Latex Rhythm Refiner logo

Latex Rhythm Refiner

Organization
appautomaton
latex-rhythm-refiner

Post-process LaTeX project prose to improve readability through varied sentence and paragraph lengths. Removes filler phrases and unnecessary transitions while preserving all citations and semantic meaning. Use after drafting is complete, when sections read as monotonous or blocky.

Overview

Publisherappautomaton
Repositorylatex-arxiv-SKILL
Skill namelatex-rhythm-refiner
Stars
467
Forks
39
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Latex Rhythm Refiner 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/appautomaton/latex-arxiv-SKILL/tree/main/.codex/skills/latex-rhythm-refiner
  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/appautomaton/latex-arxiv-SKILL.git /tmp/latex-arxiv-SKILL
mkdir -p .claude/skills
cp -r /tmp/latex-arxiv-SKILL/.codex/skills/latex-rhythm-refiner .claude/skills/latex-rhythm-refiner
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Latex Rhythm Refiner 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 Latex Rhythm Refiner 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 Latex Rhythm Refiner 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.

LaTeX Rhythm Refiner

When to Use

  • After LaTeX content generation is complete
  • To improve prose flow and readability in academic documents
  • When sections feel monotonous or blocky

When NOT to Use

  • During initial content drafting
  • For citation verification or addition
  • For technical/structural LaTeX fixes

Core Principles

1. Preserve Citations Exactly

  • Every \cite{...} must remain in place
  • Citations stay attached to their original semantic context
  • Never move a citation to a different claim or sentence meaning

2. Vary Rhythm Stochastically

Sentence length: Mix short (5-12 words), medium (13-22 words), and long (23-35 words) sentences. Avoid consecutive sentences of similar length.

Paragraph length: Alternate between:

  • Short (2-3 sentences) for emphasis or transitions
  • Medium (4-5 sentences) for standard exposition
  • Long (6-8 sentences) for complex arguments

3. Remove Fillers

Eliminate or replace:

  • "in order to" → "to"
  • "it is worth noting that" → (delete or rephrase directly)
  • "due to the fact that" → "because"
  • "in the context of" → "in" or "for"
  • "a large number of" → "many"
  • "in spite of the fact that" → "although"
  • "at the present time" → "now" or "currently"
  • "for the purpose of" → "to" or "for"

4. Minimize Transitions

Remove when structure already implies the relationship:

  • "However," / "Therefore," / "Moreover," / "Furthermore,"
  • "As mentioned above," / "As previously discussed,"
  • "It should be noted that" / "In this regard,"

5. Tighten Prose

  • Prefer active voice; replace vague verbs ("shows", "does", "works") with concrete ones
  • Replace mid-sentence em-dashes with commas, colons, or a new sentence
  • Use semicolons sparingly (at most one per paragraph as a rule of thumb)
  • Avoid repeated sentence openings across adjacent sentences ("This", "In practice", etc.)
  • Replace hedge stacks ("may potentially") with one qualifier
  • Each paragraph: one main idea, clear first sentence
  • Ensure figures/tables are referenced and explained in text

Processing Workflow

Per-Section Refinement

Process one section at a time:

  1. Read the section fully to understand context and argument flow
  2. Identify all \cite{...} locations and their attached claims
  3. Map current sentence/paragraph lengths
  4. Refine:
    • Vary sentence lengths (break long chains, combine choppy sequences)
    • Adjust paragraph boundaries for rhythm
    • Strip fillers and unnecessary transitions
  5. Verify all citations remain with their original semantic claims
  6. Output the refined section

Verification Checklist

Before finalizing each section:

  • Citation count unchanged
  • Each citation still supports its original claim
  • No 3+ consecutive sentences of similar length
  • Paragraph lengths vary
  • Filler phrases removed
  • Unnecessary transitions eliminated
  • Technical accuracy preserved

Constraints

  • Do not add, remove, or relocate citations
  • Do not change technical claims or data
  • Do not alter LaTeX commands, environments, or structure
  • Do not modify figure/table references or captions
  • Do not expand abbreviations or change terminology

Frequently asked questions

What does the Latex Rhythm Refiner AI skill do?

Post-process LaTeX project prose to improve readability through varied sentence and paragraph lengths. Removes filler phrases and unnecessary transitions while preserving all citations and semantic meaning. Use after drafting is complete, when sections read as monotonous or blocky.

Why use Latex Rhythm Refiner on TypingMind?

Because you install it once and use it with any model. Latex Rhythm Refiner 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 Latex Rhythm Refiner in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/appautomaton/latex-arxiv-SKILL/tree/main/.codex/skills/latex-rhythm-refiner. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Latex Rhythm Refiner?

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 Latex Rhythm Refiner?

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

Is the Latex Rhythm Refiner AI skill free?

Yes. It is published on GitHub by appautomaton 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 👇