A rewriting procedure for making text sound more natural and less machine-written. It adjusts wording and style according to the requested type of writing and language.

Use it only when you explicitly want text humanized, such as an email, contract, announcement, or general prose.

It removes noticeable artificial phrasing while preserving the intended meaning and register.

humanize — Skill for Claude Code by marcoguillermaz

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.

Any agent

npx skills add marcoguillermaz/Tierward --skill humanize

Clone the repo

git clone --depth 1 https://github.com/marcoguillermaz/Tierward

Made for: Claude Code.

Or install tierward, the plugin that ships this one along with the rest of its 29 skills, 1 command, 1 hook, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marcoguillermaz/tierward/humanize/github.svg)](https://agentmods.dev/skills/marcoguillermaz/tierward/humanize)

Your own site

<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/humanize"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/humanize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/humanize"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,162 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.01162
Opus 5	$0.00036	$0.00581
Sonnet 5	$0.00014	$0.00232
Haiku 4.5	$0.00007	$0.00116

Measured 8d ago against content hash de38057b187f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

humanize scanned grade A with 0 findings 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 8d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/skills/humanize/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Humanize

Rewrites text to remove AI-generated patterns and produce natural, human-quality prose.

Input

The user provides text to humanize. They may also specify a domain:

email — transactional or relational email
contratto / contract — formal legal/contractual document
comunicazione / announcement — editorial content for an audience
generico / generic — default when no domain is specified

If no domain is stated, default to generico.

Process

Read the full input text.
If no AI patterns are detected and the text already reads naturally for its register, return the original text unchanged. Do not force edits on already-human writing.
Identify all patterns from @references/patterns-en.md and @references/patterns-it.md present in the text.
Apply transformations below, calibrated to the detected language (IT / EN / mixed).
Respect domain register: email = conversational; contratto = formal but not robotic; comunicazione = editorial voice; generico = match the surrounding register of the input.
For very short input (<50 words): apply only HIGH severity vocabulary rules and obvious opener removal. Skip sentence rhythm and structural rules — insufficient text for structural variation.

Transformation rules

Sentence rhythm

Break uniform sentence length. Vary between short (5-8 words) and long (20-30 words) sentences within the same paragraph.
Add at least one sentence fragment or rhetorical one-liner per 4-5 paragraphs if appropriate to register.
Dissolve the "topic sentence - evidence - conclusion" paragraph template wherever it appears mechanically.

Vocabulary substitution

Replace every word or phrase in the HIGH severity list in @references/patterns-en.md and @references/patterns-it.md.
Replace MEDIUM severity items when they cluster (3+ in the same paragraph).
LOW severity items: replace only if removing improves the sentence, otherwise leave.

Structure

Remove unsolicited "Challenges" sections. Integrate genuine limitations inline if they appear.
Remove "In conclusion / In summary / Overall / In conclusione" openers on final paragraphs. End by saying something specific, not by repeating the beginning.
Remove predictable five-part essay scaffolding. Preserve the content, not the scaffold.
Convert mechanical bullet-point lists to prose when the items are short and connected.

Read the full file on GitHub · 91 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 91 lines · 71 tokens per session scan A de38057b187f

Subscribe to this mod's changes

humanize is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,162 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Writing and docs ai-assisted-development ai-governance cli developer-tools nodejs

harness-engineering

Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.

paladini/harness-score · 55 tokens

codex-hud

Show Codex workspace context with local config, git state, hooks, and project hints. Standalone mode can show an expanded snapshot; patched Codex TUI footer mode is single-line. Use when the user says "codex-hud", "show Codex HUD", "status HUD", "workspace snapshot", or asks for richer Codex context.

brandonwie/codex-hud · 76 tokens

humanize