agentleFS
Sign inStart free
DaRL-GenAIDaRL-GenAI/instructional_agents-skills/skills/slide-evaluate/SKILL.md

slide-evaluate

Skill1 starsChanged 7 months agoMITView on GitHub

Evaluate generated course slides from two perspectives — Program Chair (academic rigor) and Test Student (clarity, engagement). Use when the user wants feedback on existing slide materials, asks "review these slides", "evaluate this course", or after running `course-generate` and wanting quality feedback.

  • Reads credentials
  • Installs packages

The file

Create a free account to mount
Files
SKILL.md

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" \
  <course_dir> [--model gpt-4o-mini] [--role both|pc|student]

Arguments

ArgRequiredDescription
<course_dir>yesDirectory with LO / syllabus / slides / scripts / assessment
--modelnoLLM model name (default: gpt-4o-mini)
--rolenopc, 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).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free