Imported from gabrielmoreira/agent-skills-mirror (mirrors/repos/kazimrmerchant@skill-slice/skills/examprep-ai/SKILL.md). Install upstream with npx skills add gabrielmoreira/agent-skills-mirror --skill examprep-ai. Copyright stays with the author.

ExamPrep AI

When to Use

Use this skill when a student needs to:

• Convert a syllabus, past papers, or study notes into a prioritized study roadmap.
• Focus on specific exam question types: Theory, Numerical, MCQ, Coding, or Lab.
• Generate flashcards, predicted exam papers, or an exam-readiness dashboard.
• Perform last-minute revision or deep-dive into high-probability exam topics.

Trigger keywords: "exam prep", "what to study", "syllabus analysis", "past papers", "important questions", "question prediction", "flashcards", "mock paper", "readiness check", "revision plan", "score roadmap".

Selective Reading Rule — Read ONLY the section matching the request

Rule: Read the matched section and the Shared Foundations block. Skip everything else. Do not load all sections for a focused request.

Shared Foundations

Load this block for every request. It is small and always needed.

Difficulty Scale (Universal)

Order rule: Always present Easy → Medium → Hard. Never reverse.

Intake (ask once, then proceed)

1. Collect at least one of: syllabus, past question papers, notes, or subject name + university.
2. Confirm course code if OCR confidence < 80%: "I detected [X] — is this correct?"
3. Ask time available. If no answer → default Standard Mode (6–12 hrs) and state the assumption.

Study Modes

Syllabus Guardrail

• Map every question to a syllabus unit (≥ 70% match → [IN SYLLABUS]).
• Never generate content for topics absent from the uploaded syllabus.
• Out-of-syllabus items → flag, ask student before including.

Probability Score

Score = (Frequency × 0.40) + (Recency × 0.30) + (Unit Weight × 0.20) + (Marks × 0.10)

• Frequency: appearances ÷ max appearances × 100
• Recency: last 2 yrs = 100 · 3–4 yrs = 60 · older = 30
• Unit Weight: core = 100 · elective = 50
• Marks: 10+ = 100 · 5–9 = 60 · 2–4 = 30 · MCQ = 20

Limitations

• This skill supports study planning and revision; it cannot guarantee exam questions, marks, grading outcomes, or instructor expectations.
• Probability scores are heuristics based on supplied materials; sparse, outdated, or incomplete inputs reduce reliability.
• Never fabricate syllabus coverage. If source material is missing, ambiguous, or out of scope, ask the student to confirm before adding predicted content.
• Not a substitute for official course guidance, accessibility accommodations, academic-integrity policies, or instructor feedback.
• Do not request or process private student records beyond the study material needed for the current revision task.

Prerequisites

• At least one of the following inputs from the student: syllabus text, past question papers (images or text), study notes, or subject name + university name.
• If inputs are images, OCR must be available (built into the agent's Read tool). If OCR confidence is below 80%, manually confirm course code and question text with the student.
• No external API keys or network access required — all processing is local to the agent.

Procedure

Full Roadmap Mode

Use when: student uploads syllabus + past papers, or asks "what should I study?"

Step 1 — Extract. Pull all questions; note year/source for each. Confirm with the student: "Extracted [N] questions from [M] papers for [Course]. Found: 📝[A] 🔢[B] 🔘[C] 💻[D] 🧪[E]. Proceed?"

Step 2 — Classify + tag difficulty. Use the five-type table:

Step 3 — Build ranked tables (one per type):

| # | Question | Times | Marks | Difficulty | Unit | Priority |
|---|----------|-------|-------|------------|------|----------|
| 1 | [question text] | [N]× | [X] | 🟩/🟨/🟥 | Unit [X] | 🔥 Must / ✅ Do |

Step 4 — Generate notes using the matching type section below. Order: Easy across all types first → then Medium → then Hard.

Step 5 — Coverage tracker:

Unit 1: [Name]  →  📝✅  🔢✅  🔘⚠️ PREDICTED  💻—  🧪—
Legend: ✅ past paper  ⚠️ predicted  — not applicable

For any gap: generate one predicted question + note, label [PREDICTED — not from past papers].

Step 6 — Offer next steps: "Would you like (a) Flashcards, (b) Predicted Exam Paper, or (c) Readiness Dashboard?"

Theory Notes

Use when: student asks about definitions, explanations, long-answer questions.

🟩 Easy — Definition / List (30 sec)

📝🟩 [Question] | [N]× | [X] marks
─────────────────────────────────
ANSWER: [2–4 bullets max]
KEY TERM: [single most important word]
MEMORY HOOK: [one-liner trick]

🟨 Medium — Explanation / Comparison (2 min)

📝🟨 [Question] | [N]× | [X] marks
─────────────────────────────────
DEFINITION: [1 sentence]
MAIN POINTS: • P1 • P2 • P3 • P4
DIAGRAM: [text description — student sketches from this]
EXAM TIP: [what examiner rewards]

🟥 Hard — Discussion / Evaluation (5 min read · 10 min write)

📝🟥 [Question] | [N]× | [X] marks | Unit [X]
─────────────────────────────────────────────
INTRO: [2–3 sentences]
SECTION 1 — [subtopic]: • point • point
SECTION 2 — [subtopic]: • point • point
SECTION 3 — [subtopic]: • point • point
DIAGRAM: [sketch description]
CONCLUSION: [1–2 lines]
MARKS HINT: Intro ~2 · each section ~3 · diagram ~2 · conclusion ~1
MEMORY: [acronym or order trick]

Numerical Notes

Use when: student asks for calculation problems, derivations, formulas.

🟩 Easy — Direct formula plug-in

🔢🟩 [Problem Type] | [N]× | [X] marks
──────────────────────────────────────
FORMULA:        [clearly written]
GIVEN → FIND:   [what's given / what to find]
WORKED EXAMPLE:
  Step 1: [substitute]
  Step 2: [calculate]
  Answer: [result + unit]
COMMON MISTAKE: [the one error students make]
MEMORY HOOK:    [how to remember formula]

🟨 Medium — Multi-step with condition

🔢🟨 [Problem Type] | [N]× | [X] marks
──────────────────────────────────────
FORMULA(S): [all needed]
APPROACH:   [which formula when — decision rule]
WORKED EXAMPLE:
  Step 1: [setup / draw table]
  Step 2: [apply condition]
  Step 3: [calculate]
  Step 4: [verify / interpret]
  Answer: [result]
WATCH OUT:  [condition that trips students]
EXAM TIP:   [show working — marks for method too]

🟥 Hard — Derivation / Proof

🔢🟥 [Problem / Derivation] | [N]× | [X] marks
───────────────────────────────────────────────
PREREQUISITES: [what student must know first]
DERIVATION:
  Step 1: [first principles]
  Step 2: [key transformation]
  ...Final: [result / QED]
WORKED EXAMPLE: [concrete numbers applied]
MARKS BREAKDOWN: [method marks vs answer marks]
COMMON ERRORS: [2–3 errors that lose marks]

MCQ Notes

Use when: student asks for MCQ practice, true/false, objective questions.

🟩 Easy — Recall

🔘🟩 [Question] | [N]×
──────────────────────
CORRECT: [option + text]
WHY CORRECT: [one sentence]
WHY OTHERS WRONG: • A: ... • B: ... • C: ...
KEY FACT: [the one thing this tests]

🟨 Medium — Application

🔘🟨 [Question] | [N]×
──────────────────────
CORRECT: [option + text]
REASONING: [identify concept] → [apply rule] → [eliminate wrong]
TRAP: [why students pick the wrong answer]

🟥 Hard — Trap / Edge-case

🔘🟥 [Question] | [N]×
──────────────────────
CORRECT: [option + text]
WHY TRICKY: [what assumption is exploited]
ELIMINATE: • Drop [A]: [reason] • Drop [B]: [reason] • Keep [C]: [reason]
RULE: [the precise rule that settles this type]

Coding Notes

Use when: student asks to write programs, trace output, implement algorithms, debug.

🟩 Easy — Syntax / Pattern recall

💻🟩 [Task] | [N]× | [X] marks
────────────────────────────────
PATTERN:     [algorithm/structure name]
TEMPLATE:    [minimal working skeleton — pseudocode or language-specific]
KEY LINES:   [1–2 lines examiner looks for]
MEMORY HOOK: [how to recall under pressure]

🟨 Medium — Logic construction

💻🟨 [Task] | [N]× | [X] marks
────────────────────────────────
APPROACH:
  1. [sub-tasks]  2. [data structures]  3. [step-by-step logic]
ANNOTATED CODE: [code with inline comments]
EDGE CASES:  [inputs needing special handling]
EXAM TIP:    [comment code — examiners reward clarity]

🟥 Hard — Optimize / Trace / Debug

💻🟥 [Task] | [N]× | [X] marks | TYPE: [Optimize / Trace / Debug]
──────────────────────────────────────────────────────────────────
TRACE →   Input | Trace Table (Iter · VarA · VarB · Output) | Final Output
OPTIMIZE → Naive O(?) → Optimized O(?) | Key Insight: [what enables it]
DEBUG →   Bug Location | Bug Type | Fix | Why it works

Lab Notes

Use when: student asks about experiments, procedures, observations, viva prep.

🟩 Easy — Name / Identify

🧪🟩 [Experiment] | [N]×
─────────────────────────
AIM:      [one sentence]
APPARATUS: [bullet list]
RESULT:   [expected outcome to state]
KEY TERM: [most important term]

🟨 Medium — Write procedure

🧪🟨 [Experiment] | [N]×
─────────────────────────
AIM / APPARATUS: [brief]
PROCEDURE: Step 1 → Step 2 → Step 3 → Step 4
OBS TABLE: [column headers + example row]
RESULT:    [how to state conclusion]
PRECAUTIONS: [2–3 points examiners look for]

🟥 Hard — Analysis / Viva

🧪🟥 [Experiment] | [N]×
─────────────────────────
ANALYSIS: • result in context • formula used • source of error
VIVA:
  Q1: [question]  A: [2–3 sentence answer]
  Q2: [question]  A: [2–3 sentence answer]
  Q3: [question]  A: [2–3 sentence answer]
EXAM TIP: [what viva examiner always asks]

Flashcards

Use when: student asks for flashcards or quick-recall cards.

One card per question:

[TYPE EMOJI][DIFFICULTY EMOJI]
Q: [question]
A: [answer in 1–2 lines]
Key: [formula / term / pattern — if applicable]

Predicted Exam Paper

Use when: student asks for a mock paper or practice test.

Generate one paper with all types represented. Label every question with type + difficulty.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
AI PREDICTION — Not official. For practice only.
Course: [Name]  |  Total Marks: [X]  |  Time: [X] hrs
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

SECTION A — Short / Objective  [🟩 Easy]
  [MCQ / T-F / 1-mark definitions]

SECTION B — Medium Answer      [🟨 Medium]
  [Theory explanations + medium numericals]

SECTION C — Long Answer        [🟥 Hard]
  [Long theory + derivations + coding]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Exam Readiness Dashboard

Use when: student asks for a score estimate or readiness check.

📊 EXAM READINESS
──────────────────────────────────────────────────────
TYPE          EASY    MEDIUM   HARD    OVERALL
📝 Theory     [X]%    [X]%     [X]%    [X]%
🔢 Numerical  [X]%    [X]%     [X]%    [X]%
🔘 MCQ/T-F    [X]%    [X]%     [X]%    [X]%
💻 Coding     [X]%    [X]%     [X]%    [X]%
🧪 Lab        [X]%    [X]%     [X]%    [X]%
──────────────────────────────────────────────────────
PREPAREDNESS  : [X]%
MARKS RANGE   : [Low]–[High] out of [Total]
──────────────────────────────────────────────────────
STRONG        : [types + topics]
WEAK → FOCUS  : [types + topics]
──────────────────────────────────────────────────────
Confidence: [High/Medium/Low]  |  Based on: [N] papers

Examples

Worked Example

Input:

"I have my OS exam tomorrow. Here's the syllabus [paste] and 3 past papers [upload]. I have 4 hours."

Skill routes to: Full Roadmap Mode → Sprint Mode (3–5 hrs)

Output sequence:

1. Extraction confirm: "Extracted 47 questions from 3 papers for Operating System (CSC-207). Found: 📝18 🔢12 🔘10 💻7 🧪0. Proceed?"
2. Ranked tables for all types, Easy → Medium only (Sprint Mode skips Hard except top-1 per unit)
3. Notes for top 25 questions — Easy across all types first, then Medium
4. Coverage tracker showing which units are covered
5. Offer: flashcards, mock paper, or dashboard

Pitfalls

Verification

Run these quality checks before every output:

Related Skills

• note-summarizer — for condensing lecture notes into revision sheets
• flashcard-generator — for standalone spaced-repetition card decks
• syllabus-parser — for extracting structured unit/topic trees from raw syllabus PDFs