Canvas Course Qc logo

Canvas Course Qc

Community
vishalsachdev
canvas-course-qc

Learning designer quality check for Canvas LMS courses. Audits module structure, content completeness, publishing state, date consistency, and rubric coverage. Use when asked to "QC a course", "is this course ready", "pre-semester check", or "quality review".

Overview

Publishervishalsachdev
Repositorycanvas-mcp
Skill namecanvas-course-qc
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 Qc 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-qc
  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-qc .claude/skills/canvas-course-qc
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Canvas Course Qc 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 Qc 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 Qc 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 QC

Automated quality checklist for Learning Designers to verify a Canvas course is ready for students. Runs structure, content, publishing, and completeness checks — then reports issues by priority.

Prerequisites

  • Canvas MCP server must be running and connected.
  • Authenticated user must have instructor, TA, or designer role in the target course.
  • Best run before the semester starts or before publishing a course to students.

Steps

1. Identify Target Course

Ask the user which course to QC. Accept a course code, Canvas ID, or course name.

If not specified, prompt:

Which course would you like to quality-check?

Use list_courses to look up available courses if needed.

2. Retrieve Course Structure

Call get_course_structure(course_identifier) to get the full module-to-items tree in one call.

This returns all modules with their items, publishing states, and summary statistics.

3. Run Structure Checks

Analyze the module tree for structural issues:

CheckPriorityWhat to Look For
Empty modulesWarningModules with 0 items (confusing to students)
Naming consistencySuggestionDo all modules follow the same pattern? (e.g., "Week N:", "Unit N:")
Module countSuggestionDoes it match expected count for course length?
Item orderingSuggestionSubHeaders present for organization?

4. Run Content Checks

Call list_assignments(course_identifier) and check each assignment:

CheckPriorityWhat to Look For
Missing due datesBlockingGraded assignments without a due_at date
Missing descriptionsWarningAssignments with empty or null description
Missing pointsWarningAssignments without points_possible set
Date sequencingWarningDue dates that don't follow module order
Rubric coverageSuggestionGraded assignments without an associated rubric

For pages, check if any pages in modules have empty body content using get_page_content for pages flagged in the structure.

5. Run Publishing Checks

Using the structure data:

CheckPriorityWhat to Look For
Ghost itemsBlockingPublished items inside unpublished modules (invisible to students)
Unpublished modulesWarningModules that may need publishing before semester
No front pageWarningCourse has no front page set

Check for front page by calling list_pages(course_identifier) and looking for front_page: true.

6. Run Completeness Checks

Compare module structures to find inconsistencies:

CheckPriorityWhat to Look For
Inconsistent structureWarningMost modules have 4 items but some only have 1
Missing item typesSuggestionMost modules have an Assignment but some don't

Build a "typical module" profile from the most common item-type pattern, then flag modules that deviate.

7. Generate QC Report

Present results grouped by priority:

## Course QC Report: [Course Name]

### Summary
- Modules: 15 | Items: 67 | Assignments: 15 | Pages: 20
- Issues found: 3 blocking, 5 warnings, 2 suggestions

### Blocking Issues (fix before publishing)
1. Assignment "Final Project" has no due date
2. Published "Week 5 Quiz" is inside unpublished "Week 5" module (invisible to students)
3. Assignment "Midterm" has no due date

### Warnings (should fix)
1. 2 empty modules: "Week 14", "Week 15"
2. 3 assignments missing descriptions: HW 3, HW 7, HW 12
3. No front page set for course
4. Due dates out of order: Week 8 assignment due before Week 7
5. "Week 3" module has 1 item while typical modules have 4

### Suggestions (nice-to-have)
1. Module naming: 13/15 use "Week N:" pattern but "Midterm Review" and "Final Review" don't
2. 5 graded assignments have no rubric attached

8. Offer Follow-up Actions

After presenting the report, offer actionable next steps:

Would you like me to:

  1. Auto-fix publishing -- Publish all unpublished modules (with confirmation)
  2. Show details -- Expand on a specific issue
  3. Run accessibility audit -- Check for WCAG-oriented issues (uses canvas-accessibility-auditor skill)
  4. Check another course

For auto-fix, use update_module or bulk_update_pages with user confirmation before each batch.

MCP Tools Used

ToolPurpose
list_coursesFind available courses
get_course_structureFull module tree with items
list_assignmentsAssignment details for content checks
get_assignment_detailsDeep-dive on flagged assignments
list_pagesCheck for front page
get_page_contentVerify pages have content
list_rubricsCheck rubric coverage
update_moduleAuto-fix: publish modules
bulk_update_pagesAuto-fix: publish pages

Example

User: "QC check for BADM 350"

Agent: Runs all checks, outputs the prioritized report.

User: "Fix the publishing issues"

Agent: Publishes the 2 unpublished modules after confirmation.

Notes

  • This skill is designed for Learning Designers who manage course structure before students access it.
  • Run this before each semester or after major content updates.
  • Pairs well with canvas-accessibility-auditor for comprehensive course review.

Frequently asked questions

What does the Canvas Course Qc AI skill do?

Learning designer quality check for Canvas LMS courses. Audits module structure, content completeness, publishing state, date consistency, and rubric coverage. Use when asked to "QC a course", "is this course ready", "pre-semester check", or "quality review".

Why use Canvas Course Qc on TypingMind?

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

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

Which AI models can use Canvas Course Qc?

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 Qc?

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

Is the Canvas Course Qc 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 👇