Sponsor Suno AI Music arrow_forward
Slash Command

Update Tutorial

Generate or update tutorials with VHS and Playwright recordings

Type
Slash Command
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026

What Update Tutorial is

Update Tutorial is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Update Tutorial gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Update Tutorial

Claude Code

  1. Download update-tutorial.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/sanctum/commands/update-tutorial.md, shared under the repository's MIT license. Read the full file on GitHub.

To generate or update tutorials with accompanying GIFs, invoke the tutorial-updates skill:

  1. Run Skill(sanctum:tutorial-updates) with the appropriate arguments.

When To Use

Use this command when you need to:

  • Creating or updating documentation tutorials
  • Generating terminal/browser recording GIFs

When NOT To Use

  • Simple changes that don't need the full workflow
  • Work already completed through another sanctum command

Usage

/update-tutorial <name>              # Single tutorial
/update-tutorial <name1> <name2>     # Multiple tutorials
/update-tutorial --all               # All tutorials in manifest
/update-tutorial --list              # Show available tutorials
/update-tutorial --scaffold          # Create directory structure without recording
/update-tutorial --validate-only     # Validate tape without generating GIF
/update-tutorial --skip-validation   # Skip validation for rapid regeneration

Validation Flags

--validate-only

Run tape validation without generating GIF. Useful for CI checks or pre-commit hooks.

Example:

/update-tutorial quickstart --validate-only

Exit codes:

  • 0: Validation passed
  • 1: Validation failed (errors found)

Use when: You want to verify tape commands are correct before committing or before running expensive GIF generation.

--skip-validation

Bypass pre-flight tape validation. Use when commands are known-good and you need rapid GIF regeneration.

Example:

/update-tutorial quickstart --skip-validation

Warning: Skipping validation may result in VHS failures that could have been caught earlier.

Use when: You've already validated the tape and are iterating on timing/styling only.

Rebuild Flags

--skip-rebuild

Skip binary freshness check and rebuild step. Use when binary is known to be current.

Example:

/update-tutorial quickstart --skip-rebuild

Use when: You've just rebuilt the binary manually and want to avoid redundant rebuilds.

--force-rebuild

Force binary rebuild even if freshness check passes. Ensures absolute latest code.

Example:

/update-tutorial quickstart --force-rebuild

Use when: You want to guarantee the binary matches source, regardless of timestamps (useful after git operations that don't change timestamps).

Workflow

The skill orchestrates scry media generation capabilities:

  1. Discovery: Parse tutorial manifests to identify tape files and browser specs.
  2. Validation: Test tape commands locally BEFORE recording to catch errors early.
  3. Rebuild: Check binary freshness and rebuild if stale so demos reflect latest code.
  4. Recording: Invoke Skill(scry:vhs-recording) for terminal demos and Skill(scry:browser-recording) for web UI demos.
  5. Processing: Use Skill(scry:gif-generation) for format conversion and optimization.
  6. Composition: Apply Skill(scry:media-composition) for multi-source tutorials.
  7. Documentation: Generate dual-tone markdown (project docs and technical book).
  8. Integration: Update README demo sections and book chapters.

Examples

Update Single Tutorial

/update-tutorial quickstart

Update Multiple Tutorials

/update-tutorial quickstart sync mcp

Regenerate All Tutorials

/update-tutorial --all

Preview Available Tutorials

/update-tutorial --list

Create Scaffold Only

/update-tutorial --scaffold

Creates the directory structure (assets/tapes/, assets/gifs/, docs/tutorials/) without executing recordings.

Requirements

Required

  • VHS (Charmbracelet) - Terminal recording to GIF
  • Install: brew install vhs or go install github.com/charmbracelet/vhs@latest
  • Dependencies: ttyd, ffmpeg (VHS installs ttyd automatically)

Optional (for browser tutorials)

  • Playwright - Browser automation and video recording
  • Install: npm install -D @playwright/test
  • ffmpeg - Video-to-GIF conversion (usually pre-installed)

WSL2 Notes

  • VHS works on WSL2 but may require building ttyd from source
  • Test early; fallback to asciinema + agg if issues arise

Manifest Format

Tutorials are defined via YAML manifests:

# assets/tapes/mcp.manifest.yaml
name: mcp
title: "MCP Server Integration"
components:
  - type: tape
    source: mcp.tape
    output: assets/gifs/mcp-terminal.gif
  - type: playwright
    source: browser/mcp-browser.spec.ts
    output: assets/gifs/mcp-browser.gif
    requires:
      - "skrills serve"
combine:
  output: assets/gifs/mcp-combined.gif
  layout: vertical

Manual Execution

If skills cannot be loaded, follow these steps:

  1. Run VHS directly

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Update Tutorial?

Update Tutorial is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Generate or update tutorials with VHS and Playwright recordings

How do I install Update Tutorial in Claude Code?

Download update-tutorial.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Update Tutorial in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Update Tutorial safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.