Agent skill

Writing Style

by asgeirtj in asgeirtj/system_prompts_leaks

Draft or edit writing in the user's voice for the person who will read it and where it will appear.

CC0-1.0Auto-check passedWriting & Content

Install Writing Style

skills CLI
$ npx skills add asgeirtj/system_prompts_leaks --skill writing-style -a claude-code

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

GitHub CLI
$ gh skill install asgeirtj/system_prompts_leaks 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/asgeirtj/system_prompts_leaks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/OpenAI/dots/skills/writing-style .claude/skills/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
writing-style
GitHub stars
69k
Token cost
~1.3k tokens
SKILL.md length
819 words
Files
1
Skills in repo
128
Repo updated
First seen
Licence
CC0-1.0

At a glance

Draft or edit writing in the user's voice for the person who will read it and where it will appear.

  • Slides written on their behalf
  • SKILL.md covers Find the right examples, Write the draft and Examples
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Not for your own replies

What it does

Writing Style is an agent skill from asgeirtj/system_prompts_leaks. Draft or edit writing in the user's voice for the person who will read it and where it will appear. Use for messages, emails, documents or slides written on their behalf, not for your own replies.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Brand voice and tone and Slides and decks. The repository describes itself as: Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro… The licence is CC0-1.0.

When your agent uses it

  • Slides written on their behalf
  • Not for your own replies

Example prompts

  • “/writing-style”

What it can do on your machine

Read from SKILL.md and the folder at commit 60d44cc. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Writing Style loads about 1.3k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 819 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 asgeirtj/system_prompts_leaks at commit 60d44cc, republished under its CC0-1.0 licence (© asgeirtj). 819 words, ~1,303 tokens.

Download SKILL.mdSave it as .claude/skills/writing-style/SKILL.md (or your agent's skills folder).
name
writing-style
description
Draft or edit writing in the user's voice for the person who will read it and where it will appear. Use for messages, emails, documents or slides written on their behalf, not for your own replies.

Writing style

Write in the user's voice for the person who will read it. Use this skill when writing on their behalf. The user's dot's own replies follow the main prompt.

Find the right examples

  • Start with who will read it, what the user wants to say, and where it will appear. Read the latest relevant exchange. Look for the user's own recent writing to that person, in that channel, or for a similar purpose.
  • Choose the source that fits. Sent email can show how the user writes to a customer; Slack can show how they talk to a teammate; past memos or decks can show how they write for that audience. Check authorship. Quoted or forwarded text, shared-file ownership, templates, and generated text may belong to someone else. Don't infer a style from a person's job or background.
  • Compare a few good examples when available. Notice how they open, make requests, disagree, and sign off, and how they use punctuation, humor, and length. A note to a friend says little about how they write to a client. Examples on a different topic can still show the right voice.
  • The current request, a supplied style reference, and recent corrections come first. If you can't find examples, write naturally using what you know. Ask only if a missing fact or choice would materially change the result. Keep unrelated details from samples private.

Write the draft

  • Keep the user's meaning and the facts. Don't add promises, deadlines, feelings, or personal details they haven't expressed. Preserve dictated wording unless they ask for a rewrite; tidy punctuation or casing only when it doesn't change the meaning. For a small edit, leave the rest alone.
  • Make the point clear in familiar words. Remove generic pleasantries, forced jokes, flattery, and stock closings unless the user actually writes that way. Don't add em dashes, dramatic fragments, or formulaic contrasts to dress up a straightforward message.
  • Fit the medium and the relationship. A teammate's Slack reply may be one sentence; a difficult client email may need a brief acknowledgment, the facts, and a next step. Check that the draft answers the exchange and sounds like this user talking to this person. Put any explanation or question for the user outside the draft.
  • Follow preferences on where to display drafts to the user specific to the channel – for example make sure you add the draft in Gmail if the user has expressed a preference for that already
  • Proofread what you wrote and make sure it accomplishes the goals of the user and matches the writing style of the user. Avoid common AI writing tropes such as "It's not X, it's Y" or "An A is not a B", and "That doesn't mean J, K, or L. Those are what need to be verified next". After proofreading, improve the draft based on this writing-style skill guidance.
  • Follow <confirmation_policy> and the email or channel skill before saving or sending. A request for a draft doesn't authorize a send. When review is needed, show the recipient with the draft. If the approved wording or relevant facts change, ask before sending a changed version. Verify any native draft or send before claiming it happened.
  • Learn from the user's edits and explicit preferences. When working as a subagent, tell the main assistant what the user corrected or what they said they want reviewed. A one-time approval or silence doesn't establish standing permission.
Show full SKILL.md (251 more words)Show less

Examples

A teammate asks about a delay.
  • User: "Draft a Slack reply to Sam about why the project slipped."
  • Action: After checking the status and the user's messages to Sam,
  • Guidance: Don't add a deadline the user hasn't agreed to.
  • dot (draft): "Hey! Heads up that the export failed in QA. The rerun's still going, so we don't have a new date yet."
A friend did them a favor.
  • User: "Write a quick thank-you to Zoe for watching Milo."
  • Context: If their texts to Zoe are usually lowercase and use hearts,
  • Guidance: Don't invent a story to make it warmer.
  • dot (draft): "thank you again for watching Milo this weekend ❤️"
An executive update.
  • User: "Turn my rollout recommendation into a short update for the exec team."
  • Context: If the brief and test report support it,
  • Guidance: Use the structure the user normally uses with this audience.
  • dot (draft): "Recommendation: delay the rollout until Thursday. Payments still fails in 2 of 20 test accounts. Ana owns the rerun."
A sensitive note without style samples.
  • User: "Tell Maya I'm thinking of her after her dad died. Keep it simple."
  • Context: With no reliable examples,
  • Guidance: Show it privately; follow the email or channel guidance before sending.
  • dot (draft): "Maya, I'm so sorry about your dad. I'm thinking of you."
A small edit.
  • User: "Make 'Need this ASAP' less abrupt, but keep it short."
  • Guidance: Leave out any deadline the user didn't supply.
  • dot (draft): "Could you send this as soon as you can?"

© asgeirtj, 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

Just SKILL.md in OpenAI/dots/skills/writing-style of asgeirtj/system_prompts_leaks.

Open the folder on GitHubat commit 60d44cc

Compare with similar skills

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.

Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Style this skillasgeirtj/system_prompts_leaks69k—~1.3kAutomated safety check: PassCC0-1.0
Brand Voice Generatorcoleam00/second-brain-skills832—~2.5kAutomated safety check: PassNone
Reportmicrosoft/data-formulator18k—~1.5kAutomated safety check: PassMIT
Blog Cover Posterdigoal/blog8.6k—~1.4kAutomated safety check: PassGPL-2.0
Post AcceptanceGalaxy-Dawn/claude-scholar5.7k1 repos~1.5kAutomated safety check: PassMIT
Repurpose InstagramAgriciDaniel/claude-repurpose157—~1.7kAutomated safety check: PassMIT

Similar skills

  • Brand Voice Generator

    coleam00/second-brain-skills

    Generate tone-of-voice and brand-system files for use with the PPTX Generator and other brand-aware skills.

    832 GitHub stars~2.5k tokensUpdated 8 mo ago
    Writing & ContentAuto-check passed
  • Report

    microsoft/data-formulator

    Official

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded…

    18k GitHub stars~1.5k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Post Acceptance

    Galaxy-Dawn/claude-scholar

    This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter…

    5.7k GitHub starsUsed in 1 repo~1.5k tokens
    Writing & ContentAuto-check passed
  • Repurpose Instagram

    AgriciDaniel/claude-repurpose

    Generates Instagram content from content atoms: carousel slide scripts (7-10 slides), captions optimized for the 125-character fold, and reel scripts with hook-first structure.

    157 GitHub stars~1.7k tokensUpdated 6 mo ago
    Writing & ContentAuto-check passed
  • Repurpose Linkedin

    AgriciDaniel/claude-repurpose

    Generates LinkedIn content from content atoms: text posts with hook-first formatting, PDF carousel slide scripts (10-12 slides), and strategic polls.

    157 GitHub stars~1.6k tokensUpdated 6 mo ago
    Writing & ContentAuto-check passed

More from asgeirtj/system_prompts_leaks

All 125 skills in this repo
  • Fleet Manager for Agent Sessions

    asgeirtj/system_prompts_leaks

    Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.

    69k GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Muse Code Product Doctor

    asgeirtj/system_prompts_leaks

    Diagnoses a Muse Code installation's own failures from binary and session evidence, instead of treating the report as an ordinary repository bug.

    69k GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • DOCX

    asgeirtj/system_prompts_leaks

    A skill your agent uses whenever the user wants to create, read, edit, or manipulate Word documents (.docx) or Word templates (.dotx).

    69k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Agents Project Coordinator

    asgeirtj/system_prompts_leaks

    Runs a goal as a project in which the agent coordinates separate agent threads, judging when to split the work, and interviews you first when nothing can be verified.

    69k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Muse Plugin Creator

    asgeirtj/system_prompts_leaks

    Creates and validates a new native Muse plugin package in the current workspace, limited to five capability families, and leaves installation to you.

    69k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Deep Research

    asgeirtj/system_prompts_leaks

    A skill your agent uses when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or…

    69k GitHub stars~3.3k tokensUpdated today
    Auto-check passed

Questions about Writing Style

What does Writing Style do?

Draft or edit writing in the user's voice for the person who will read it and where it will appear. Writing Style is an agent skill from asgeirtj/system_prompts_leaks. Draft or edit writing in the user's voice for the person who will read it and where it will appear.

When should I use Writing Style?

Writing Style fits situations like: slides written on their behalf; not for your own replies.

How do I install Writing Style in Claude Code?

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

How do I install Writing Style in Codex?

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

Can I use 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 asgeirtj/system_prompts_leaks --skill 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/writing-style, .gemini/skills/writing-style, .github/skills/writing-style and .opencode/skills/writing-style in your project.

What does Writing Style need to run?

SKILL.md names no scripts, command-line tools or credentials: Writing Style is instructions for the agent only.

Does Writing Style access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is 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 Writing Style use?

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 Writing Style use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Writing Style?

Skills that share tags, products or a category with Writing Style: Brand Voice Generator (coleam00/second-brain-skills, 832 stars), Report (microsoft/data-formulator, 18k stars), Blog Cover Poster (digoal/blog, 8.6k stars) and Post Acceptance (Galaxy-Dawn/claude-scholar, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Style?

asgeirtj (a GitHub user) maintains it in asgeirtj/system_prompts_leaks, which has 69,280 GitHub stars. The repository holds 128 skills in this directory. The repository was last updated on October 10, 2026.

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