Writing Cadence logo

Writing Cadence

Community
msimchowitz
writing-cadence

Diagnose and revise prose with staccato runs, uniform sentence lengths, repeated openings, mechanical clause structures, repeated contrast formulas, or abstract process framing that hides the actor and delays the real comparison. Use for requests about cadence, rhythm, meter, sentence variety, choppy prose, monotonous prose, or patterns such as "not X but Y" and "treats X as Y, not Z."

Overview

Publishermsimchowitz
Repositorywriting-skills
Skill namewriting-cadence
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 Writing Cadence 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/writing-cadence
  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/writing-cadence .claude/skills/writing-cadence
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Writing Cadence 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 Writing Cadence 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 Writing Cadence 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.

Writing Cadence

Shape rhythm around meaning and emphasis. Preserve every supported claim, qualification, citation, and recognizable voice signal. Sentence variety is a result of clear relationships, not a target sequence of short and long lines.

Read cadence-principles.md when the task requires a full cadence edit or an explanation of the underlying principles.

Diagnose The Passage

Read at paragraph scale before changing individual sentences. Mark:

  • runs of three or more sentences of roughly ten words or fewer;
  • several neighboring sentences with similar lengths;
  • repeated openings, especially "This," "The," "It," "We," or the same dependent-clause frame;
  • repeated subject-verb-complement skeletons;
  • abstract process nouns such as "review," "analysis," or "evaluation" that hide the actor or imply an event the source never established;
  • long sentences that contain more than one main inference;
  • long gaps between a grammatical subject and its verb;
  • endings that place routine setup after the important result; and
  • paragraphs whose final sentence merely restates the topic, shifts to housekeeping, or adds a vague conclusion; and
  • paragraph breaks that conceal the same rhythm on both sides.

Treat these as diagnostics. A run may be deliberate, and a technical passage may need repeated syntax for a fixed taxonomy or proof. Compare the pattern with the writer's sample and the genre before revising it.

Scan Repeated Contrast Frames

Mark every contrast built from a reusable difference template, including:

  • "not X but Y" and "not only X but also Y";
  • "This is not X. It is Y.";
  • "X, not Y" used as a sentence-ending correction;
  • "treats X as Y, not Z";
  • "treats X like Y rather than Z";
  • "rather than merely X, Y";
  • repeated "unlike X, Y" openings; and
  • several neighboring sentences built around "while," "whereas," or "in contrast."

Keep a contrast when the distinction limits a scientific claim or separates two mechanisms. Revise repeated templates by stating the positive claim, naming the governing comparison once, or distributing the distinction across different sentence structures. Do not erase a meaningful negative result.

Rebuild Rhythm From Relationships

  1. Identify the point that deserves emphasis in each sentence and paragraph.
  2. Link backward near the opening with the subject, condition, or established context that the reader already knows.
  3. Keep the subject near its verb unless an intervening phrase is truly secondary.
  4. Name the actor when an abstract process hides who acts. If no review, analysis, or evaluation occurred, state the actual contrast between properties directly.
  5. Place the important new result near syntactic closure when that ordering matches the logic.
  6. Join short neighboring sentences when one supplies the other's cause, condition, contrast, or consequence.
  7. Split a long sentence when it makes two independent claims, changes subjects repeatedly, or postpones the governing verb.
  8. Vary openings only when the new opening changes emphasis or improves the link to the previous sentence.
  9. Reserve a very short sentence for a conclusion that merits the pause.

Do not alternate lengths mechanically, add fragments for texture, or move a modifier merely to avoid repetition. These changes produce visible variety without improving the reading experience.

Let Paragraphs End Where The Reasoning Arrives

Identify the paragraph's intellectual destination before revising its last sentence. A supported consequence, a condition that limits the claim, an unresolved tension, or a concrete fact can provide natural closure. A transition may also end quietly when the next paragraph supplies the consequence.

Do not append a summary, slogan, generic implication, or sentence about the document merely because the paragraph seems to need a conclusion. If the penultimate sentence already completes the thought, cut the weaker ending. If the important point appears earlier, reorder the paragraph instead of writing a more emphatic final line. Audit abstracts, section openings, and section closings separately because readers assign those positions additional weight.

Read At Speaking Pace

Read the revision aloud or at a deliberate speaking pace. Check where a reader naturally pauses, which words receive stress, and whether syntactic closure lands on the intended information. Rework any passage that:

  • requires the same breath pattern several times in a row;
  • gives equal emphasis to claims of unequal importance;
  • makes the reader wait too long for the main verb;
  • ends several sentences with the same grammatical shape; or
  • repeatedly closes paragraphs with a miniature summary or slogan; or
  • sounds varied on a sentence-length count but monotonous aloud.

Compare the revision with the source once more. Restore any technical distinction, uncertainty, or personal cadence lost during restructuring.

Invocation Boundary

When another skill invokes this one, return only the revised prose or cadence findings requested by the caller. Do not invoke Humanizer, general-writing, better-usage, or academic-voice from this skill; Humanizer owns the integration so the shared writing pipeline does not cycle.

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 Writing Cadence AI skill do?

Diagnose and revise prose with staccato runs, uniform sentence lengths, repeated openings, mechanical clause structures, repeated contrast formulas, or abstract process framing that hides the actor and delays the real comparison. Use for requests about cadence, rhythm, meter, sentence variety, choppy prose, monotonous prose, or patterns such as "not X but Y" and "treats X as Y, not Z."

Why use Writing Cadence on TypingMind?

Because you install it once and use it with any model. Writing Cadence 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 Writing Cadence in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/msimchowitz/writing-skills/tree/main/for-agents/writing-cadence. 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 Writing Cadence?

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 Writing Cadence?

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

Is the Writing Cadence 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 👇