agentmods.dev

human-copywrite

human-copywrite is a skill for Claude Code, Codex from pproenca/dot-skills. It costs 182 tokens per session (1,544 once invoked), scanned A, original, MIT.

Editorial guidance for writing text that people read, including interface text, documentation, release notes, and marketing copy.

In plain words
What is it for?
Use it to write or review buttons, error messages, guides, blog posts, onboarding text, and other user-facing content.
Why use it?
It helps keep wording clear, consistent, and free of unnecessary jargon across a product.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 205repo +4 24d ago A scan SkillSpector: pass 182 tokens original MIT

Good fit Use it to write or review buttons, error messages, guides, blog posts, onboarding text, and other user-facing content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pproenca/dot-skills/human-copywrite
View source ↗ pproenca/dot-skills
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 pproenca/dot-skills --skill human-copywrite
Clone the repo
git clone --depth 1 https://github.com/pproenca/dot-skills

Made for: Claude Code, Codex.

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-copywrite

README.md
[![agentmods](https://agentmods.dev/badge/skills/pproenca/dot-skills/human-copywrite/github.svg)](https://agentmods.dev/skills/pproenca/dot-skills/human-copywrite)
Your own site
<a href="https://agentmods.dev/skills/pproenca/dot-skills/human-copywrite"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/human-copywrite/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.

agentmods 80×15 button for human-copywrite

Your own site · 80×15
<a href="https://agentmods.dev/skills/pproenca/dot-skills/human-copywrite"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/human-copywrite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 182 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,544 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00182 $0.01544
Opus 5 $0.00091 $0.00772
Sonnet 5 $0.00036 $0.00309
Haiku 4.5 $0.00018 $0.00154

Measured 5d ago against content hash 4530a6d59ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

human-copywrite 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 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.

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/.experimental/human-copywrite/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human Copywrite

Editorial style and usage guidance distilled from the Apple Style Guide (June 2025). Use it whenever you're producing text a human will read.

When to Apply

Trigger this skill whenever the output is text a human will read. Specifically:

  • UI strings & error messages — button labels, dialog text, empty states, onboarding copy. Voice and UI-vocabulary rules apply.
  • User-facing documentation — help articles, READMEs, onboarding guides, tutorials. All rules apply.
  • Developer documentation — API references, SDK guides, code comments meant for humans. Add the technical-notation rules.
  • Marketing copy — feature announcements, landing pages, release notes. Voice, capitalization, and product-name rules are load-bearing.
  • Localized content — anything that will be translated. The international-style rules become primary.
  • Writing about Apple platforms — even if the surrounding product isn't an Apple product, refer to Apple hardware/software by Apple's preferred forms (iPhone, iPad, macOS, App Store).

If the user is writing code with no user-facing strings, skip this skill. If they're writing a function name or variable, that's not copywriting — that's naming, which lives elsewhere.

Core Principles

These run through every section. When in doubt, fall back on them.

  1. Active voice, present tense, second person. You can connect your iPhone to a Mac. Not Your iPhone may be connected to a Mac.
  2. Specific over generic. Choose File > Save. Not Use the menu to save the file.
  3. Plain words over jargon. Turn on over activate. Log in over authenticate (unless authenticate is technically precise).
  4. Don't make the product the subject of an action the user takes. You can create a database with FileMaker Pro. Not FileMaker Pro allows you to create a database.
  5. Items appear on screen — they don't display. The setup assistant appears. Not The setup assistant is displayed.
  6. Don't restate what code does — say why. Applies to code comments.
  7. Respect product names verbatim. AirPods (not Airpods), iCloud (not iCloud+ unless you mean the paid tier), Apple Pencil (not the Apple pencil).
  8. Numbers ≥10 stay digits; <10 spell out — but with many exceptions (numbers-and-dates.md).
  9. Compound modifiers preceding a noun are hyphenated; following the verb they're not — user-friendly app, the app is user friendly.
  10. In code, never use a function name as a verb. Run ls on both directories — not ls both directories.

Read the full file on GitHub · 70 lines

Files

What ships with it

17 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.

  1. 5d ago First seen · 70 lines · 182 tokens per session scan A 4530a6d59ec2

Subscribe to this mod's changes

human-copywrite is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 182 tokens to every session and 1,544 once invoked, about $0.0009 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 2026-09-03.

Writing and docs
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens