matlab-log-tutor-sessions
Use when starting, continuing, updating, exporting, or sharing a running transcript of a MATLAB AI tutoring session, especially when the transcript will be shared with an instructor, attached to a learner session report, or passed to an evaluation workflow for quality review.
git clone --depth 1 https://github.com/matlab/agent-skills-playground /tmp/matlab-log-tutor-sessions && cp -r /tmp/matlab-log-tutor-sessions/demos/ai-tutoring/skills/matlab-log-tutor-sessions ~/.claude/skills/matlab-log-tutor-sessionsSKILL.md
# MATLAB AI Tutor Transcript Log ## Purpose Keep a running, evidence-preserving transcript of a MATLAB tutoring session once tutoring has started. The transcript should capture enough context for an instructor or evaluator to understand what happened without turning the log into a polished summary or grade. Use this skill with: - `matlab-tutor-learners` - `matlab-coach-programming` - `matlab-apply-assignment-guardrails` - `matlab-create-hands-on-exercises` - `matlab-coach-debugging` - `matlab-create-mcq-practice` - `matlab-report-tutor-sessions` - `matlab-evaluate-tutor-quality` ## Logging Principles - Start the transcript when a MATLAB tutoring session begins or when the learner asks to record, share, evaluate, or report on the session. - Preserve the sequence of tutor and learner turns. - Capture MATLAB evidence exactly enough to support review: code snippets, outputs, errors, Code Analyzer warnings, test results, and inspected values. - Label uncertain, missing, synthetic, or reconstructed content clearly. - Keep private or unnecessary personal information out of the transcript. - Do not convert the transcript into feedback, a grade, or a learner report. - Ask before including sensitive course, identity, or grade information. - If the user only provides a partial transcript, mark it as partial. ## Transcript Workflow 1. Identify the session context: course, assignment status, learner goal, MATLAB topic, and whether the transcript is real, synthetic, partial, or reconstructed. 2. Create or update the transcript artifact using the required structure. 3. Append each meaningful turn in order with speaker, timestamp if available, and observed content. 4. Add MATLAB evidence blocks for code, errors, outputs, tests, and tool results. 5. Tag tutor moves when visible: active learning, feedback, guardrail, debugging support, transfer, or direct explanation. 6. Add brief session markers for important events such as policy checks, learner revisions, verified fixes, unresolved issues, and transfer prompts. 7. End with export notes that state what is complete, partial, omitted, or synthetic. Read [references/transcript-template.md](references/transcript-template.md) for the required transcript structure, evidence tags, and export format. ## File Naming Autoname transcript files: ```text MATLAB AI Tutor Transcript YYYY-MM-DD HHMMSS.md ``` Use local session datetime when available. Use 24-hour time and omit colons from the time. Example: ```text MATLAB AI Tutor Transcript 2026-06-03 101500.md ``` ## Instructor and Evaluation Use When a transcript is intended for an instructor or evaluation workflow: - include the transcript provenance: real, synthetic, partial, reconstructed, or mixed; - include the assignment policy context if it was provided; - include enough MATLAB evidence to judge correctness; - mark any hidden, omitted, or unavailable turns; - preserve exact tutor wording for moments that may affect guardrails, feedback quality, or student independence. Use `matlab-report-tutor-sessions` after this skill when the user wants a learner-facing progress summary. Use `matlab-evaluate-tutor-quality` when the user wants a quality review of tutor behavior.
>
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.
Use this skill for any work involving a MATLAB Project (.prj file) — creating a new project, tracking files, managing the project path, configuring Simulink cache and code-generation folders, running project health checks, or writing build scripts that keep the project in sync with the file system. Trigger phrases include "set up a MATLAB project", "create a .prj", "track this file in the project", "project health check", "build script conventions". This skill is the generic foundation; domain-specific skills (e.g. `mbse-workflow`) build on it.
Use this skill for the architecture phases of an MBSE workflow in MATLAB, when writing idempotent buildXxx.m scripts that produce a three-layer RFLPV architecture (Functional, Logical, Physical) with interface dictionaries, stereotype profiles, allocation sets, and requirements Implement links. Trigger for defining stereotype properties, functional-to-logical / logical-to-physical allocation, mapping requirements to components via slreq Implement links, or running quantitative roll-up analysis on the architecture. Do NOT trigger for ad-hoc structural edits to an already-built System Composer model (adding one component, rewiring a port) — use `building-simulink-models` with `model_edit` for that. Works alongside the `system-composer` skill for detailed SC API patterns.
Use this skill for guided MBSE work in MATLAB — starting a new project, resuming work mid-workflow on an existing project, or answering orientation questions about how the MBSE skills fit together. Trigger when the user says they want to create, start, or set up a new MBSE project; work on a model-based systems engineering / RFLPV project; or asks which skill covers which phase. Walks through phases one at a time — propose → approve → generate → run → confirm. Use proactively whenever someone mentions starting or continuing an MBSE project.
Use this skill for all requirements-related work in a MATLAB MBSE project using the Requirements Toolbox (slreq). Covers creating and populating requirement sets, derivation links, test case requirements, verification coverage, reading and tracing links across requirement sets and models, checking link health, allocating requirements to components (Implement links), and building traceability reports. Trigger when the user asks about slreq API, slreqx files, slmx link files, outLinks/inLinks, traceability matrices, coverage analysis, broken links, or mapping requirements to architecture components. Use proactively for any requirements or traceability task.
Use this skill when authoring reusable, idempotent MATLAB scripts that build System Composer architecture models via the architecture-modeling API — `systemcomposer.createModel`, `addComponent`, `addPort`, `setInterface`, `connect(srcPort, dstPort)`, interface dictionaries (.sldd) with `addInterface`/`addElement`, profiles/stereotypes with `Profile.createProfile` and `addStereotype`, or `systemcomposer.allocation.createAllocationSet`. Also trigger when debugging these APIs (connections that don't appear, interfaces that don't resolve, profile save errors, `createAllocationSet` signature-mismatch errors). Do NOT trigger for ad-hoc structural edits to an already-built model (adding one SubSystem, rewiring a port) — use `building-simulink-models` with `model_edit` for that.
Optimize MATLAB code for better performance through vectorization, memory management, and profiling. Use when user requests optimization, mentions slow code, performance issues, speed improvements, or asks to make code faster or more efficient.