Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Math Exam Quality Guard

    1

    Audit math exam questions and answer keys with independent solutions, option-equivalence checks, domain validation, issue severity and a ready-to-use QA report. Includes a safe exact-arithmetic helper.

    $9.90

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Math Exam Quality Guard

    Math Exam Quality Guard

    Example session with this skill installed

    Audit the following mathematics exam question before publication.

    Question Q7: Solve x² = 9 over the real numbers.

    Provided answer key: x = 3.

    Independently solve the equation, verify all solutions, check whether the answer key is complete, classify any errors by severity, and provide a final release recommendation.

    Do not modify the original question or answer key.

    • Read your context and instructions
    • Compiled the math exam quality

    Math Exam Quality Audit Report

    Item: Q7
    Status: FAIL
    Severity: BLOCKER
    Answer key: Incorrect (incomplete)
    Release decision: DO NOT RELEASE

    1. Independent Mathematical Solution

    Given the equation

    x² = 9

    Subtracting 9 from both sides:

    x² − 9 = 0

    Applying the difference of squares

    (x − 3)(x + 3) = 0

    Therefore, the complete solution set over the real numbers is:

    S = {−3, 3}

    2. Answer Verification

    Both solutions satisfy the original equation:

    • x = 3: 3² = 9 — VALID
    • x = −3: (−3)² = 9 — VALID

    The provided answer key only includes x = 3, omitting the equally valid solution x = −3.

    3. Quality Assessment

    Finding: Incomplete answer key.

    Severity: BLOCKER

    Impact: Students who correctly identify both solutions may be penalized if the grading process relies on the incomplete answer key.

    The question itself is mathematically valid. The error is in the provided answer key.

    4. Recommended Correction

    Replace the original answer key with

    x = −3 or x = 3

    No modification to the original question is necessary.

    5. Verification and Limitations

    The equation was solved independently using mathematical factorization.

    During functional testing, the skill's Python exact-arithmetic helper confirmed that both 3 and −3 satisfy the original equation.

    The helper verified numerical substitutions; it did not perform a general symbolic proof.

    Final Recommendation

    DO NOT RELEASE

    Correct the answer key and review the updated assessment before publication.

    Audit summary: 1 question reviewed, 1 blocking issue identified, 1 answer-key correction recommended.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Stop answer-key mistakes before students see them.

    Math Exam Quality Guard transforms your AI agent into a structured quality reviewer for mathematics exams, worksheets, quizzes, and AI-generated assessments.

    Instead of blindly trusting an answer key, the skill guides the agent through independent mathematical solutions, domain checks, alternative verification, and evidence-based reporting.

    What it checks

    • Incorrect or incomplete answer keys
    • Multiple correct answers in single-choice questions
    • Equivalent alternatives, such as 3/5 and 60%
    • Extraneous roots and missing domain restrictions
    • Mathematical contradictions and impossible conditions
    • Ambiguous notation and missing assumptions
    • Missing or unreadable diagrams
    • Units, rounding, and basic pedagogical clarity

    What you receive

    A structured audit report containing:

    • Question-by-question classification: PASS, FAIL, NEEDS_REVIEW, or INSUFFICIENT_INFORMATION
    • Issue severity and mathematical justification
    • Independent solutions and answer-key comparisons
    • Recommended corrections
    • Final release recommendation

    Included tools

    The package includes a safe Python exact-arithmetic helper, review rubrics, mathematical checklists, worked examples, and a reusable reporting template.

    No paid APIs, external subscriptions, or additional Python packages are required.

    Tested with Codex

    The initial version completed two functional test batches involving 11 mathematics questions, with all expected classifications obtained.

    Important limitations

    This skill supports mathematical quality assurance but is not a formal theorem prover or a guarantee of error-free exams.

    Advanced symbolic reasoning and diagram analysis depend on the capabilities of the AI agent and its available tools. High-stakes assessments should receive independent review by a qualified mathematics educator.

    Built by Tecérale AI Skills.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Education & Learning.

    Cannot audit unreadable diagrams or images. Cannot provide formal proofs for complex calculus or irrational radicals. Requires manual verification for high-level pedagogy or styling.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 6 days ago

    Nothing to install. It runs in your AI agent.

    Optional
    Python 3

    Python 3 is optional for exact-arithmetic verification. Without Python, the skill can still perform reasoning-based audits. Human review is recommended for high-stakes assessments.

    Permissions

    Terminal / Shell
    Read Files
    Listed6 days ago

    What's inside

    Frequently Asked Questions

    This skill solves the problem of 'key-blindness' by performing a mandatory independent solve of every problem before checking the key, ensuring that typos, missing variables, or multiple correct answers are caught before the exam reaches students.

    The skill is designed for file-aware environments like Claude Code or Cursor that support file analysis and code execution, allowing it to process entire question banks and run exact-arithmetic Python scripts.

    You will receive the structured workflow instructions, the Python-based exact arithmetic module for verification, and the standardized error categorization rubric for generating your audit reports.

    The skill supports questions formatted in standard text, Markdown, and LaTeX; however, it cannot audit visual diagrams or handwritten images unless your specific AI agent environment includes vision capabilities.

    Simply import the skill into your preferred AI development environment and point it toward your exam files; the setup includes a brief initialization step to inventory your question stems and claimed keys.

    New in Education & Learning