan in a draft that may sit gets a short named day, "Friday 13th", not "tomorrow" or "this weekend"; add the month only when the day alone could mean two dates. Something already past stays loose, "at the end of last week", not a full weekday and date. Drafts often sit for a day or two, so re-read every time word, the loose ones too, against the day it is actually sent.

## What to cut

- A first line that previews the message ("A quick update and one bigger question").
- A second sentence that shrinks a gracious out ("No problem if not. It works fine without it.").
- Limitations the reader doesn't need in order to say yes.
- Flourishes that read as boasts, over-offering ("happy to do a panel, a talk, or whatever suits"), and a PS bolted onto a first approach. One ask per message.
- Presuming the reader's state of mind ("as I'm sure you've noticed"), and contrarian jabs.
- Something the reader already has from an earlier message or from the product itself.

Length is not the goal. Real edits lengthen as often as they shorten; what goes is logistics, research and devices, and what comes in is something about the person. Revise by cutting: a second pass deletes, it doesn't polish.

## By kind of writing

- **Texts and DMs:** usually two to five short messages rather than one paragraph. Show each separate message as its own blockquote so the user can paste them one by one. End on the practical line.
- **First approaches and introductions:** describe a company by what it does, not where it is; for a non-technical or senior reader, purpose and impact beat technique, and one checkable credential beats a product description. Lead with what people can picture using, not with the tool the writer is proudest of.
- **Emails and updates in any channel:** name the one point the message has to land, open with a short paragraph that says it head-on, then give one or two proof points: concrete facts that make it believable. The ask or next step comes after and is easy to find. One topic per email, and a second email names the first; a disclosure or apology in one plain sentence, not a confession. Introduce anything embedded (a template, a quoted reply, a table) in one sentence that says what it is and where it came from. When the reader must act on a decision, give an instruction they can relay ("Use version 2 for this batch; flag uncertain words") and say plainly if it is still pending.
- **Technical and research updates:** real system names, exact numbers with their units and comparison ("error rate fell from 30% to 16%", not only "halved"), and what remains uncertain. Respect what the reader already knows; don't explain their own project back to them.
- **Posts and shared documents:** follow the conventions already on the page or in the thread.

## Check, then hand over

In Claude Code or anywhere Python runs, check the drafts before showing them:

```bash
python3 scripts/draft_lint.py --markdown reply.md       # every blockquote is one message
python3 scripts/draft_lint.py --channel email draft.txt # one email
```

It flags em dashes, stock phrases, "not X but Y" constructions, header-style labels, relative dates and over-long texts. (The phrase lists live in the script on purpose: naming them here would prime them.) If a flag is wrong for this reader because the sender genuinely writes that way, keep it and say so.

Show the drafts ready to paste, with no commentary on the writing process. This skill drafts; the user sends. When they edit a draft and ask for another pass, carry their edits forward rather than regenerating from scratch.
Files in this package (3)
  • SKILL.md 7 KB
  • scripts/draft_lint.py 8 KB
  • scripts/test_draft_lint.py 3 KB

Versions

RepositoryScoreLicence
This page · marliechorgan/claude-setup100MIT
tojim00d/Orbit-skills100MIT

Database snapshot: 13.11.2026 · package version 8253525e8fdc (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100write-like-human
    Make anything you write sound like a real person, not AI, keeping your facts, numbers, and formatting. Fixes or drafts emails, WhatsApp replies, letters (including RTI and complaints), resumes, posts, bios, reports, speeches, wishes, reviews, form answers, payment reminders,…
  • 100voice
    Writes and edits messages, emails, posts and drafts in the user's own voice and strips the common signs of AI-written text. Use when the user asks to "draft", "write", "reply to", "polish", "make this sound like me", "de-AI this", "proofread", or when any chief-of-staff skill…
  • 100write-as-me
    Draft text in the user's own voice using their write-like-me voice pack - chat replies, emails, posts, docs. Use whenever the user asks to write, draft or reply "as me", "in my voice", "like I would", "sound like me", "draft a reply to <person>", "write an email to <person>…
  • 86draft-with-my-context
    Draft everyday writing that needs the user's own information — emails, replies, bios, LinkedIn or X posts, short statements, intros for a meeting, progress updates, abstracts or talk descriptions. Use when asked to write, reply, draft, introduce, update or summarise something…
  • 100human-voice
    Write anything (blog posts, articles, emails, chat replies, LinkedIn posts, summaries, release notes, feedback, apologies, bios, explainers) so it reads like one sharp, warm person and never like AI slop. Point first, specifics over adjectives, wit only where it is earned, and…
  • 100ownvoice
    Write, rewrite, or reply to emails and everyday messages in the user's natural voice. Use for recruiter emails, founder DMs, follow-ups, Slack or WhatsApp messages, and requests to make a draft less stiff or AI-sounding. Supports English and Hinglish with optional user-provided…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.