Lathe Voice logo

Lathe Voice

CommunityPopular
devenjarvis
lathe-voice

Author a custom writing voice for Lathe tutorials, in session, then persist it via the CLI. Use when the user invokes /lathe-voice (optionally with a name like "/lathe-voice terse") to craft a new tone/register preset that /lathe can generate in.

Overview

Publisherdevenjarvis
Repositorylathe
Skill namelathe-voice
Stars
1.7K
Forks
49
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 devenjarvis on GitHub. Read the source before you install it.

Installation

Install the Lathe 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.
  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/devenjarvis/lathe.git /tmp/lathe
mkdir -p .claude/skills
cp -r /tmp/lathe/internal/skills/data/lathe-voice .claude/skills/lathe-voice
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lathe 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 Lathe 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 Lathe 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.

Lathe — Author a Voice

Help the user craft a custom writing voice — a tone/register preset that /lathe and /lathe-extend can generate tutorials in — then persist it through the CLI. Triggered by /lathe-voice [name].

A voice controls tone and register only. It never changes accuracy, research, citation, verification, substance, pedagogy, or structure — those are fixed invariants in the lathe skill, and every voice is wrapped at read time with a preamble that says so. You are authoring how the prose sounds, nothing more.

What a voice is (and what it is not)

Look at the built-ins for the exact shape before you draft — they are the template:

bash
lathe voice show plainspoken     # the honest, non-anthropomorphic default
lathe voice show companion       # the warm, first-person original
lathe voice list                 # everything currently available

A voice spec is a small markdown file with name:/description: frontmatter and three working sections:

  • Stance and register — persona, point of view, sentence rhythm, how the reader is addressed, the first-person policy, humor.
  • Avoid — the tonal anti-patterns this voice rejects.
  • Calibration — before / after — two or three ❌/✅ pairs showing the voice's tone (not pedagogy; the pedagogy before/afters live in the lathe skill).

Refuse to author these (deception guardrail)

Decline, and explain why, if the request is to make a voice that:

  • Impersonates a real, named person ("write exactly like <specific living author/engineer>", or as a named public figure) or implies their endorsement. A register inspired by a tradition is fine ("plain, in the spirit of good systems writing"); writing as a specific real person is not.
  • Fabricates credentials or authority — a voice that claims real-world experience, institutions, or qualifications the author doesn't have, or that presents invented anecdotes as things that actually happened. (A voice may use first person as a stance, like companion, but it must not manufacture a fake résumé.)
  • Denies LLM authorship or is built to pass the tutorial off as human-written.
  • Is coercive or deceptive — manipulative urgency, dark patterns, dishonesty toward the reader.

These aren't negotiable: the wrap preamble and the lathe invariants would override such instructions at generation time anyway, so a voice that depends on them is dead on arrival. Steer the user to an honest version of what they want.

Protocol

  1. Pick the name. Use the /lathe-voice <name> argument if given; otherwise ask for a short, lowercase slug (e.g. terse, socratic, field-notes). It must not collide with a built-in (plainspoken, companion) — lathe voice add will reject that, so check lathe voice list first.

  2. Interview the user. Ask, briefly (one round, grouped — don't interrogate):

    • Register: formal ↔ casual? dense ↔ spacious? dry ↔ warm?
    • Person: first person ("I"), collaborative ("we"), or impersonal? If first person, is it a stance (opinions) or are they hoping for fabricated experience? (If the latter, redirect per the guardrail.)
    • Humor: none, dry/sparing, or playful? Never at the reader's expense.
    • Anti-patterns: what should this voice never sound like? (Pull concrete words/phrases to feed the Avoid list.)
  3. Draft the spec. Write it in the built-in structure: frontmatter (name, a one-line description), # <Title>, ## Stance and register, ## Avoid, and ## Calibration — before / after with two or three ❌/✅ tone pairs. Keep it tonal — don't restate accuracy/structure rules; those are invariants.

  4. Show it and confirm. Print the full draft to the user. Iterate until they approve. Don't persist anything unapproved.

  5. Persist via the CLI. On approval, pipe the spec to:

    bash
    lathe voice add <name> --file -

    (The skill writes no files itself — the CLI owns ~/.lathe/voices/. --file - reads the spec from stdin.) If it errors on a built-in collision, pick another name and retry.

  6. Tell the user how to use it:

    • Generate in it now: /lathe <topic> and name the voice ("…in the <name> voice"), or make it the default with lathe voice set-default <name>.
    • Inspect or remove it later: lathe voice show <name> / lathe voice rm <name>.

Boundaries

  • The only durable-state write is lathe voice add (and, if the user asks, lathe voice set-default / lathe voice rm). Never write to ~/.lathe/ directly.
  • Author tone only. If the user wants to change pedagogy, structure, or accuracy behavior, that's a change to the lathe skill, not a voice — say so.

Frequently asked questions

What does the Lathe Voice AI skill do?

Author a custom writing voice for Lathe tutorials, in session, then persist it via the CLI. Use when the user invokes /lathe-voice (optionally with a name like "/lathe-voice terse") to craft a new tone/register preset that /lathe can generate in.

Why use Lathe Voice on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devenjarvis/lathe/tree/main/internal/skills/data/lathe-voice. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Lathe 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 Lathe Voice?

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

Is the Lathe Voice AI skill free?

Yes. It is published on GitHub by devenjarvis 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 👇