Generate submission-ready Markdown homework from course directories and lecture materials.
npx skills add https://github.com/vect-G/lecture-to-hw --skill lecture-to-hw
Please help me install this Agent Skill. Skill: lecture-to-hw Source: https://github.com/vect-G/lecture-to-hw/tree/main Command: npx skills add https://github.com/vect-G/lecture-to-hw --skill lecture-to-hw
Automates the end-to-end workflow of finishing course homework by scanning a messy course folder, extracting questions from many file formats, matching them to taught lecture methods and code, and producing concise, student-style Markdown answers that are ready to submit.
作业/hw*_solution/*.md without copying the content.Use lecture-to-hw to complete your current homework and output a submission-ready Markdown solution.
High-intent search queries and answers about installing and using this skill.
Generating homework solutions from mixed course files automatically involves scanning course directories, extracting tasks from varied formats like PDFs and notebooks, and matching them to lecture methods to produce submission-ready Markdown answers.
Yes, you can reuse lecture code and classroom demo results by grounding extracted questions with lecture slides and provided code, prioritizing course terminology and reproducing runnable experiment results directly in the final Markdown.
Multi-format homework ingestion works with PDF, DOCX, HTML, notebooks, and images using OCR or vision, flagging uncertain reads instead of inventing content to ensure accurate task extraction across varied file formats.
The best way to match homework questions with taught lecture methods is searching lecture slides and classroom demo code using question keywords, prioritizing course terminology and formulas to align the solution with classroom instruction.
Maintaining student formatting conventions across Markdown homework submissions requires learning heading, formula, and table styles from existing historical solution files, imitating the formatting without copying the actual content.
Limitations when decomposing tasks for parallel solving include running a maximum of 4 bounded subagents, requiring a controller to unify edits into a single final Markdown, and applying a TA-style review to validate completeness and correctness.
time-machine2025Convert course materials into learner-centered HTML tutorials with cross-lecture links.
ShinyGuaConvert Markdown manuscripts into PDF and DOCX exports.
OPTIMETAConvert PDF documents into editable markdown with OCR and manipulation workflows.
landing-aiExtract fields from mixed document batches into Markdown and hierarchical JSON.