paideia

Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.

Save a clean reference derivation of a target equation or theorem to derivations/. Draws from course materials (textbook, lecture notes) rather than testing the user.

Grade user's answer PDF (hand-written, scanned) against reference solution. OCR engine is selectable: claude (default, no extra install), ollama (Qwen3-VL local), or tesseract. Then strategy-based grade.

Show HW/example coverage of course sections from course-index/coverage.md. HW density = exam probability; surface the exam-hot zones.

Convert all course-material PDFs (lectures, textbook, homework, solutions) to markdown via the vision pipeline — one parallel agent per file, LaTeX-faithful transcription. Idempotent — skips already-converted files.

Use whenever the user uploads a hand-written or scanned answer PDF to be graded against a reference solution. Converts answer PDFs in `answers/*.pdf` to markdown in `answers/converted/*.md` using the pdf skill (OCR as needed), then performs strategy-based grading against `converted/solutions/*.md` or `quizzes/*_answers.md`. Invoked by `/grade`.

Use whenever the user wants to ingest a new course's materials (lecture notes, textbook chapters, HW problems, HW solutions) and build the course-specific knowledge base — patterns.md (recurring solution techniques), coverage.md (HW-to-section map with blind spots), and summary.md (topic tree). Invoked by `/ingest` and `/analyze` slash commands. Designed to be domain-general across math and physics courses (calculus, linear algebra, real/complex analysis, classical mechanics, E&M, thermodynamics, quantum, etc.).

Use when the user wants exam-focused drilling from the course's analyzed material. Generates twin variants of known problems (`/twin`), runs strategy-level blind drills on known problems (`/blind`), creates integration problems chaining multiple patterns (`/chain`), surfaces pattern cards (`/pattern`), and shows coverage/blind-spot maps (`/hwmap`). Reads from `course-index/patterns.md`, `course-index/coverage.md`, and `converted/solutions/*.md`. Works for any math/physics course that has been ingested and analyzed.

Use whenever the user works with PDF files — reading/extracting text from PDFs (lecture notes, textbook chapters, HW problems, HW solutions, hand-written answers), converting PDFs to markdown for downstream analysis, merging/splitting PDFs, or creating PDFs. For scanned or hand-written PDFs, OCR is required (pytesseract + pdf2image). Based on Anthropic's official PDF skill (github.com/anthropics/skills/tree/main/skills/pdf).

Use whenever a hand-written or scanned answer PDF needs transcription to markdown for /grade. Three tiers — Claude native vision (default, no extra install), local Qwen3-VL 8B via ollama (opt-in privacy mode), pytesseract fallback. The engine is selected via `OCR_ENGINE` in `.course-meta` (written by /paideia:init-course) and can be overridden per-call with `/paideia:grade --ocr=<engine>`.