Agent skill

Xe Writing Style

by Xe in Xe/x

Transform unstructured notes into polished blog posts in Xe Iaso's voice.

CC0-1.0Auto-check passedWriting & Content

Install Xe Writing Style

skills CLI
$ npx skills add Xe/x --skill xe-writing-style -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Xe/x xe-writing-style --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Xe/x.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/xe-writing-style .claude/skills/xe-writing-style && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
xe-writing-style
GitHub stars
337
Token cost
~2.2k tokens
SKILL.md length
882 words
Files
14 (incl. references, assets)
Skills in repo
4
Repo updated
First seen
Licence
CC0-1.0

At a glance

Transform unstructured notes into polished blog posts in Xe Iaso's voice.

  • Works in 6 steps: Successive paragraphs must not start… → Write for peers, not beginners. Assume… → No corporate or marketing tone. No… → …
  • The user provides a brain dump
  • SKILL.md covers Hard Rules, Voice in Brief, Structure and Openings, plus 6 more sections
  • Calls git

What it does

Xe Writing Style is an agent skill from Xe/x. Transform unstructured notes into polished blog posts in Xe Iaso's voice. Use when the user provides a brain dump or outline and wants it organized into a cohesive post with Xe's technical, opinionated, and candid tone. Also use when editing or reviewing prose that should match Xe's style.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including reference files and assets (for example `references/emotional-personal.md`, `references/fiction-mythic.md` and `references/humor-satire.md`).

It sits in Writing & Content, covering Blog and article writing and Brand voice and tone. The repository describes itself as: Various tools, trinkets and experiments. The licence is CC0-1.0.

When your agent uses it

  • The user provides a brain dump
  • Outline and wants it organized into a cohesive post with Xes technical
  • Reviewing prose that should match Xes style

Example prompts

  • “/xe-writing-style”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Successive paragraphs must not start with the same letter. If paragraph N starts with "T", paragraph N+1 must start with a different…
  2. Write for peers, not beginners. Assume professional-level technical context.
  3. No corporate or marketing tone. No "leverage", "synergy", "empower", "streamline", "harness", "unlock". Write like a human talking to…
  4. Admit uncertainty. "I think", "I suspect", "I'm not sure" when genuinely uncertain.
  5. Show tradeoffs. Never present a solution without its costs.
  6. Context before implementation. Explain why something matters before showing how.

What it can do on your machine

Read from SKILL.md and the folder at commit 5388b62. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Xe Writing Style loads about 2.2k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 882 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Xe/x at commit 5388b62, republished under its CC0-1.0 licence (© Xe). 882 words, ~2,215 tokens.

Download SKILL.mdSave it as .claude/skills/xe-writing-style/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
xe-writing-style
description
Transform unstructured notes into polished blog posts in Xe Iaso's voice. Use when the user provides a brain dump or outline and wants it organized into a cohesive post with Xe's technical, opinionated, and candid tone. Also use when editing or reviewing prose that should match Xe's style.

Xe Iaso Blog Post Writer

Transform messy notes into blog posts that sound like Xe Iaso. Read references/voice-tone.md for detailed voice characteristics. Read 2-3 random example posts from assets/ to calibrate tone. Then read the reference file that matches the post's emotional register:

  • references/story-circle.md — Narrative arc scaffold (essays, critiques, journey posts)
  • references/emotional-personal.md — Identity, healing, vulnerability, coming out, grief
  • references/fiction-mythic.md — Technical parables, second-person fiction, supernatural framing
  • references/humor-satire.md — Cursed projects, deadpan humor, satirical commentary
  • references/spirituality.md — Meditation, belief-as-tool, programming-consciousness parallels

Most posts blend 2-3 of these modes. Read whichever apply.

Hard Rules

Non-negotiable constraints:

  1. Successive paragraphs must not start with the same letter. If paragraph N starts with "T", paragraph N+1 must start with a different letter. Rewrite sentence openings as needed. Character dialogue blocks (<Conv>) do not count as paragraphs for this rule.
  2. Write for peers, not beginners. Assume professional-level technical context.
  3. No corporate or marketing tone. No "leverage", "synergy", "empower", "streamline", "harness", "unlock". Write like a human talking to another human.
  4. Admit uncertainty. "I think", "I suspect", "I'm not sure" when genuinely uncertain.
  5. Show tradeoffs. Never present a solution without its costs.
  6. Context before implementation. Explain why something matters before showing how.

Voice in Brief

Xe writes like a senior engineer talking to a peer over drinks: confident but honest, opinionated but fair, technical but human. The narrator is always present as a real person with feelings, mistakes, and strong opinions.

Markers that distinguish this voice from generic technical writing:

  • Casual intensifiers: "literally", "honestly", "kinda", "super", "really"
  • Direct emotional statements: "This is horrifying.", "I love this.", "I hate that this makes sense."
  • Self-deprecation: "I felt like a dunce.", "I literally have no idea what I am doing wrong."
  • Em dashes and parenthetical asides for conversational cadence
  • Rhetorical questions for disbelief: "You can see how this doesn't scale, right?"
  • Sentence fragments for emphasis. Single-sentence paragraphs for pacing.
  • Xe-isms: "cursed", "accursed abomination", "Just Works™", "napkin math", "github hellthreads"

Read references/voice-tone.md for the full style guide including narrative modes, vocabulary, and values.

Structure

Choose the pattern that fits the material:

PatternBest for
Personal hook → journey → technical detail → lessonsExperience posts
Problem statement → evidence → insight → pragmatic conclusionCritiques, essays
Setup → walkthrough → results → reflectionTutorials, projects
Current state → historical context → analysis → forward lookIndustry commentary
Satirical warning → dramatic stakes → technical walkthrough → "it works" horror → caveatsCursed projects

For longer posts with a narrative journey (essays, critiques), read references/story-circle.md for the 8-beat story circle scaffold.

Openings

Lead with one of:

  • Personal memory: "A while ago, I got really frustrated at my Samsung S7."
  • Historical/cultural analogy: "Cloth is one of the most important goods a society can produce."
  • Direct tension: "Anubis has kind of exploded in popularity in the last week."
  • Pop culture/sci-fi hook: "In Blade Runner, Deckard hunts down replicants..."
  • Satirical warning box followed by dramatic stakes (for cursed content)

Never open with a generic thesis or "In this post, I will..."

Closings

  • Tie back to the opening hook or tension
  • End with forward momentum, an open question, or a sober reality check
  • Often followed by --- then supplementary material (related links, credits, stream plugs)
  • Sometimes a final character dialogue as a coda
Show full SKILL.md (360 more words)Show less

Character Dialogue System

Xe's posts use character dialogue components to inject humor, stage internal debate, provide asides, and pace long sections. This is one of the most distinctive features.

Characters
CharacterRoleTypical moods
CadeyXe's main voice for asides, emotional reactions, and commentarycoffee, aha, enby, percussive-maintenance, facepalm
AoiAsks clarifying questions, expresses confusion or surprisecoffee, wut, sus, grin, facepalm
MaraProvides helpful context, technical explanations, linkshacker, happy
NumaCorrections, dark humor, "well actually" momentsdelet, happy, smug, neutral
Dialogue Syntax

Single aside (standalone comment):

jsx
<Conv name="Cadey" mood="coffee">
  Is this how we end up losing the craft?
</Conv>

Multi-character exchange (wrap in <ConvP>):

jsx
<ConvP>
  <Conv name="Aoi" mood="wut">
    Wait, really?
  </Conv>
  <Conv name="Cadey" mood="aha">
    Yep!
  </Conv>
</ConvP>
When to Use Dialogue
  • Break up long technical sections with a reaction or joke
  • Ask the question the reader is thinking (usually Aoi)
  • Provide tangential-but-useful info without derailing the text (usually Mara)
  • Deliver a punchline or emotional beat (usually Cadey or Numa)
  • Stage a mini-debate that illuminates tradeoffs

Signature Devices

  • Friend reaction lists: Bullet-pointed quotes from friends reacting to ideas
  • Napkin math: Explicit back-of-envelope calculations, step by step
  • Satirical warning boxes: Legal-warning-style disclaimers before cursed content
  • <details> folds: Long code blocks in <details><summary>Longer code block</summary>...</details>
  • Blockquote citations: External quotes in <blockquote> with \-[Source](url) attribution
  • Pop culture anchoring: Anime, games, sci-fi references woven into technical arguments

MDX Format

Posts are MDX (Markdown + JSX). Component imports vary by platform.

Personal Blog (xeiaso.net)
mdx
---
title: "Post Title"
desc: "One-line description"
date: YYYY-MM-DD
hero:
  ai: "Photo credit or AI model name"
  file: "hero-image-slug"
  prompt: "Image description"
  social: false
---

import Conv from "../../_components/XeblogConv.tsx";

Images: <Picture path="blog/YYYY/post-slug/image-name" desc="Alt text"/>

Company Blog (Tigris)
mdx
---
slug: post-slug
title: "Post Title"
description: |
  Multi-line SEO description
keywords: [...]
authors: [xe]
tags: [...]
---

import Conv from "@site/src/components/Conv";

Images: Standard <img> with imported files. Admonitions: :::note ... :::

Body Writing Checklist

  • Vary paragraph length (single-sentence emphasis vs. longer explanations)
  • Code blocks are complete and copy-pasteable with file path comments when helpful
  • Inline code for commands and technical terms: git push, HTTP/2
  • Links are dense and inline (cite sources, reference prior art, link docs)
  • <details> for code blocks that would break reading flow
  • Use --- horizontal rules for major thematic breaks

Process

  1. Accept the user's brain dump without requiring organization
  2. Read references/voice-tone.md
  3. Read 2-3 random example posts from assets/ for tone calibration
  4. Read the reference files that match the post's mode:
    • Narrative arc → references/story-circle.md
    • Personal/vulnerable → references/emotional-personal.md
    • Fiction/parable → references/fiction-mythic.md
    • Humor/satire → references/humor-satire.md
    • Spiritual themes → references/spirituality.md
  5. Choose a structure pattern and draft
  6. Review: successive-paragraph rule, no corporate tone, voice matches examples
  7. Show draft to user and iterate

© Xe, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (references, assets) in .claude/skills/xe-writing-style of Xe/x.

  • SKILL.md
  • assets/anything-message-queue.mdx
  • assets/gpt-oss-for-agents.mdx
  • assets/markdownlang.mdx
  • assets/parallel-universes.mdx
  • assets/rolling-ladder-behind-us.mdx
  • assets/squandered-holy-grail.mdx
  • assets/who-assistant-serve.mdx
  • references/emotional-personal.md
  • references/fiction-mythic.md
  • references/humor-satire.md
  • references/spirituality.md
  • references/story-circle.md
  • references/voice-tone.md

Open the folder on GitHubat commit 5388b62

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in Xe/x, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Xe Writing Style next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Xe Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xe Writing Style this skillXe/x337—~2.2kAutomated safety check: PassCC0-1.0
Khazix WeChat Article WriterKKKKhazix/khazix-skills21k1 repos~2.9kAutomated safety check: PassMIT
Brand Voice Content Creatordavila7/claude-code-templates33k3 repos~1.9kAutomated safety check: PassMIT
Voice Buildercharlie947/social-media-skills3.8k—~3.3kAutomated safety check: PassMIT
Content CreatoraAAaqwq/AGI-Super-Team1053 repos~1.9kAutomated safety check: PassMIT
Content Writerchrispangg/deepagentsdk128—~3.3kAutomated safety check: PassMIT

Similar skills

  • Khazix WeChat Article Writer

    KKKKhazix/khazix-skills

    Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.

    21k GitHub starsUsed in 1 repo~2.9k tokens
    Writing & ContentAuto-check passed
  • Brand Voice Content Creator

    davila7/claude-code-templates

    Analyzes a brand's existing writing to lock in a consistent voice, then builds SEO blog posts and platform-specific social content around it.

    33k GitHub starsUsed in 3 repos~1.9k tokens
    Writing & ContentAuto-check passed
  • Voice Builder

    charlie947/social-media-skills

    Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing.

    3.8k GitHub stars~3.3k tokensUpdated 25 days ago
    Writing & ContentAuto-check passed
  • Content Creator

    aAAaqwq/AGI-Super-Team

    Create SEO-optimized marketing content with consistent brand voice.

    105 GitHub starsUsed in 3 repos~1.9k tokens
    Writing & ContentAuto-check passed
  • Content Writer

    chrispangg/deepagentsdk

    Writing content across different platforms and styles. An agent skill from chrispangg/deepagentsdk.

    128 GitHub stars~3.3k tokensUpdated 7 mo ago
    Writing & ContentAuto-check passed
  • Feature Blog

    pockethost/pockethost

    Ship user-facing PocketHost features with a blog post instead of semver release notes.

    1.4k GitHub stars~818 tokensUpdated 12 days ago
    Writing & ContentAuto-check passed

More from Xe/x

  • Write Go table-driven tests following Go community best practices and this repository's conventions.

    337 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Build interactive hypermedia-driven applications with templ and HTMX.

    337 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Write Go code following the conventions and patterns used in the within.website/x repository, including CLI patterns with internal.HandleStartup(), error handling, logging with slog, HTTP handlers…

    337 GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Xe Writing Style

What does Xe Writing Style do?

Transform unstructured notes into polished blog posts in Xe Iaso's voice. Xe Writing Style is an agent skill from Xe/x. Transform unstructured notes into polished blog posts in Xe Iaso's voice.

When should I use Xe Writing Style?

Xe Writing Style fits situations like: the user provides a brain dump; outline and wants it organized into a cohesive post with Xes technical; reviewing prose that should match Xes style.

How do I install Xe Writing Style in Claude Code?

Run `npx skills add Xe/x --skill xe-writing-style -a claude-code`. Or copy the skill folder (.claude/skills/xe-writing-style in Xe/x) into .claude/skills/xe-writing-style in your project. Claude Code loads it when a task matches its description.

How do I install Xe Writing Style in Codex?

Run `npx skills add Xe/x --skill xe-writing-style -a codex`. Or copy the skill folder (.claude/skills/xe-writing-style in Xe/x) into .agents/skills/xe-writing-style in your project. Codex loads it when a task matches its description.

Can I use Xe Writing Style in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Xe/x --skill xe-writing-style -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xe-writing-style, .gemini/skills/xe-writing-style, .github/skills/xe-writing-style and .opencode/skills/xe-writing-style in your project.

What does Xe Writing Style need to run?

Going by SKILL.md and its folder, Xe Writing Style needs the command-line tools its instructions call (git).

Does Xe Writing Style access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Xe Writing Style safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Xe Writing Style use?

Xe Writing Style is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Xe Writing Style use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.4k tokens, read only when the agent opens those files.

What are the alternatives to Xe Writing Style?

Skills that share tags, products or a category with Xe Writing Style: Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars), Brand Voice Content Creator (davila7/claude-code-templates, 33k stars), Voice Builder (charlie947/social-media-skills, 3.8k stars) and Content Creator (aAAaqwq/AGI-Super-Team, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xe Writing Style?

Xe (a GitHub user) maintains it in Xe/x, which has 337 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 2026.

Source: Xe/x on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.