human-writing-style

human-writing-style is a skill for Claude Code, Codex from LFTPadilla/agent-dev-kit. It costs 26 tokens per session (583 once invoked), scanned B, original, MIT.

A writing guide for producing direct, natural, practical text. It defines sentence, voice, formatting, and word-choice rules.

In plain words
What is it for?
Use it when writing instructions, documentation, messages, or other text that should be short, clear, and human.
Why use it?
It helps remove robotic, vague, overly formal, or promotional wording from written output.

Skill for Claude CodeCodex

Part of the dev-skills plugin — 24 skills, 1 command 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/lftpadilla/agent-dev-kit/human-writing-style
Any agent
npx skills add LFTPadilla/agent-dev-kit --skill human-writing-style
Clone the repo
git clone --depth 1 https://github.com/LFTPadilla/agent-dev-kit

Made for: Claude Code, Codex.

Or install dev-skills, the plugin that ships this one along with the rest of its 24 skills, 1 command.

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 human-writing-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/human-writing-style.svg)](https://agentmods.dev/skills/lftpadilla/agent-dev-kit/human-writing-style)
Your own site
<a href="https://agentmods.dev/skills/lftpadilla/agent-dev-kit/human-writing-style"><img src="https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/human-writing-style.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 583 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00026 $0.00583
Opus 5 $0.00013 $0.00292
Sonnet 5 $0.00005 $0.00117
Haiku 4.5 $0.00003 $0.00058

Measured 5d ago against content hash 3f0f05179580, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

human-writing-style scanned grade B with 1 finding 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 5d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

14. Do not add warnings or notes at the end.
plugins/dev-skills/skills/human-writing-style/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human Writing Style Skill

Use this skill when the user asks for writing that sounds more human, natural, direct, or less robotic.

Core Goal

Write like a clear human, not like marketing copy and not like corporate AI filler.

Mandatory Rules

  1. Use clear and simple language.
  2. Be direct and informative.
  3. Use short, strong sentences.
  4. Use active voice. Avoid passive voice.
  5. Focus on practical, actionable ideas.
  6. For social media posts, use bullet lists.
  7. Use facts, numbers, and examples when they help support a claim.
  8. Address the reader as "tu" when writing in Spanish.
  9. Do not use dashes. Use commas, periods, or colons instead.
  10. Do not use constructions like "no solo X, sino Y" or "no solo esto".
  11. Avoid metaphors and clichés.
  12. Avoid vague generalizations.
  13. Do not end with closing formulas such as "en conclusión", "para cerrar", or "en resumen".
  14. Do not add warnings or notes at the end.
  15. Avoid unnecessary adjectives.
  16. Do not use hashtags.
  17. Do not use semicolons.
  18. Do not use markdown.
  19. Do not use asterisks.

Banned Words and Phrases

Do not use these words or phrases unless the user explicitly asks for them in quoted text:

poder quizás solo realmente literalmente ciertamente probablemente básicamente recordar significativamente transformar estimado arrojar luz límites potenciar desafío peligro desbloquear descubrir dispararse revolucionar disruptivo pionero innovador iluminar revelar vibrante vital crucial además ámbito sin embargo aprovechar navegar paisaje notable testimonio en resumen en conclusión abrió paso poderoso inquietudes en constante evolución

Final Check Before Sending

Review the full response and confirm:

  1. There are no dashes.
  2. There are no semicolons.
  3. There are no hashtags.
  4. There are no asterisks.
  5. None of the banned words or phrases appear unless quoted on purpose.
  6. The writing is direct, practical, and specific.

Default Behavior

If the user does not ask for another style, prefer this style for drafting, rewriting, social posts, and advice writing tasks.

Read the full file on GitHub · 99 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. 5d ago First seen · 99 lines · 26 tokens per session scan B 3f0f05179580

Subscribe to this mod's changes

human-writing-style is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 583 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

edgeone skill scanner

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…

Tencent/AI-Infra-Guard · 148 tokens

avoid-ai-writing

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…

conorbronsdon/avoid-ai-writing · 97 tokens

ai-writing-detector

Use when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local detector result when the host can execute Node.

conorbronsdon/avoid-ai-writing · 44 tokens

preservation-verifier

Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code, frontmatter, quotes, tables, links, paths, numbers, headings, and residual AI-pattern regressions.

conorbronsdon/avoid-ai-writing · 54 tokens

avoid-ai-writing-router

Use when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation, verification, or when the user invokes Avoid AI Writing without naming a mode.

conorbronsdon/avoid-ai-writing · 41 tokens

voice-preserving-rewriter

Use when the user asks to rewrite, humanize, clean up, or remove AI-isms from text while preserving the writer's voice, facts, intent, structure, register, and protected material.

conorbronsdon/avoid-ai-writing · 46 tokens