mcpField
G
generate-learning-content

generate-learning-content

github.com/willboosterOther0196 installsUpdated today
Repository

About generate-learning-content

A skill for creating and revising Exercode course materials, judge problems, and contests. It guides repository setup, selects the relevant authoring workflows, and requires validation and model-answer checks before reporting changes.

Key features

  1. 01Repository and content inspection
  2. 02Exercode repository setup guidance
  3. 03Course and contest authoring workflows
  4. 04Validation and evaluation checks
  5. 05Model-answer judging with CLI

Use cases

  1. 01Creating course lessons and embedded questions
  2. 02Writing coding practice problems or contests
  3. 03Revising existing Exercode learning content

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/willbooster/exercode-problem-utils --skill generate-learning-content

After installing, type/generate-learning-contentin Claude Code to confirm it loaded.

Details

From the project README

Generate or improve exercode learning content

  1. Inspect the requested outcome, repository instructions, and existing learning-content layout. When the user is unavailable (e.g. in an automated workflow), make reasonable decisions from the available context instead of pausing for confirmation; the confirmation steps of the workflows below then fall back to the same rule.

  2. If the repository is not prepared for Exercode course authoring, follow setup-exercode-course-repository before authoring.

  3. Follow every applicable authoring workflow:

    Treat both course-material and Judge-problem workflows as applicable when writing, modifying, or executing code is part of the course's learning objective. Do not treat embedded questions or complete code examples as substitutes for graded coding practice.

  4. Run the validation and evaluation required by every applicable workflow and fix failures until clean.

  5. For each generated or changed judge problem, run every model answer through the exercode-problem CLI when @exercode/problem-utils is available: from the problem directory, bunx exercode-problem judge model_answers/<languageId> (it applies the problem's own judge.ts when present and the standard stdio judge otherwise; see generate-judge-problems/references/problem-format.md). Confirm the command exits 0, prints at least one TEST_CASE_RESULT line, and every printed line has the accepted decision code 2000; bunx exercode-problem <problemsDir> checks all problems' model answers at once, but runs them without harness params and therefore fails parameterized problems — exclude those with --skip <substring> and judge them individually. Judge each starter template too and confirm it does not pass every test case. An agent challenge (agentChallenge in problem.md) has no harness: do not judge it; validate it with bunx exercode-problem validate-problem <problemDir> instead.

  6. Report the generated or changed paths, validation and evaluation performed, assumptions made, and intentionally retained warnings.

Comments

Markdown supported