abaj8494
UserAn agentic Recommender System over your working knowledge: builds an on-disk map from your course PDFs and quizzes you at the edge of it. Packaged simply as a pair of Claude Code skills.
Categories
Indexed Skills (5)
lambda-draw
Diagram production for λambda — ANY teaching figure OR data chart, any subject. Graphical models (BNs, Markov chains, HMMs, DBNs, jointrees) AND quantitative charts (time-series, line/bar plots, distributions, option-payoff diagrams). Use for "/lambda-draw <description>" or whenever a session's teaching step needs a figure or a chart. Picks the medium (mermaid / mermaid xychart / TikZ / DOT / ASCII), enforces the compile→render→LOOK→fix loop for TikZ and a trace-every-point check for data charts; nothing unviewed or unverified is ever embedded.
lambda-map
Build or incrementally update a λambda course map — the marks-bound routing table that makes /lambda sessions target assessed problems. Use as "/lambda-map <course-name> <folder(s)>" when materials first arrive and again each week as new sheets drop. Indexes question files (solutions are consulted as grounding only, never copied) and writes courses/<name>/map.md into the vault.
lambda
λambda — Learner-Adaptive, Marks-Bound Drilling Agent. An MCQ-driven learning REPL over a persistent learner model. Use for "/lambda <lecture|topic>" sessions, "/lambda resume", "/lambda drill" to run the re-attempt queue, or "/lambda log <stall>" to file a misconception atom. Probes to the edge of understanding, teaches only misses, routes every miss to real assessed problems, and maintains the mind image in the vault.
lambda-core
The evidence-based learning foundation shared by every λambda field skill (lambda-math, lambda-science, lambda-english, lambda-humanities). The WHY behind the method — retrieval practice, spacing, elaborative encoding, the generation effect, desirable difficulty, calibration, evidence provenance. Load this whenever a lambda-<field> skill loads; its principles govern how you probe, teach, and route regardless of subject.
lambda-math
Field skill for teaching MATHEMATICS in λambda. Loads lambda-core (the learning-science foundation) and adds math-specific conventions — chief among them that every answer and every worked step is presented in SIMPLEST form (reduced fractions, simplified surds, rationalised denominators, exact forms, canonical expressions). Use whenever a session's course or topic is mathematics (stage5-math, yr10-maths, MATH courses, or any quantitative teaching).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.