Canvas Course Builder logo

Canvas Course Builder

Community
vishalsachdev
canvas-course-builder

Scaffold complete Canvas LMS course structures from specs, templates, or existing courses. Creates modules, pages, assignments, and discussions in bulk. Use when asked to "build a course", "scaffold modules", "create course structure", "set up a new course", or "copy course structure".

Overview

Publishervishalsachdev
Repositorycanvas-mcp
Skill namecanvas-course-builder
Stars
305
Forks
99
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 vishalsachdev on GitHub. Read the source before you install it.

Installation

Install the Canvas Course Builder 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/vishalsachdev/canvas-mcp/tree/main/skills/canvas-course-builder
  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/vishalsachdev/canvas-mcp.git /tmp/canvas-mcp
mkdir -p .claude/skills
cp -r /tmp/canvas-mcp/skills/canvas-course-builder .claude/skills/canvas-course-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Canvas Course Builder 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 Canvas Course Builder 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 Canvas Course Builder 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.

Canvas Course Builder

Build complete Canvas course structures from a natural language description, a JSON template, or by cloning an existing course. Creates modules with pages, assignments, discussions, and proper organization in one workflow.

Prerequisites

  • Canvas MCP server must be running and connected.
  • Authenticated user must have instructor or designer role in the target course.
  • Target course must already exist in Canvas (this skill populates it, does not create the course itself).

Modes

This skill operates in three modes:

Mode 1: Build from Spec (default)

The user describes the course structure in natural language or provides a structured spec.

Mode 2: Build from Template

Load a saved JSON template to scaffold a course.

Mode 3: Clone from Existing Course

Read the structure of Course A and replicate it into Course B.

Steps

1. Determine Mode and Gather Input

Ask the user how they want to build:

How would you like to build the course structure?

  1. Describe it -- Tell me the structure (e.g., "15 weeks, each with an overview page, assignment, and discussion")
  2. From template -- Load a saved template file
  3. Clone another course -- Copy structure from an existing course

For Mode 1 (Spec): Ask for:

  • Target course (code or ID)
  • Number of modules/weeks/units
  • Module naming pattern (e.g., "Week N: [Topic]")
  • Standard items per module (overview page, assignment, discussion, etc.)
  • Any module-specific variations (midterm week, final project, etc.)

For Mode 2 (Template): Ask for the template file path. Parse the JSON template.

For Mode 3 (Clone): Ask for:

  • Source course (code or ID)
  • Target course (code or ID)
  • Call get_course_structure(source_course) to read the full structure

2. Generate Structure Preview

Build a preview of what will be created and present it to the user:

## Course Build Plan: [Course Name]

### Structure: 15 modules x 4 items each = 60 items total

| Module | Page | Assignment | Discussion | SubHeader |
|--------|------|------------|------------|-----------|
| Week 1: Introduction | Overview | HW 1 (10 pts) | Week 1 Forum | Materials |
| Week 2: Fundamentals | Overview | HW 2 (10 pts) | Week 2 Forum | Materials |
| ... | ... | ... | ... | ... |
| Week 14: Review | Overview | -- | Review Forum | Materials |
| Week 15: Final | Overview | Final Project (100 pts) | -- | Materials |

### Items to create:
- 15 modules
- 15 overview pages
- 14 assignments
- 14 discussion topics
- 15 subheaders
- Total: 73 Canvas objects

Shall I proceed?

3. User Approves or Modifies

Wait for explicit approval. The user may:

  • Approve as-is
  • Request modifications (add/remove items, change naming, adjust points)
  • Cancel

Do NOT proceed without approval.

4. Execute Creation

Create items in dependency order:

  1. Modules first: Call create_module with published=false for each module (modules default to published)
  2. Pages: Call create_page with published=false for each overview page (pages default to published)
  3. Assignments: Call create_assignment for each assignment (unpublished)
  4. Discussions: Call create_discussion_topic for each forum
  5. Module items: Call add_module_item to link each created item to its module

Track progress and report as you go:

Creating modules... 15/15 done
Creating pages... 15/15 done
Creating assignments... 14/14 done
Creating discussions... 14/14 done
Linking items to modules... 58/58 done

If any creation fails, log the error and continue with remaining items.

5. Report Results

## Build Complete: [Course Name]

### Created:
- 15 modules
- 15 overview pages
- 14 assignments
- 14 discussion topics
- 58 module items linked

### Failed (0):
None

### Next Steps:
- All items created **unpublished** -- publish when ready
- Add content to overview pages
- Set due dates on assignments
- Run `/canvas-course-qc` to verify structure

6. Save as Template (Optional)

After building, offer to save the structure as a reusable template:

Would you like to save this structure as a template for future courses?

If yes, call get_course_structure(target_course) and save the output as a JSON file.

MCP Tools Used

ToolPurpose
list_coursesFind available courses
get_course_structureRead source course for cloning; verify after build
create_moduleCreate each module
create_pageCreate overview/content pages
create_assignmentCreate assignments
create_discussion_topicCreate discussion forums
add_module_itemLink items to modules
update_modulePublish modules when ready

Template Format

Templates are JSON files with this structure:

json
{
  "template_name": "Standard 15-Week Semester",
  "modules": [
    {
      "name_pattern": "Week {n}: {topic}",
      "items": [
        {"type": "SubHeader", "title_pattern": "Week {n} Materials"},
        {"type": "Page", "title_pattern": "Week {n} Overview"},
        {"type": "Assignment", "title_pattern": "HW {n}", "points": 10},
        {"type": "Discussion", "title_pattern": "Week {n} Discussion"}
      ]
    }
  ],
  "special_modules": [
    {"position": 8, "name": "Midterm Review", "items": [{"type": "Page", "title": "Midterm Study Guide"}]},
    {"position": 15, "name": "Final Project", "items": [{"type": "Assignment", "title": "Final Project", "points": 100}]}
  ]
}

Example

User: "Build a 15-week structure for BADM 350 with a weekly overview page, homework, and discussion"

Agent: Generates preview, asks for approval, creates 60+ items.

User: "Clone the structure from CS 101 into CS 102"

Agent: Reads CS 101 structure, generates preview for CS 102, asks approval, creates matching structure.

Notes

  • Modules and pages are unpublished only when published=false is passed (both default to published). create_assignment defaults to unpublished. create_discussion_topic always publishes on creation; if students must not see a discussion yet, schedule it with delayed_post_at instead of creating it now.
  • Content is not copied when cloning -- only structure (module names, item types, organization).
  • To copy content (not just structure) between courses, use create_content_migration (preview + confirmation token) and poll get_content_migration_status; per-page copy via get_page_content + create_page suits a few pages.
  • Run canvas-course-qc after building to verify the structure is complete and consistent.

Frequently asked questions

What does the Canvas Course Builder AI skill do?

Scaffold complete Canvas LMS course structures from specs, templates, or existing courses. Creates modules, pages, assignments, and discussions in bulk. Use when asked to "build a course", "scaffold modules", "create course structure", "set up a new course", or "copy course structure".

Why use Canvas Course Builder on TypingMind?

Because you install it once and use it with any model. Canvas Course Builder 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 Canvas Course Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vishalsachdev/canvas-mcp/tree/main/skills/canvas-course-builder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Canvas Course Builder?

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 Canvas Course Builder?

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

Is the Canvas Course Builder AI skill free?

Yes. It is published on GitHub by vishalsachdev 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 👇