# Agentic Exam Prep > Agentic Exam Prep - Skill: `evnchn-agentic/agentic-exam-prep` (Agent Skill, multi-file: 4 files) - Install (CLI): `npx skillmds@latest add evnchn-agentic/agentic-exam-prep` - Raw SKILL.md: https://api.skillmd.com/api/skills/evnchn-agentic/agentic-exam-prep/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: evnchn-agentic (https://skillmd.com/u/evnchn-agentic) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/evnchn-agentic/agentic-exam-prep --- # Agentic Exam Prep ## Overview An assembly line for open-book exam packs: an iterative MCQ drill loop that tightens recall *and* reveals cheatsheet gaps, a print-pack architecture, course-material mining, and cram-pod/PDF tooling. Course-agnostic in *mechanics*; the depth axes and sources are re-designed per course (two worked applications: the COMP4021 and COMP4431 arc repos in this org). The point is to drill 7–15 correctly-chosen questions, not 561 — selection and signal quality are the whole game. ## HARD RULES (safety + quality rails — read first) - **Canvas (`canvas.ust.hk`): GET only. NEVER POST/PUT/PATCH/DELETE. NEVER start a quiz attempt. No exceptions you initiate.** This is an always-enforce, catastrophic-if-missed rule — a mutation creates a graded submission record that **cannot be un-created**. Quizzes (incl. "Pop Quiz" / "Lecture Video" types) count for grade. To get quiz *content*, you do NOT touch the quiz — mine from slides / transcripts / past papers / GitHub mirrors instead. - There exists a practice-quiz pool-harvest technique that **mutates state** (it POSTs). **You never run it and never decide it's safe.** You cannot reliably tell graded-from-practice via a read, so you do not judge it — only the operator does. It runs ONLY when the operator, this instance, explicitly tells you to AND has confirmed the quiz is ungraded practice. Absent that exact instruction: treat it as forbidden and don't surface the endpoints. - **Don't surface-clone** the sample/past paper. Concept overlap is fine; reusing its code/scenario stems is not. - **Don't ship a one-shot autonomous trivia file as primary material.** Fully-autonomous self-graded subagents are LOW-TRUST (the 4021 trivia agent missed 4 of 7 worth-attempting traps). Build high-yield material interactively or with mid-flight review; diff against an answer key before declaring complete. - **Don't teach to the test** when patching the cheatsheet — patch general-truth claims, not the user's specific blind spot. ## The MCQ drill loop (the core) One active 25-Q set at a time; everything else is source pool or graduated flashcards. **Initial spawn (once per course):** read materials → group into modules → diagnostic gap probe → **hand-author Set 1 + Set 2 as style anchors** (don't delegate until tone is set) → dispatch parallel creator subagents for the depth-axis source banks → run verifier subagents (second pair of eyes — real, not theatre: caught wrong-answer-letter bugs) → concat `all_notes.md` for one-file Ctrl-F. **Refresh cycle (each round)** — triage the user's attempt by **reasoning quality, not just correctness** (read the `Thinking:` line): | Outcome | Action | Tag | |---|---|---| | Correct + confident reasoning (named the rule / used cheatsheet) | **Graduate** to flashcard bank | — | | Correct via elimination / lucky guess / blank Thinking | **Retest** (same concept, new shape) — letter right, rule not internalized | 🔁 | | Wrong / skipped / "don't know" | **Revamp** (fresh shape, explain misconception) | 🔄 | | Misread (right reasoning, wrong letter) | Cheatsheet strategy patch + revamp | 🔄 | | Ran out of time | Carryover (no revamp) | 📦 | Then: **patch the cheatsheet** where a miss revealed a gap (the miss *is* the completeness signal) → build next set = revamps (you author inline — you know the misconception) + carryovers + **pulls** from source banks to refill to 25 → **drain**: delete pulled Qs from their source files (sources shrink monotonically) → verifier pass on freshly-authored revamps → update lineage/drain tables. **Headline metric:** 🔁/🔄 repeat-test passes — miss in round N, pass the revamp in N+1 = concept internalized. **Why the loop is shaped this way (the learning science — and the one gap to close):** the graduate/retest/revamp triage IS *desirable difficulty* — retrieval practice (recall from memory, not re-reading) + varying the shape. Name the trap it guards against: **fluency strength** (got it right *now*) ≠ **storage strength** (will retain it) — and getting a card right once feels like mastery it hasn't earned. Two mechanics the base loop under-uses, worth adding: - **Spacing:** a graduated card that's *gone forever* optimizes fluency, not storage. Re-surface a fraction of graduated cards on a widening interval (round N+2, N+5…); a graduated card that misses on spaced re-exposure was fluency, not storage — send it back. - **Interleaving:** don't drill one module to exhaustion then the next — **mix modules within a set** so retrieval has to first *identify which rule applies* (the real exam condition), not just apply a primed one. (Skills/procedure practice only; pure fact-recall doesn't need it.) Keep grounding every question in a **primary source** (slides/past-paper/key), never parametric recall — the HARD RULES already bind this. *(Fold from mattpocock/skills `teach`, 2026-07-22.)* **Set 0.x extrapolation track** (after ≥2 rounds): group misses by **cognitive failure shape** (e.g. "mutation ≠ completion", "Pythonic-coercion leak", "adjacent-concept decision-tree gap", "API getter/setter asymmetry") and predict where the SAME shape will bite on **un-drilled** concepts. A Set 0.x miss = "the pattern hasn't generalized" = diagnostic gold. Out-of-syllabus is OK in moderation **if flagged** (≥70% in-syllabus, ≤30% flagged stretch). ## Print-pack architecture - **Tag-freeze:** after round-1 prints, `git tag print-pack-v1-`. Never edit packed files in place (the printed copy is now the index of record); new material lands as `to_print_md_roundN/` addenda with their own `build_pack_roundN.py`. - **Two-stage PDF** for hard print-shop margins (Chrome `--print-to-pdf` silently shrinks-to-fit on overflow): Stage 1 pandoc+Chrome headless renders raw (`@page{margin:0}`, no margin-boxes); Stage 2 pypdf `scale(0.93)`-wraps each page onto a fresh letter (the scale envelope = inviolable ~0.30in white margin) + reportlab imprints headers in the outer band. - **Per-module N-up lectures:** 9-up landscape, 3×3, slides rotated 90° CW; one PDF per module, not one book. Decide layout by **visual A/B** (render, look) and quantify utilization% first; confirm slide aspect (16:9 vs 4:3) before scaling. - **Pull-out maneuver:** when the cheatsheet bloats with audience-specific content, pull detail to a dedicated primer and **leave a one-line breadcrumb stub** at the original spot ("references must be kept, else it's dangerous to read the other sheets with missing content"). ## Source mining - **Canvas** (read-only — see HARD RULES): snapshot via the browser's own session — `fetch(url,{credentials:'include'})` from a Canvas-origin Edge tab (HttpOnly cookie never leaves the browser). Works as a student: course/modules/assignments/files/folders/pages-by-slug/lecture-video file-IDs. - **Course site** (e.g. `course.cse.ust.hk//`) when materials aren't on Canvas; **check GitHub mirrors first** (`martin-mok/HKUST-COMP*`) before any paywall. - **Past-paper syllabus-drift table** before drilling any past paper: ` topic | status in current syllabus` — flag REMOVED topics (a 2020 paper had ~25% mass in removed topics). - **NotebookLM cram pods:** 3 topic-coherent notebooks ≤20 sources each (quality degrades past ~20); Pod 1 = exam forensics (≤7: past papers + worked keys, "walk every question, don't pad"); tone = "TA the night before". 1-up PDFs only (verify `pdftotext`); markdown ingests natively. ## Subagent dispatch + trust calibration Trust ranking (highest 4021 post-mortem finding): **interactive-build > vendor-sheet-with-annotation > autonomous-mined-trivia.** Dispatch that works: exact paths + exact output shape + word budget + "OK | ISSUE: " format + hard tool-call cap (≤25). Doesn't work: answer-inference when curated answers exist, naive Read on >10 MB JSONL (Bash-grep first), "summarize" without a target schema. **Author revamps yourself** — you know the user's specific misconception; a subagent doesn't. ## Course adaptation | Domain-agnostic (use as-is) | Course-specific (re-design) | |---|---| | 25-Q active set + module quota; graduate→revamp→pull→drain cycle | The **depth axes** (4021: footguns/code-trace/confusion-pairs/depth-lookup/stack-translate; a DSP course needs formula-recall / algorithm-step-trace / diagram-interpretation instead) | | Verifier second-pass; flashcard graduation format | Source-of-truth files + the mock/sample paper for no-clone | | Cheatsheet-patch-on-miss; `all_notes.md` concat; 🔄/📦/➕ tags | Stack-translate set (keyed to user's daily stack) | ## When NOT to apply - One-off exam not part of a series (tag-freeze/round-addenda is overkill). - Closed-book exam (print-pack matters less; lean into drills + cram pods). - User explicitly opts out of a step ("skip the diagnostic probe, time is short") — follow that.