write-simply

Rewrites prose using Strunk's style rules and removes AI writing patterns from text.

9|Updated Jul 17, 2026
One-click install
npx skills add https://github.com/Yassimba/loom --skill write-simply-yassimba
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: write-simply
Source: https://github.com/Yassimba/loom/tree/main/skills/write-simply
Command: npx skills add https://github.com/Yassimba/loom --skill write-simply-yassimba

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Prose written or edited by AI assistants often sounds generic, padded, and machine-generated. This Skill applies Strunk's Elements of Style, ASD-STE100 Simplified Technical English, and Wikipedia's catalogue of AI writing patterns to produce clear, human-sounding text for docs, commit messages, error messages, UI text, and reports. ## Core Features & Use Cases - Style-guided writing and editing: Applies Strunk's rules of usage and composition (active voice, concrete language, omitted needless words) to paragraphs, docs, and explanations. - AI pattern removal (humanizer): Detects and fixes 35 catalogued AI writing patterns such as inflated importance, promotional tone, rule-of-three padding, em-dash overuse, and chatbot leakage, without changing facts or inventing details. - Compact technical register: Provides a shared register other skills invoke for docstrings, comments, commit messages, and captions. - Use Case: Paste a README draft that reads like ChatGPT wrote it; the Skill flags the AI patterns, rewrites each sentence in plain active prose, and returns the final text with a short list of remaining issues. ## Quick Start Use the write-simply skill to rewrite this paragraph so it sounds human and every word earns its place.

Frequently Asked Questions about write-simply

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make AI-generated text sound human?

Run the text through the humanizer reference, which checks it against 35 known AI writing patterns such as inflated importance, vague attribution, and formulaic conclusions. It rewrites each flagged sentence in plain active prose while keeping every original fact, name, and claim unchanged.

How to write clearer technical documentation and commit messages?

Apply the compact register based on ASD-STE100 Simplified Technical English: one idea per sentence, about 20 words or fewer, simple present tense, and imperatives for instructions. Strunk's composition rules add active voice, concrete language, and omission of needless words.

What are the signs that text was written by AI?

Common signs include overused words like delve, leverage, and seamless, superficial -ing phrases such as highlighting or underscoring, promotional adjectives, rule-of-three padding, boldface overuse, and chatbot leftovers like I hope this helps. The signs-of-ai-writing reference catalogues these with real examples.

Does rewriting text with this skill change the facts or meaning?

No. The rewrite process forbids adding or removing any fact, name, number, date, quote, or citation. If a sentence needs a missing detail, the skill asks for it or simplifies the sentence rather than inventing content.

When should I load the full set of style references versus one file?

Load a single reference file matched to the task, such as grammar fixes or word choice, for small edits like fixing a paragraph. Load the full pass of all references only for substantial new writing like drafting a README or when the user explicitly asks for a thorough edit.