humanize

humanize is a skill for Claude Code from extrasmall0/dear-hiring-manager. It costs 71 tokens per session (519 once invoked), scanned A, original, MIT.

A writing guide for making generated text sound like a person wrote it. It sets rules for plain wording, punctuation, structure, and claims that stay grounded in the source material.

In plain words
What is it for?
Use it to revise application answers, cover letters, and other free-form writing so the language is direct, natural, and specific.
Why use it?
It removes common artificial-sounding phrases and patterns without adding unsupported facts. This makes open-ended answers and cover letters easier to read.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dear-hiring-manager plugin — 7 skills, 6 commands, 1 MCP server shipped together

Good fit Use it to revise application answers, cover letters, and other free-form writing so the language is direct, natural, and specific.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/extrasmall0/dear-hiring-manager/humanize
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 extrasmall0/dear-hiring-manager --skill humanize
Clone the repo
git clone --depth 1 https://github.com/extrasmall0/dear-hiring-manager

Made for: Claude Code.

Or install dear-hiring-manager, the plugin that ships this one along with the rest of its 7 skills, 6 commands, 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.

agentmods badge for humanize

README.md
[![agentmods](https://agentmods.dev/badge/skills/extrasmall0/dear-hiring-manager/humanize.svg)](https://agentmods.dev/skills/extrasmall0/dear-hiring-manager/humanize)
Your own site
<a href="https://agentmods.dev/skills/extrasmall0/dear-hiring-manager/humanize"><img src="https://agentmods.dev/badge/skills/extrasmall0/dear-hiring-manager/humanize.svg" alt="Measured on agentmods" 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 519 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.00519
Opus 5 $0.00036 $0.00260
Sonnet 5 $0.00014 $0.00104
Haiku 4.5 $0.00007 $0.00052

Measured 8d ago against content hash ead74c793bea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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.

skills/humanize/SKILL.md · 39 lines

What it actually says

Humanize

Apply to any free text we generate for the user: open-ended application answers ("Why this company?", custom essays) and cover letters. Goal: it reads like the candidate wrote it, plainly and specifically. Adapted from the public blader/humanizer rules.

Punctuation

  • No em-dashes or en-dashes (— –). Use a period, comma, or colon.
  • No parentheses for an aside or explanation. Rewrite it as a plain sentence or a comma clause.
  • Straight quotes, not curly. Don't over-use bold. No emoji. No inline mini-lists inside a prose answer.

Banned words / swaps

  • Drop: actually, additionally, furthermore, moreover, testament, landscape, showcasing, leverage, delve, robust, seamless, deeply, intricate, boasts.
  • Swap: "in order to" → "to"; "due to the fact that" → "because"; "serves as / features / boasts" → "is / has".
  • Cut hedging stacks: "could potentially possibly" → "may".
  • No clichés: "I'm passionate / excited…", "team player", "hit the ground running".

Structure to avoid

  • Negative parallelism: "it's not just X, it's Y".
  • Automatic rule-of-three lists — use the natural number of items.
  • Synonym cycling — repeat the clearest term instead of swapping synonyms.
  • False ranges ("from the Big Bang to dark matter") — name the things directly.
  • Manufactured drama / aphorisms ("Symmetry is the language of trust").
  • Signposting ("Let's dive in", "Here's what you need to know") and chatbot closers ("I hope this helps").
  • Fake candor ("Honestly? It depends…").
  • Hyphenated buzz-pairs when avoidable ("cross-functional", "data-driven").

Do

  • Be specific: real facts and numbers from the resume, not "experts believe".
  • Show what you did; don't summarize.
  • Vary sentence length — mix short and longer.
  • Use contractions. Sound like a person talking, not a press release.
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. 8d ago First seen · 39 lines · 71 tokens per session scan A ead74c793bea

Subscribe to this mod's changes

humanize is a skill published in the GitHub repository extrasmall0/dear-hiring-manager (107 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 519 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 2026-08-30.