Agent skill

Lathe Extend

by devenjarvis in devenjarvis/lathe

Write the next part of an existing Lathe tutorial, in session.

MITAuto-check passed

Install Lathe Extend

skills CLI
$ npx skills add devenjarvis/lathe --skill lathe-extend -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install devenjarvis/lathe lathe-extend --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/devenjarvis/lathe.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/lathe-extend .claude/skills/lathe-extend && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lathe-extend
GitHub stars
1.7k
Token cost
~1.4k tokens
SKILL.md length
752 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Write the next part of an existing Lathe tutorial, in session.

  • Works in 6 steps: Absorb the existing tutorial. Read every… → Research first. Same discipline as the… → Reserve the part. Run → …
  • Optionally followed by guidance for where the part should go
  • SKILL.md covers Protocol, Boundaries and Stay in session
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Lathe Extend is an agent skill from devenjarvis/lathe. Write the next part of an existing Lathe tutorial, in session. Use when the user invokes /lathe-extend with a slug like "/lathe-extend digital-synth-zig" (the "Add a new part" button in lathe serve hands you that command), optionally followed by guidance for where the part should go.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋. The licence is MIT.

When your agent uses it

  • Optionally followed by guidance for where the part should go

Example prompts

  • “/lathe-extend digital-synth-zig”
  • “Add a new part”
  • “/lathe-extend”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Absorb the existing tutorial. Read every part in ~/.lathe/tutorials// (part-NN.md). You need the load-bearing context before you write a…
  2. Research first. Same discipline as the lathe skill's "Research first" step: actually open 3–8 authoritative sources for whatever this new…
  3. Reserve the part. Run
  4. Write the part to ~/.lathe/tutorials//.
  5. Commit the part. Run
  6. Tell the user it's added: how to view it (lathe serve), and that verification is opt-in (/lathe-verify — the "Verify this tutorial" button…

What it can do on your machine

Read from SKILL.md and the folder at commit 1e7c9f6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lathe Extend loads about 1.4k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 752 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from devenjarvis/lathe at commit 1e7c9f6, republished under its MIT licence (© devenjarvis). 752 words, ~1,401 tokens.

Download SKILL.mdSave it as .claude/skills/lathe-extend/SKILL.md (or your agent's skills folder).
name
lathe-extend
description
Write the next part of an existing Lathe tutorial, in session. Use when the user invokes /lathe-extend with a slug like "/lathe-extend digital-synth-zig" (the "Add a new part" button in `lathe serve` hands you that command), optionally followed by guidance for where the part should go.

Lathe — Extend a Tutorial

Add the next part to a stored tutorial. Triggered by /lathe-extend <slug> [guidance…]. The new part must continue that tutorial — its example, its numbers, its voice — not a fresh generic one. Everything about shape, research discipline, and callouts comes from the lathe skill; read it and apply it. The voice is whatever the tutorial was generated in — fetch it from the CLI (see step 1), don't guess or re-pick. This skill only adds what's different about extending: continuity and the extend-start → write → extend-commit handshake.

Protocol

  1. Absorb the existing tutorial. Read every part in ~/.lathe/tutorials/<slug>/ (part-NN.md). You need the load-bearing context before you write a word:

    • The controlling example and the fixed numbers (sample rate, page size, buffer size) — reuse them exactly; don't invent new ones.
    • The controlling metaphor, if any, and whether a prior part already retired it (if retired, don't resurrect it).
    • The voice. Fetch the tutorial's recorded voice and apply it for all tonal choices:
      bash
      lathe voice show --tutorial <slug>
      This prints the wrapped voice spec (guardrail preamble + tone guidance). It resolves the voice recorded on the tutorial's metadata, falling back to the configured default for tutorials stored before voices existed. Don't re-pick or drift the voice; structure and substance still defer to the lathe skill, which wins on any conflict with the voice.
    • The level of the reader.
    • The repo and pinned tool versions in metadata.json (repo, repo_branch, tools) — the new part inherits them. Write against the same versions; don't silently bump to a newer toolchain. (If the reader explicitly wants to move the tutorial to a new version, that's a heads-up that it may be time for a fresh tutorial, not a quiet drift — flag it rather than re-pinning here.)
    • Where the previous part's "What's next" pointed — that's your mandate for this part unless the user's guidance redirects it.
  2. Research first. Same discipline as the lathe skill's "Research first" step: actually open 3–8 authoritative sources for whatever this new part introduces, take notes with URLs beside the load-bearing facts, and ground or [!UNVERIFIED]-flag every load-bearing claim. New material gets the same scrutiny as Part 1 did. No web access? Say so in one line and write conservatively, flagging the load-bearing unknowns.

  3. Reserve the part. Run:

    bash
    lathe extend-start <slug>

    It prints a single filename (e.g. part-02.md) and sets status extending. Capture that exact filename. If it errors with "already extending or verifying", stop and tell the user — something is mid-flight; don't force it.

  4. Write the part to ~/.lathe/tutorials/<slug>/<printed-filename>.

    • This is the one allowed content write. The skill writes the part markdown directly into the tutorial dir at the reserved path — that is required and deliberate, because lathe extend-commit os.Stats the file there before registering it. (Future reader: don't "fix" this by routing it through a CLI command. There is no such command; the binary owns metadata, the skill writes the part body.)
    • Follow the full Tutorial shape from the lathe skill — hook, ## What you'll build, prerequisites, specific section titles, ## Checkpoint, ## What's next, ## Exercises, ## Sources. Each part stands alone and ends with a Checkpoint.
    • Because this is Part N ≥ 2, open with a > [!RECALL] spaced-retrieval beat: one question on a load-bearing concept from a prior part, phrased so the reader must reconstruct the answer (not just recognize it). See the lathe skill's recall before/after.
    • One file, this part only. Don't write index.md, don't touch earlier parts, don't write more than one part.
  5. Commit the part. Run:

    bash
    lathe extend-commit <slug> <printed-filename> [--source <url> …] --model "<model you are running as>"

    Pass --source once for each source you newly consulted for this part — it folds them into the tutorial's research trail (de-duped). Pass --model with the model you are running as (e.g. --model "Claude Opus 4.8") so the reading-page byline reflects who wrote the latest part (last-writer-wins; omit it only to leave the existing label untouched). This registers the part, clears the pending marker, and resets status to unverified.

  6. Tell the user it's added: how to view it (lathe serve), and that verification is opt-in (/lathe-verify <slug> — the "Verify this tutorial" button hands you that command). Then stay in session for follow-ups.

Show full SKILL.md (75 more words)Show less

Boundaries

  • The only durable-state writes are lathe extend-start and lathe extend-commit. Never edit metadata.json directly.
  • Writing the reserved part-content file into the tutorial dir is the sole content write — and it's required (step 4).
  • Don't verify, don't write index.md, don't write multiple parts, don't edit existing parts.

Stay in session

You're still their expert guide. Stay available for "make this part harder", "why did we structure it this way", "how'd I do on the checkpoint".

© devenjarvis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/lathe-extend of devenjarvis/lathe.

Open the folder on GitHubat commit 1e7c9f6

Compare with similar skills

Lathe Extend next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lathe Extend compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lathe Extend this skilldevenjarvis/lathe1.7k—~1.4kAutomated safety check: PassMIT
TutorialQ00/ouroboros6.2k—~1.6kAutomated safety check: PassMIT
Tutorial Engineersickn33/agentic-awesome-skills47k2 repos~4.1kAutomated safety check: PassMIT
Technical Tutorialssickn33/agentic-awesome-skills47k1 repos~770Automated safety check: PassMIT
Step Partsearthtojake/text-to-cad19k1 repos~1.5kAutomated safety check: PassMIT
Canopy Part Title Blockheygen-com/hyperframes60k1 repos~1kAutomated safety check: PassApache-2.0

Similar skills

  • Tutorial

    Q00/ouroboros

    Interactive tutorial teaching Ouroboros hands-on. An agent skill from Q00/ouroboros.

    6.2k GitHub stars~1.6k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Tutorial Engineer

    sickn33/agentic-awesome-skills

    Creates step-by-step tutorials and educational content from code.

    47k GitHub starsUsed in 2 repos~4.1k tokens
    EducationAuto-check passed
  • Technical Tutorials

    sickn33/agentic-awesome-skills

    When the user wants to create step-by-step technical tutorials, quickstarts, or code walkthroughs.

    47k GitHub starsUsed in 1 repo~770 tokens
    Writing & ContentAuto-check passed
  • Step Parts

    earthtojake/text-to-cad

    Find, evaluate, and download common purchasable CAD parts from step.parts, including named off-the-shelf actuators, servos, motors, electronics boards, connectors, screws, bolts, nuts, washers…

    19k GitHub starsUsed in 1 repo~1.5k tokens
    Backend & APIsAuto-check passed
  • Canopy Part Title Block

    heygen-com/hyperframes

    A HyperFrames video block in which a canopy of leaves sweeps across the frame and parts to reveal two headlines, rendered at 1920×1080 for 12 seconds.

    60k GitHub starsUsed in 1 repo~1k tokens
    Media & CreativeAuto-check passed
  • Tutorial

    agenticnotetaking/arscontexta

    Interactive walkthrough for new users. An agent skill from agenticnotetaking/arscontexta.

    3.5k GitHub stars~4.8k tokensUpdated 7 mo ago
    Auto-check: notes

More from devenjarvis/lathe

  • Lathe Ask

    devenjarvis/lathe

    Answer a reader's question about a specific part of a Lathe tutorial, in session.

    1.7k GitHub stars~532 tokensUpdated 2 mo ago
    Auto-check passed
  • Lathe Tag

    devenjarvis/lathe

    Pick or backfill the search tags on a stored Lathe tutorial, in session.

    1.7k GitHub stars~466 tokensUpdated 2 mo ago
    Auto-check passed
  • Lathe Verify

    devenjarvis/lathe

    Verify that a stored Lathe tutorial actually works by following it end to end in a fresh scratch dir, in session.

    1.7k GitHub stars~844 tokensUpdated 2 mo ago
    Auto-check passed
  • Lathe Voice

    devenjarvis/lathe

    Author a custom writing voice for Lathe tutorials, in session, then persist it via the CLI.

    1.7k GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Lathe Work

    devenjarvis/lathe

    Run the Lathe worker loop so the web UI's Ask / Verify / Add-a-part buttons drive work directly in this session instead of handing back a command to paste.

    1.7k GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Lathe

    devenjarvis/lathe

    Generate hands-on technical tutorials for any topic on demand.

    1.7k GitHub stars~7.2k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Lathe Extend

What does Lathe Extend do?

Write the next part of an existing Lathe tutorial, in session. Lathe Extend is an agent skill from devenjarvis/lathe. Write the next part of an existing Lathe tutorial, in session.

When should I use Lathe Extend?

Lathe Extend fits situations like: optionally followed by guidance for where the part should go.

How do I install Lathe Extend in Claude Code?

Run `npx skills add devenjarvis/lathe --skill lathe-extend -a claude-code`. Or copy the skill folder (.claude/skills/lathe-extend in devenjarvis/lathe) into .claude/skills/lathe-extend in your project. Claude Code loads it when a task matches its description.

How do I install Lathe Extend in Codex?

Run `npx skills add devenjarvis/lathe --skill lathe-extend -a codex`. Or copy the skill folder (.claude/skills/lathe-extend in devenjarvis/lathe) into .agents/skills/lathe-extend in your project. Codex loads it when a task matches its description.

Can I use Lathe Extend in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add devenjarvis/lathe --skill lathe-extend -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lathe-extend, .gemini/skills/lathe-extend, .github/skills/lathe-extend and .opencode/skills/lathe-extend in your project.

What does Lathe Extend need to run?

SKILL.md names no scripts, command-line tools or credentials: Lathe Extend is instructions for the agent only.

Does Lathe Extend access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Lathe Extend safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Lathe Extend use?

Lathe Extend is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lathe Extend use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Lathe Extend?

Skills that share tags, products or a category with Lathe Extend: Tutorial (Q00/ouroboros, 6.2k stars), Tutorial Engineer (sickn33/agentic-awesome-skills, 47k stars), Technical Tutorials (sickn33/agentic-awesome-skills, 47k stars) and Step Parts (earthtojake/text-to-cad, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lathe Extend?

devenjarvis (a GitHub user) maintains it in devenjarvis/lathe, which has 1,686 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 3, 2026.

Source: devenjarvis/lathe on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.