Lathe Verify logo

Lathe Verify

CommunityPopular
devenjarvis
lathe-verify

Verify that a stored Lathe tutorial actually works by following it end to end in a fresh scratch dir, in session. Use when the user invokes /lathe-verify with a slug like "/lathe-verify digital-synth-zig" (the "Verify this tutorial" button in `lathe serve` hands you that command).

Overview

Publisherdevenjarvis
Repositorylathe
Skill namelathe-verify
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 Verify 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-verify .claude/skills/lathe-verify
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lathe Verify 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 Verify 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 Verify 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 — Verify a Tutorial

Follow a stored tutorial exactly as a reader would, in a throwaway directory, and record whether it actually works. Triggered by /lathe-verify <slug>. Isolation is by instruction — a fresh mktemp -d, under the user's normal interactive permissions. No sandbox-exec, no Docker.

This skill is read-only with respect to the tutorial: never edit the parts or the metadata. The only writes are status updates through lathe verify-result.

Protocol

  1. Mark it in-flight first:

    bash
    lathe verify-result <slug> --status verifying

    This sets the spinner badge in the web UI. If it errors with "cannot verify while it is extending", stop — a part is mid-flight; don't verify on top of it.

  2. Make a fresh scratch dir and work there:

    bash
    cd "$(mktemp -d)"

    Everything the tutorial tells the reader to create happens here, not in the user's project. (Status is set by this skill, never by the web/CLI button — so an unclicked button can never strand a tutorial at verifying.)

  3. Follow each part in order. Read ~/.lathe/tutorials/<slug>/part-NN.md from part-01 up. Install the prerequisites, create the files and paste the code blocks exactly as written, in order, then run the ## Checkpoint command and compare against the stated expected output.

    • Skip the pedagogical and provenance callouts> [!PREDICT], > [!RECALL], and > [!UNVERIFIED] are not verifiable steps. They prompt the reader or flag uncertainty; there's nothing to execute.
    • Treat the Checkpoint commands and code blocks as the executable surface.
  4. Record the terminal result with the matching command:

    • Everything workslathe verify-result <slug> --status verified
    • A required tool isn't installedlathe verify-result <slug> --status skipped This is not a failure — it's the ⚠️ Skipped badge, meaning "couldn't run it here," not "the tutorial is wrong." Use it whenever the toolchain the tutorial needs (compiler, runtime, SDK) is missing locally.
    • Something genuinely breaks (wrong output, code doesn't compile, a step contradicts itself) →
      bash
      lathe verify-result <slug> --status failed \
        --part <part-NN.md> \
        --failed-step <1-indexed step number within that part> \
        --error "<the error message or mismatched output>"
  5. Report to the user what happened — verified clean, skipped (and which tool was missing), or where exactly it failed.

Boundaries

  • Read-only on the tutorial. Never edit a part-NN.md, metadata.json, or verify-result.json directly — the only state writes are via lathe verify-result.
  • No OS sandboxing. Isolation is the mktemp -d scratch dir plus instruction, under the user's normal permission model. Don't reach for sandbox-exec or Docker.
  • Skipped ≠ failed. A missing toolchain is skipped. Reserve failed for the tutorial being genuinely broken.
  • Status is always set by this skill, never by the handoff button.

Frequently asked questions

What does the Lathe Verify AI skill do?

Verify that a stored Lathe tutorial actually works by following it end to end in a fresh scratch dir, in session. Use when the user invokes /lathe-verify with a slug like "/lathe-verify digital-synth-zig" (the "Verify this tutorial" button in `lathe serve` hands you that command).

Why use Lathe Verify on TypingMind?

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

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

Which AI models can use Lathe Verify?

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 Verify?

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

Is the Lathe Verify 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 👇