Better Usage logo

Better Usage

Community
msimchowitz
better-usage

Diagnose and repair semantically mismatched word combinations while preserving the intended claim. Use when prose is grammatical but a verb does not literally fit its subject or object, a claim or section is given an action it cannot perform, an abstract relation is hidden by vague personification, an abstract process hides the actor or implies a review that the source does not establish, or replacing one verb still leaves a sloppy relation that needs an intermediate noun.

Overview

Publishermsimchowitz
Repositorywriting-skills
Skill namebetter-usage
Stars
67
Forks
4
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by msimchowitz on GitHub. Read the source before you install it.

Installation

Install the Better Usage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/msimchowitz/writing-skills/tree/main/for-agents/better-usage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/msimchowitz/writing-skills.git /tmp/writing-skills
mkdir -p .claude/skills
cp -r /tmp/writing-skills/for-agents/better-usage .claude/skills/better-usage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Better Usage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Better Usage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Better Usage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Better Usage

Choose words that express the relation the sentence actually asserts. A sentence can be grammatical and still sound wrong because its subject cannot perform the named action, its object or complement does not fit the relation expressed by the verb, or an important intermediate has been omitted.

For a full semantic-usage pass, read compatibility-examples.md. Treat the examples as a curated diagnostic set, not a substitution dictionary.

Recover The Intended Relation

  1. Identify the grammatical subject, main verb, and object or complement.
  2. Paraphrase the intended relation without reusing the suspect verb.
  3. Ask whether the subject can literally perform that action in this domain and whether the verb can take that object or complement with the intended meaning.
  4. Distinguish an accidental mismatch from accepted technical shorthand or a deliberate metaphor that clarifies the idea.
  5. Preserve the claim, uncertainty, and domain terminology while repairing the relation.
  6. Check whether the sentence implies a review, analysis, or evaluation that the source never established.

Do not stop after finding a more specific verb. A new verb can remain semantically loose.

Name A Missing Intermediate

When the subject and verb do not connect directly, identify the omitted link. Useful questions include:

  • What entity actually acts?
  • What property, extent, interpretation, or consequence changes?
  • Under which conditions does the relation hold?
  • Who performs the inference or needs the information?

For example, a claim does not stop, and saying that conditions "limit the claim" still leaves the affected dimension unnamed. Write "the conditions limit the extent of the claim" or state that "the claim applies only under these conditions." If the intended question concerns implications rather than validity, ask where the consequences of the theorem end.

Insert an intermediate only when it names a real part of the relation. Do not pile up abstract nouns merely to make the sentence sound exact.

Respect Conventional Agency

Keep established scholarly shorthand when it is clear in context. A theorem may state or imply a result, evidence may support a claim, a figure may show a measurement, and an algorithm may choose an action. These verbs have stable technical meanings.

Recast the sentence when the shorthand hides a distinction that matters. For example, "the evidence explains the effect" may collapse two relations: the evidence supports an explanation, while the authors or analysis provide it.

Check The Repair

  • Confirm that the revised subject can perform the verb.
  • Confirm that the object or complement fits the relation expressed by the verb.
  • Confirm that any intermediate noun identifies a necessary relation rather than adding nominal clutter.
  • Recheck epistemic force. Do not turn support into proof or correlation into explanation.
  • Remove an implied review or evaluation when the source states only a contrast between properties.
  • Compare with the source to ensure that the repair adds no fact, mechanism, condition, or conclusion.
  • Do not add procedural detail, sequence, or emphasis merely to replace a metaphor. A semantic repair does not license unsupported texture such as "step by step."

Invocation Boundary

When another writing skill invokes this skill, return only the revised prose or the requested usage findings. Do not invoke Humanizer, general-writing, or the writing-cadence or academic-voice skills; the calling skill owns the larger prose pipeline.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Better Usage AI skill do?

Diagnose and repair semantically mismatched word combinations while preserving the intended claim. Use when prose is grammatical but a verb does not literally fit its subject or object, a claim or section is given an action it cannot perform, an abstract relation is hidden by vague personification, an abstract process hides the actor or implies a review that the source does not establish, or replacing one verb still leaves a sloppy relation that needs an intermediate noun.

Why use Better Usage on TypingMind?

Because you install it once and use it with any model. Better Usage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Better Usage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/msimchowitz/writing-skills/tree/main/for-agents/better-usage. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Better Usage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Better Usage?

As many as you like. As long as a model supports skills, you can use Better Usage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Better Usage AI skill free?

Yes. It is published on GitHub by msimchowitz under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇