Course Description Analyzer logo

Course Description Analyzer

Community
dmccreary
course-description-analyzer

Validates or creates a course description for an intelligent textbook, scoring completeness against required elements (title, audience, prerequisites, topics, Bloom's Taxonomy outcomes). Use before running the learning-graph-generator.

Overview

Publisherdmccreary
Repositoryibook-skills
Skill namecourse-description-analyzer
Stars
109
Forks
21
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dmccreary on GitHub. Read the source before you install it.

Installation

Install the Course Description Analyzer 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/dmccreary/ibook-skills/tree/main/skills/course-description-analyzer
  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/dmccreary/ibook-skills.git /tmp/ibook-skills
mkdir -p .claude/skills
cp -r /tmp/ibook-skills/skills/course-description-analyzer .claude/skills/course-description-analyzer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Course Description Analyzer 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 Course Description Analyzer 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 Course Description Analyzer 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.

Course Description Analyzer

Version: 0.05

Overview

This Anthropic Claude Skill is the first step in the process of generating an intelligent textbook. The next Skill is the 'learning-graph-generator` Skill.

Analyze or create high-quality course descriptions that contain all necessary elements for generating comprehensive learning graphs with 200+ concepts. Check the /docs/course-description.md file for completeness, quality, and alignment with 2001 Bloom's Taxonomy learning outcomes.

Workflow Decision Tree

Start by checking if /docs/course-description.md exists:

  • File does not exist → Follow Creation Workflow (Step 1)
  • File exists → Follow Analysis Workflow (Step 2)

Tell the user that they are running Version 0.05 of the Course Description Analyzer Skill.

Step 1: Course Description Creation

Use this workflow when /docs/course-description.md does not exist.

1.1 Gather Course Information

Ask the user the following questions sequentially (not all at once):

  1. What is the title of the course?

  2. What is the target audience of the course?

    • Options: elementary, junior high, high school, college undergraduate, graduate students, adult continuing education, professional development, or other
  3. What are the prerequisites for this course?

    • If none, explicitly state "None"
  4. What are the main subjects/topics covered by this course?

    • Request a list of major topics
  5. What are the learning outcomes organized by the 2001 Bloom's Taxonomy?

    • Explain that after this course, students will be able to demonstrate competencies at each level:
      • Remember: Retrieve, recognize, and recall relevant knowledge
      • Understand: Construct meaning from instructional messages
      • Apply: Carry out or use procedures in given situations
      • Analyze: Break material into parts and determine relationships
      • Evaluate: Make judgments based on criteria and standards
      • Create: Put elements together to form coherent wholes; includes capstone projects

1.2 Generate Course Description

Use the template from assets/course-description-template.md and populate it with the user's responses. Create the file at /docs/course-description.md.

Ensure the generated file includes:

  • Clear course title
  • Target audience specification
  • Prerequisites (or "None")
  • Comprehensive list of main topics
  • Section for topics NOT covered (to set boundaries)
  • Detailed learning outcomes organized by all six Bloom's Taxonomy levels
  • Descriptive text explaining why the course is important

1.3 After Creation

After creating the file, automatically proceed to Step 2 (Analysis Workflow) to validate the newly created course description and provide a quality score.

Step 2: Course Description Analysis

Use this workflow when /docs/course-description.md already exists.

2.1 Read the Course Description

Read /docs/course-description.md and analyze its contents against the quality criteria.

2.2 Course Description Quality Scoring System

Evaluate the course description using this 100-point scoring system:

ElementPointsCriteria
Title5Clear, descriptive course title present
Target Audience5Specific audience identified (e.g., "college undergraduate")
Prerequisites5Prerequisites listed or explicitly stated as "None"
Main Topics Covered10Comprehensive list of topics (ideally 5-10 topics)
Topics Excluded5Clear boundaries set for what's NOT covered
Learning Outcomes Header5Clear statement: "After this course, students will be able to..."
Remember Level10Multiple specific outcomes for remembering/recalling
Understand Level10Multiple specific outcomes for understanding/explaining
Apply Level10Multiple specific outcomes for applying/using
Analyze Level10Multiple specific outcomes for analyzing/breaking down
Evaluate Level10Multiple specific outcomes for evaluating/judging
Create Level10Multiple specific outcomes for creating/synthesizing; includes capstone ideas
Descriptive Context5Additional context about course importance, relevance, or value

Scoring Guidelines:

  • Award full points if element is complete and high-quality
  • Award partial points if element is present but incomplete or vague
  • Award 0 points if element is missing
  • For Bloom's Taxonomy levels, require at least 3 specific, actionable outcomes for full points

2.3 Gap Analysis

Identify missing or weak elements:

  • List each element that scored less than full points
  • Explain what is missing or insufficient
  • Indicate how the absence impacts learning graph generation

2.4 Improvement Suggestions

Provide specific, actionable recommendations:

  • For missing elements: Suggest what should be added
  • For weak elements: Provide examples of how to strengthen them
  • For Bloom's Taxonomy outcomes: Recommend specific verbs and topics
  • Prioritize suggestions that will have the most impact on reaching the goal of generating 200 concepts

2.5 Course Description Assessment Report

Use mkdir -p docs/learning-graph to create a learning-graph directory in the docs directory.

Generate a comprehensive quality report on the course description and write it to docs/learning-graph/course-description-assessment.md

  1. Overall Score: X/100

  2. Quality Rating:

    • 90-100: Excellent - Ready for learning graph generation
    • 75-89: Good - Minor improvements recommended
    • 60-74: Adequate - Several improvements needed
    • 40-59: Fair - Significant gaps to address
    • 0-39: Poor - Major revision required
  3. Detailed Scoring Breakdown: Show points earned for each element

  4. Gap Analysis: List of missing or weak elements

  5. Improvement Suggestions: Prioritized recommendations

  6. Next Steps:

    • If score ≥ 85: Ready to proceed with learning graph generation
    • If score < 85: Recommend addressing specific gaps before generating learning graph

2.6 Update Course Description Metadata

In this section NAME is the name of the course taken from the course description. QUALITY_SCORE is the score you computed for the course description.

If it does not exist, add the following yml metadata at the top of the docs/course-description.md file:

yml
---
title: Course Description for Course NAME
description: A detailed course description for NAME including overview, topics covered and learning objectives in the format of the 2001 Bloom Taxonomy
quality_score: QUALITY_SCORE
---

2.7 Concept Generation Readiness

Assess whether the course description contains sufficient detail to generate 200 concepts:

  • Evaluate topic breadth and depth
  • Check if Bloom's Taxonomy outcomes suggest diverse concept types
  • Estimate potential concept count based on current content
  • Recommend additions if concept generation may fall short

Add course-description.md and the course-description-assessment.md to mkdocs.yml Navigation

After the course-description.md file has been added to the /docs directory, ask the user if the new file should be added to the mkdocs.yml file. If the answer is yes, place the new file after the about.md file.

yml
nav:
  - Home: index.md
  - About: about.md
  - Course Description: course-description.md
  # ...other existing entries stay where they are...
  - Learning Graph:
      - Course Description Assessment: learning-graph/course-description-assessment.md

Every entry in nav is a YAML list item, so each one must begin with - , including the entries nested under a section such as Learning Graph. Keep the indentation the file already uses. A nested entry written without the dash makes mkdocs build --strict fail with "Expected nav to be a list".

Next Step

For all users with a score over 85, ask if the learning-graph-generator skill should be run next.

Best Practices

When using this skill:

  1. Be thorough: Don't skip Bloom's Taxonomy levels—all six are essential for comprehensive learning
  2. Be specific: Vague outcomes like "understand the material" won't support quality learning graphs
  3. Use action verbs: Each outcome should start with a measurable verb (list, explain, apply, analyze, evaluate, design, etc.)
  4. Think concepts: Each topic and outcome should suggest multiple learnable concepts
  5. Set boundaries: Topics excluded are as important as topics covered for scope management

Resources

assets/

  • course-description-template.md: Template structure for creating new course descriptions with all required sections and Bloom's Taxonomy framework

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Course Description Analyzer AI skill do?

Validates or creates a course description for an intelligent textbook, scoring completeness against required elements (title, audience, prerequisites, topics, Bloom's Taxonomy outcomes). Use before running the learning-graph-generator.

Why use Course Description Analyzer on TypingMind?

Because you install it once and use it with any model. Course Description Analyzer 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 Course Description Analyzer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dmccreary/ibook-skills/tree/main/skills/course-description-analyzer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Course Description Analyzer?

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 Course Description Analyzer?

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

Is the Course Description Analyzer AI skill free?

It is published on GitHub by dmccreary. Check the repository for licensing terms. 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 👇