Writing Voice logo

Writing Voice

OrganizationPopular
EpicenterHQ
writing-voice

Shape prose so it sounds like Braden, with conversational precision, rhythm, humor, and earned poetic turns. Use for substantial drafting or revision, an ear pass, and explicit voice or tone work in prose, UI copy, documentation, or messages. Do not use to reopen wording selected for exact use.

Overview

PublisherEpicenterHQ
Repositoryepicenter
Skill namewriting-voice
Stars
4.8K
Forks
386
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Writing Voice 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/EpicenterHQ/epicenter/tree/main/.agents/skills/writing-voice
  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/EpicenterHQ/epicenter.git /tmp/epicenter
mkdir -p .claude/skills
cp -r /tmp/epicenter/.agents/skills/writing-voice .claude/skills/writing-voice
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Writing Voice 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 Voice 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 Voice 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 Voice

Help the writing carry recognizable judgment and recognizable sound. Write in language Braden could say to an articulate friend: clear, natural, and precise, with room for rhythm, wit, and surprise. Find phrasing that makes the thought felt as well as understood. Use this craft throughout drafting and revision; voice, structure, and meaning develop together.

Find The Expression

Conversational precision with a poetic turn is an ambition, not a formula for every paragraph. A turn earns its place by revealing a connection in the material. Try a sharper verb, an unexpected comparison, a changed rhythm, or a plainer sentence when it better carries the thought. Do not invent a motive, feeling, or event to give the prose depth, or substitute ornament for the particulars. Avoid explanations of what a thought signifies merely to make the paragraph sound complete; a polished summary can add no meaning while erasing its force.

Build from the author's actual phrases, not just a summary of their meaning. Keep the comparisons, ordinary words, asides, and emphatic turns that make the speaker recognizable; arrange and connect them before replacing them with equally accurate paraphrases. Roughness can carry emotion, humor, tension, uncertainty, or rhythm. “And then there's just a lot of Asian food” can earn its own paragraph without becoming an explanation of everyday cultural connection. Repair transcription errors and obstructive phrasing without treating every “actually,” “of course,” or repetition as noise. Neither roughness nor polish is a virtue by itself.

Choose the register from the piece's purpose and Braden's reactions. Preserve substantive qualifications while removing hesitation that belongs only to the act of dictation. Preserve the degree of conviction too: changing “I would argue” into “I wonder whether” can weaken the thought even when its subject stays the same. Do not strengthen real uncertainty into certainty either. A direct argument can present a position for examination without turning it into his personal belief. Personal writing can remain unresolved without narrating every step of the conversation that produced it.

Hear The Whole Passage

Writing for the ear is part of developing the piece. Listen for how the words carry the thought, giving that attention more weight when the work will be spoken aloud. An “ear pass” names this editorial focus, not a separate workflow. The active writing workflow, such as page-writing or journal-writing, continues to own the conversation and edits.

Read connected passages at speaking speed and judge each sentence with what surrounds it. The four ear tests below guide attention, not a report to fill out. Hear what the writing is doing, then judge it by what this piece needs.

When a reaction reveals a mismatch, rehear the passage under that correction and revise at the scope it illuminates. Use the destination's exploration workflow when contrasting expressions would help; an authorized direct edit needs no options menu. Reread the changed passage in context to hear whether its movement and the author's posture still belong together. After a whole-piece pass, check that the opening, strongest concrete detail, and ending still serve the same thought.

For work intended to be heard, read spoken destinations for the extra judgments a listener's experience requires. Ordinary editing does not impose a narration or social-video standard on every piece.

Economy

Identify what each sentence or paragraph contributes: a claim, example, turn, qualification, emphasis, or the experience of discovering the thought. Try the deletion test: would removing it preserve meaning, movement, and human posture? Look for throat-clearing, doubled qualifiers, repeated explanations, generic connections, or abstract nouns a concrete verb could replace. A sentence can earn its time through hesitation, humor, contrast, or rhythm as well as new information. Cut unearned time, not simply words.

Rhythm

Listen for long clauses, stacked abstractions, repeated openings, awkward mouth-feel, false starts, and phrasing whose predictability drains its force. Hear where a breath naturally belongs and where emphasis lands. Split a sentence when it helps the listener follow, not merely to create short lines. A pause or repetition may build pressure, preserve uncertainty, or make a joke land. Judge the words before trying to fix the delivery or timing.

Movement and progressive disclosure

Trace what the reader or listener encounters in order and what each turn needs. An argument may explain a mechanism, a scene may accumulate particulars, and a question may stay open. An early conclusion can orient the reader; a later one can let the example earn its force. Choose the order this expression needs without imposing suspense, a moral, or a changed meaning at the end.

Human recognition

Ask: “Could the author genuinely have brought this to another person?” Hear whether the concrete details, odd phrasing, humor, uncertainty, and degree of judgment still belong to the author. Remove polish that makes the passage more solemn, certain, universal, or professionally scripted than its intended expression. Recognition matters more than grammatical perfection; shaping the writing should keep the person audible, including in newly discovered language.

Respect The Form

A message, essay, button, and technical explanation have different jobs. Let those jobs shape length and register while keeping the person audible. Clarity does not require corporate scaffolding or false authority.

Use punctuation to make movement legible. Prefer periods. Use colons for a real explanation, semicolons for closely related independent clauses, and parentheses for genuine asides. Avoid en dashes; default away from em dashes except for a real interruption or high-emphasis aside.

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 Voice AI skill do?

Shape prose so it sounds like Braden, with conversational precision, rhythm, humor, and earned poetic turns. Use for substantial drafting or revision, an ear pass, and explicit voice or tone work in prose, UI copy, documentation, or messages. Do not use to reopen wording selected for exact use.

Why use Writing Voice on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/EpicenterHQ/epicenter/tree/main/.agents/skills/writing-voice. 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 Voice?

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 Voice?

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

Is the Writing Voice AI skill free?

It is published on GitHub by EpicenterHQ. Check the repository for licensing terms. 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 👇