Package executable teaching labs with datasets, starter code, and autograders.
npx skills add https://github.com/YujxZJCN/teaching-skills --skill lab-forge
Please help me install this Agent Skill. Skill: lab-forge Source: https://github.com/YujxZJCN/teaching-skills/tree/main/lab-forge Command: npx skills add https://github.com/YujxZJCN/teaching-skills --skill lab-forge
Lab design and artifact assembly is tedious and error-prone; lab-forge provides an executable, end-to-end packaging pipeline that builds running teaching artifacts (datasets, starter-code scaffolds, autograders, reference solutions) so instructors can ship reliable labs with confidence.
Run the lab-forge workflow to assemble a complete, verifiable lab package from the design arc.
High-intent search queries and answers about installing and using this skill.
Executable teaching artifacts are packaged by coordinating a pipeline-stage model that assembles datasets, starter code scaffolds, autograders, and reference solutions into a ready-to-run lab package. This ensures verifiable execution records for reproducibility across multiple sections.
Reproducibility is ensured by applying a five-agent workflow that validates artifact integrity from design to deployment, generating verifiable execution records. This pipeline enforces verification standards so instructors can reliably ship teaching labs.
Yes, you can generate ready-to-run packages designed for deployment across multiple STEM course sections. The packaging pipeline includes built-in assessment hooks, autograding tooling, and documentation to support verifiable execution.
You assemble complete lab packages by defining a lab arc and running the workflow, which orchestrates the creation of data, starter repos, grading tooling, and documentation. The pipeline validates artifact integrity from design through deployment.
Yes, the teaching pipeline supports optional components and references to enable reproducibility. These are integrated into the executable lab package alongside datasets, starter code scaffolds, and autograders.
The pipeline targets STEM courses requiring executable teaching artifacts with datasets and autograding. It may be unsuitable if your lab design does not need verifiable execution records or a structured pipeline-stage model with a five-agent team.
erichowensProvide evidence-based addiction recovery guidance across treatment modalities and crisis resources.
gamawareScaffold new lab modules with directories, README files, and executable scripts.
StudentCristianTeach F# discriminated unions, railway-oriented programming, and computation expressions.
ran-isenbergLoad and validate AI-DLC rule detail artifacts before file generation.
