# Exam And Assessment Designer

> Designs rigorous assessments for higher education and professional reskilling, including written exams, machine exams, quizzes, oral exams, take-home assignments, and retakes. Use when an instructor or trainer needs a scientifically sound, level-calibrated, feasible, and gradeable assessment with subject, instructions, rubric hooks, and correction guidance.

- Skill: `alainlebret/exam-and-assessment-designer` (Agent Skill)
- Install (CLI): `npx skillmds@latest add alainlebret/exam-and-assessment-designer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/alainlebret/exam-and-assessment-designer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: alainlebret (https://skillmd.com/u/alainlebret)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/alainlebret/exam-and-assessment-designer

---


# Exam and Assessment Designer

## Goal
Create assessments that measure what was actually taught, remain feasible in the available time, and support fair grading.

## Inputs
Read `mission.json` first. Then read any existing course, TD, TP, syllabus, prior exam, or institutional constraints.

## Produce
Depending on the request, generate:
- assessment blueprint;
- subject statement;
- teacher version and student version when relevant;
- correction guidance;
- expected answers or reference solution outline;
- anti-ambiguity notes;
- grading hooks for `rubric-builder`.

## Assessment types supported
- written exam;
- machine exam;
- oral exam;
- quiz / QCM;
- take-home assignment;
- retake exam;
- diagnostic assessment;
- professional certification-style task.

## Design rules
- Only assess notions that are explicitly taught or formally listed as prerequisites.
- Keep the wording precise, short, and unambiguous.
- Separate what is mandatory from what is optional.
- Calibrate the workload against the real exam duration.
- Distinguish knowledge recall, method application, reasoning, and technical execution.
- For machine exams, specify environment assumptions and recovery paths.
- For professional reskilling, prefer authentic tasks over purely academic tricks.

## Mandatory checks
Before validating an assessment, verify:
- alignment with learning outcomes;
- level appropriateness;
- feasibility under time pressure;
- completeness of instructions;
- existence of a defensible grading path;
- consistency between subject, expected solution, and later rubric.

## Anti-failure rules
- Refuse subjects with hidden dependencies.
- Refuse trick questions that reward guessing more than competence.
- Refuse questions requiring unstated notation or vocabulary.
- Flag topics assessed but not prepared by prior activities.
- Flag machine exams that depend on fragile tooling without fallback.