Use this skill when you need to: - Convert a syllabus, past papers, or study notes into a prioritized roadmap. - Focus on specific types of exam questions (Theory, Numerical, MCQ, Coding, Lab). - Create flashcards, predicted exam papers, or check your overall exam readiness. - Perform last-minute revision or deep-dive into important exam topics.

Category: AI & Intelligent Agents
Repo: antigravity-awesome-skills
Path: skills/examprep-ai/SKILL.md
Updated: 7/19/2026, 7:47:10 PM
Open on GitHubHow to Install

AI Summary

Use this skill when you need to: - Convert a syllabus, past papers, or study notes into a prioritized roadmap. - Focus on specific types of exam questions (Theory, Numerical, MCQ, Coding, Lab). - Create flashcards, predicted exam papers, or check your overall exam readiness. - Perform last-minute revision or deep-dive into important exam topics. It is useful for LLM applications, agent orchestration, RAG pipelines, AI evaluation, and multi-agent workflows. Source: antigravity-awesome-skills (skills/examprep-ai/SKILL.md).

ExamPrep AI

When to Use

Use this skill when you need to:

  • Convert a syllabus, past papers, or study notes into a prioritized roadmap.
  • Focus on specific types of exam questions (Theory, Numerical, MCQ, Coding, Lab).
  • Create flashcards, predicted exam papers, or check your overall exam readiness.
  • Perform last-minute revision or deep-dive into important exam topics.

🎯 Selective Reading Rule β€” Read ONLY the section matching the request

What the student asks forJump to
Full roadmap / "what to study" / syllabus + past papers uploadedFull Roadmap Mode
Theory questions only / definitions / explanationsTheory Notes
Numerical / calculation / derivation problemsNumerical Notes
MCQ / True-False / objective practiceMCQ Notes
Coding / algorithm / trace / debugCoding Notes
Lab / practical / viva prepLab Notes
Flashcards onlyFlashcards
Mock exam paperPredicted Exam Paper
Readiness check / score projectionExam Readiness Dashboard

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)

LevelSignal WordsStudent Goal
🟩 Easydefine, state, list, name, identify, what isGuaranteed marks β€” study first
🟨 Mediumexplain, describe, compare, calculate, implement, traceMid-paper marks
πŸŸ₯ Hardderive, prove, optimize, analyze, evaluate, design, whyScore separators β€” study last

Order rule: Always present Easy β†’ Medium β†’ 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] β€” is this correct?"
  3. Ask time available. If no answer β†’ default Standard Mode (6–12 hrs) and state the assumption.

Study Modes

ModeTimeLoad
🚨 Emergency1–2 hrs🟩 Easy only, top 10 questions
⚑ Sprint3–5 hrs🟩 + 🟨, top 25 questions
πŸ“š Standard (default)6–12 hrsAll difficulties, full roadmap
πŸ—“οΈ AdvanceDays+Daily schedule + mock papers

Syllabus Guardrail

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

Probability Score

Score = (Frequency Γ— 0.40) + (Recency Γ— 0.30) + (Unit Weight Γ— 0.20) + (Marks Γ— 0.10)
  • Frequency: appearances Γ· max appearances Γ— 100
  • Recency: last 2 yrs = 100 Β· 3–4 yrs = 60 Β· older = 30
  • Unit Weight: core = 100 Β· elective = 50
  • Marks: 10+ = 100 Β· 5–9 = 60 Β· 2–4 = 30 Β· MCQ = 20

Limitations

  • This skill supports study planning and revision, but it cannot guarantee exam questions, marks, grading outcomes, or instructor expectations.
  • Probability scores are heuristics based on supplied syllabi, notes, and past papers; sparse, outdated, or incomplete inputs reduce reliability.
  • The skill should not fabricate syllabus coverage. If source material is missing, ambiguous, or out of scope, ask the student to confirm before adding predicted content.
  • It is 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.

Full Roadmap Mode

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

Step 1 β€” Extract. Pull all questions; note year/source for each. Confirm: "Extracted [N] questions from [M] papers for [Course]. Found: πŸ“[A] πŸ”’[B] πŸ”˜[C] πŸ’»[D] πŸ§ͺ[E]. Proceed?"

Step 2 β€” Classify + tag difficulty. Use the five-type table:

TypeIdentify By
πŸ“ Theorydefine, explain, discuss, compare, differentiate
πŸ”’ Numericalcalculate, find, solve, derive, prove, numbers in question
πŸ”˜ MCQ/T-Foptions listed, "true or false", "which of the following"
πŸ’» Codingwrite a program, implement, trace output, algorithm, flowchart
πŸ§ͺ Labexperiment, procedure, observation, aim, apparatus, viva

Step 3 β€” Build ranked tables (one per type):

| # | Question | Times | Marks | Difficulty | Unit | Priority |
|---|----------|-------|-------|------------|------|----------|
| 1 | [question text] | [N]Γ— | [X] | 🟩/🟨/πŸŸ₯ | Unit [X] | πŸ”₯ Must / βœ… Do |

Step 4 β€” Generate notes using the matching type section below. Order: Easy across all types first β†’ then Medium β†’ then Hard.

Step 5 β€” Coverage tracker:

Unit 1: [Name]  β†’  πŸ“βœ…  πŸ”’βœ…  πŸ”˜βš οΈ PREDICTED  πŸ’»β€”  πŸ§ͺβ€”
Legend: βœ… past paper  ⚠️ predicted  β€” not applicable

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

Step 6 β€” Offer: "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 β€” Definition / List (30 sec)

πŸ“πŸŸ© [Question] | [N]Γ— | [X] marks
─────────────────────────────────
ANSWER: [2–4 bullets max]
KEY TERM: [single most important word]
MEMORY HOOK: [one-liner trick]

🟨 Medium β€” Explanation / Comparison (2 min)

πŸ“πŸŸ¨ [Question] | [N]Γ— | [X] marks
─────────────────────────────────
DEFINITION: [1 sentence]
MAIN POINTS: β€’ P1 β€’ P2 β€’ P3 β€’ P4
DIAGRAM: [text description β€” student sketches from this]
EXAM TIP: [what examiner rewards]

πŸŸ₯ Hard β€” Discussion / Evaluation (5 min read Β· 10 min write)

πŸ“πŸŸ₯ [Question] | [N]Γ— | [X] marks | Unit [X]
─────────────────────────────────────────────
INTRO: [2–3 sentences]
SECTION 1 β€” [subtopic]: β€’ point β€’ point
SECTION 2 β€” [subtopic]: β€’ point β€’ point
SECTION 3 β€” [subtopic]: β€’ point β€’ point
DIAGRAM: [sketch description]
CONCLUSION: [1–2 lines]
MARKS HINT: Intro ~2 Β· each section ~3 Β· diagram ~2 Β· conclusion ~1
MEMORY: [acronym or order trick]

Numerical Notes

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

🟩 Easy β€” Direct formula plug-in

πŸ”’πŸŸ© [Problem Type] | [N]Γ— | [X] marks
──────────────────────────────────────
FORMULA:        [clearly written]
GIVEN β†’ 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 β€” Multi-step with condition

πŸ”’πŸŸ¨ [Problem Type] | [N]Γ— | [X] marks
──────────────────────────────────────
FORMULA(S): [all needed]
APPROACH:   [which formula when β€” 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 β€” marks for method too]

πŸŸ₯ Hard β€” Derivation / Proof

πŸ”’πŸŸ₯ [Problem / Derivation] | [N]Γ— | [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 β€” Recall

πŸ”˜πŸŸ© [Question] | [N]Γ—
──────────────────────
CORRECT: [option + text]
WHY CORRECT: [one sentence]
WHY OTHERS WRONG: β€’ A: ... β€’ B: ... β€’ C: ...
KEY FACT: [the one thing this tests]

🟨 Medium β€” Application

πŸ”˜πŸŸ¨ [Question] | [N]Γ—
──────────────────────
CORRECT: [option + text]
REASONING: [identify concept] β†’ [apply rule] β†’ [eliminate wrong]
TRAP: [why students pick the wrong answer]

πŸŸ₯ Hard β€” Trap / Edge-case

πŸ”˜πŸŸ₯ [Question] | [N]Γ—
──────────────────────
CORRECT: [option + text]
WHY TRICKY: [what assumption is exploited]
ELIMINATE: β€’ Drop [A]: [reason] β€’ Drop [B]: [reason] β€’ 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 β€” Syntax / Pattern recall

πŸ’»πŸŸ© [Task] | [N]Γ— | [X] marks
────────────────────────────────
PATTERN:     [algorithm/structure name]
TEMPLATE:    [minimal working skeleton β€” pseudocode or language-specific]
KEY LINES:   [1–2 lines examiner looks for]
MEMORY HOOK: [how to recall under pressure]

🟨 Medium β€” Logic construction

πŸ’»πŸŸ¨ [Task] | [N]Γ— | [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 β€” examiners reward clarity]

πŸŸ₯ Hard β€” Optimize / Trace / Debug

πŸ’»πŸŸ₯ [Task] | [N]Γ— | [X] marks | TYPE: [Optimize / Trace / Debug]
──────────────────────────────────────────────────────────────────
TRACE β†’   Input | Trace Table (Iter Β· VarA Β· VarB Β· Output) | Final Output
OPTIMIZE β†’ Naive O(?) β†’ Optimized O(?) | Key Insight: [what enables it]
DEBUG β†’   Bug Location | Bug Type | Fix | Why it works

Lab Notes

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

🟩 Easy β€” Name / Identify

πŸ§ͺ🟩 [Experiment] | [N]Γ—
─────────────────────────
AIM:      [one sentence]
APPARATUS: [bullet list]
RESULT:   [expected outcome to state]
KEY TERM: [most important term]

🟨 Medium β€” Write procedure

πŸ§ͺ🟨 [Experiment] | [N]Γ—
─────────────────────────
AIM / APPARATUS: [brief]
PROCEDURE: Step 1 β†’ Step 2 β†’ Step 3 β†’ Step 4
OBS TABLE: [column headers + example row]
RESULT:    [how to state conclusion]
PRECAUTIONS: [2–3 points examiners look for]

πŸŸ₯ Hard β€” Analysis / Viva

πŸ§ͺπŸŸ₯ [Experiment] | [N]Γ—
─────────────────────────
ANALYSIS: β€’ result in context β€’ formula used β€’ 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 β€” 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 β€” Not official. For practice only.
Course: [Name]  |  Total Marks: [X]  |  Time: [X] hrs
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

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

SECTION B β€” Medium Answer      [🟨 Medium]
  [Theory explanations + medium numericals]

SECTION C β€” Long Answer        [πŸŸ₯ Hard]
  [Long theory + derivations + coding]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Exam Readiness Dashboard

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

πŸ“Š EXAM READINESS
──────────────────────────────────────────────────────
TYPE          EASY    MEDIUM   HARD    OVERALL
πŸ“ Theory     [X]%    [X]%     [X]%    [X]%
πŸ”’ Numerical  [X]%    [X]%     [X]%    [X]%
πŸ”˜ MCQ/T-F    [X]%    [X]%     [X]%    [X]%
πŸ’» Coding     [X]%    [X]%     [X]%    [X]%
πŸ§ͺ Lab        [X]%    [X]%     [X]%    [X]%
──────────────────────────────────────────────────────
PREPAREDNESS  : [X]%
MARKS RANGE   : [Low]–[High] out of [Total]
──────────────────────────────────────────────────────
STRONG        : [types + topics]
WEAK β†’ FOCUS  : [types + topics]
──────────────────────────────────────────────────────
Confidence: [High/Medium/Low]  |  Based on: [N] papers

Worked Example

Concrete before/after demonstrating the skill.

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 β†’ Sprint Mode (3–5 hrs)

Output sequence:

  1. Extraction confirm: "Extracted 47 questions from 3 papers for Operating System (CSC-207). Found: πŸ“18 πŸ”’12 πŸ”˜10 πŸ’»7 πŸ§ͺ0. Proceed?"
  2. Ranked tables for all types, Easy β†’ Medium only (Sprint Mode skips Hard except top-1 per unit)
  3. Notes for top 25 questions β€” Easy across all types first, then Medium
  4. Coverage tracker showing which units are covered
  5. Offer: flashcards, mock paper, or dashboard

Quality Checks (run before every output)

CheckRule
Syllabus complianceEvery note maps to a syllabus unit
Difficulty orderEasy before Medium before Hard β€” never reversed
Numerical accuracyWorked examples compute correctly
Code validitySnippets are syntactically correct
Note lengthReadable in ≀ 2–5 min per note
No hallucinationNo facts absent from uploaded materials
Course code confirmedOCR-detected code verified by student

Error Responses

SituationSay
No syllabus"Without a syllabus I can't guarantee on-topic notes. Paste your unit list as text?"
1 past paper only"One paper = lower prediction confidence. More papers = better accuracy."
OCR failure"Couldn't read part of the image. Can you retype those questions?"
Out-of-syllabus question"This doesn't match your syllabus β€” skipping it. Want me to include it anyway?"
Mixed subjects"Found questions from two subjects. Should I separate them?"
No time given"Defaulting to Standard Mode (6–12 hrs). Tell me if you have less time."
No numericals/coding found"No numerical/coding questions found. Share a paper that includes them if your exam has these."

Related skills