Slide Evaluate

Slide Evaluate

Runs two validation agents over generated course materials and writes markdown evaluation reports.

• Program Chair — academic rigor, assessment validity, alignment with

program standards, coherence.

• Test Student — clarity, engagement, learning support, accessibility.

When to invoke this skill

• User has a directory of generated slides (from course-generate or manual)

and wants quality feedback

• User asks "how good is this course?" / "review these slides"
• Used as the Phase 3 evaluation in the ADDIE pipeline

Prerequisites

• pip install instructional-agents
• OPENAI_API_KEY set in the environment

Usage

python3 "${CLAUDE_PLUGIN_ROOT}/skills/slide-evaluate/scripts/evaluate.py" \
   [--model gpt-4o-mini] [--role both|pc|student]

Arguments

| Arg | Required | Description | |---|---|---| | ` | yes | Directory with LO / syllabus / slides / scripts / assessment | | --model | no | LLM model name (default: gpt-4o-mini) | | --role | no | pc, student, or both (default: both`) |

Expected course_dir layout

course_dir/
├── learning_objectives.md
├── syllabus.md
├── assessment.md
├── chapter_1/
│   ├── slides.tex
│   ├── script.md
│   └── assessment.md
└── ...

Output

course_dir/evaluation/
├── program_chair_review.md
└── test_student_review.md

Citation

Built on the ValidationAgent from Instructional Agents (arXiv:2508.19611).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: DaRL-GenAI
• Source: DaRL-GenAI/instructional_agents-skills
• License: MIT
• Homepage: https://darl-genai.github.io/instructionalagentshomepage/

Install and usage instructions live in the source repository linked above.