Skip to main content
ClaudeWave
ES, Spanish
Skill190 estrellas del repoactualizado 14d ago

matlab-plan-tutor-adoption

Use when an instructor asks for a MATLAB AI tutor setup guide, adoption guide, pilot plan, course-specific rollout, or recommended tutor configuration based on a learning objective, course title, course description, module description, or lab description.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/matlab/agent-skills-playground /tmp/matlab-plan-tutor-adoption && cp -r /tmp/matlab-plan-tutor-adoption/demos/ai-tutoring/skills/matlab-plan-tutor-adoption ~/.claude/skills/matlab-plan-tutor-adoption
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# MATLAB AI Tutor Instructor Setup Guide

## Purpose

Generate a short instructor-facing setup guide that fits the provided learning
objective, course title, course description, module description, or lab
description.

Treat the user's provided objective or course description as the guide input. If
the input is missing, ask for one sentence describing the course, module, or
learning objective before generating the guide.

## Input Handling

Use the input argument to infer the best-fit teaching context:

- introductory MATLAB programming course;
- engineering computation course;
- data analysis lab;
- graded homework, lab, project, quiz, or exam support;
- mixed or uncertain context.

If multiple contexts fit, choose the primary context and add a short note about
secondary considerations. Do not ask follow-up questions unless the input is too
vague to identify a course goal.

## Guide Workflow

1. Restate the inferred course or learning objective in one sentence.
2. Identify the best-fit teaching context and why it fits.
3. Recommend the MATLAB AI tutor skill sequence for that context.
4. Provide an instructor-ready starter prompt that can be used with students.
5. Define guardrails for assignment or assessment use.
6. Recommend `matlab-create-ai-policy` when the instructor needs a
   learner-facing AI-use policy or local tutoring-session enforcement file.
7. Propose a first-week pilot activity with one MCQ, one hands-on task, and one
   reflection or transcript/report review step.
8. Explain how to review session reports and transcripts.
9. Include a short revision loop: what the instructor should adjust after the
   first 5-10 sessions.

Read [references/setup-guide-template.md](references/setup-guide-template.md)
for context mapping, output format, and adaptation rules.

Read [references/research-summary.md](references/research-summary.md) when the
user asks for research basis, evidence, rationale, literature mapping, or an
instructor-facing explanation of why the recommended tutor behaviors are used.

## Output Rules

- Default to Markdown unless the user asks for another format.
- Keep the guide practical enough for an instructor to use without extra setup.
- Include concrete prompt text, not only advice.
- When the instructor asks for a demo, pilot, or adoption walkthrough, point to
  `assets/demo-kit/instructor-demo-kit-guide.md` (relative to the demo folder
  that contains `skills/`) and select only the demo-kit pieces that match their
  course context.
- Use course-appropriate guardrails: stricter for graded work, lighter for
  optional practice.
- Include `matlab-log-tutor-sessions`, `matlab-report-tutor-sessions`,
  and `matlab-evaluate-tutor-quality` when the guide involves instructor review.
- Do not invent course policies. If policy is not provided, write a conservative
  default and mark it as adjustable.
- Include a brief research-basis section only when requested or when the guide is
  intended for instructor adoption, departmental review, or pilot approval.
agent-skill-authorSkill

Use this skill when the user wants to author, design, scope, or refine an Agent Skill (a SKILL.md file). Trigger phrases include "build a new skill", "design an agent skill", "scope a SKILL.md", "how should I structure this skill", "write a skill for X", "my skill isn't working well", or any request to improve an existing SKILL.md. Walks the user through an empirical, test-first process — probe the agent for real failures, design only for genuine knowledge gaps, iterate against runnable examples, and verify across models.

embedded-ai-deploymentSkill

>

matlab-apply-assignment-guardrailsSkill

Use when a learner asks for help with MATLAB homework, labs, projects, graded assignments, take-home exams, quizzes, or any programming task where academic integrity, course policy, or instructor constraints may limit direct solutions. Use to provide policy-aware hints, conceptual coaching, partial feedback, and assignment-safe MATLAB tutoring.

matlab-coach-debuggingSkill

Use when tutoring a learner through MATLAB debugging, error interpretation, failed tests, incorrect outputs, array-shape problems, indexing mistakes, function argument issues, or code repair practice. Use for guided debugging sessions, debugging drills, teach-the-agent critique, and evidence-based MATLAB troubleshooting.

matlab-coach-programmingSkill

Use when an AI tutor session concerns MATLAB programming concepts, MATLAB syntax, MATLAB errors, MATLAB code style, MATLAB projects, or MATLAB toolbox workflows.

matlab-create-ai-policySkill

Use when an instructor wants to create, interview for, configure, install, update, or review a course AI-use policy for MATLAB AI tutoring. Produces an AI-POLICY.md file for LMS sharing and local tutoring-session enforcement by assignment guardrails.

matlab-create-course-activitySkill

Create MATLAB Course Designer MATLAB Exercise learning activities by wrapping the existing matlab-generate-grader-assessments skill, then validating generated solution.m, template.m, and tests.m files with MATLAB MCP Server tool calls. Use when the user asks to create a MATLAB Exercise, MATLAB course activity, Course Designer MATLAB activity, validated MATLAB solution file, or MATLAB Exercise component folder.

matlab-create-hands-on-exercisesSkill

Use when prompting a learner to complete hands-on MATLAB coding exercises, guided practice, debugging drills, code tracing, small MATLAB projects, or MATLAB-script assessment during tutoring. Use when the tutor should create a complete runnable MATLAB script, execute it through MATLAB tools, compare the produced outputs with expected outputs, and evaluate MATLAB programming style.