EA

    English Assessment 1

    0

    Companion-style English proficiency test at CEFR B1-C2: adaptive difficulty, random papers of 7-10 question types, silent scoring, mistake collection and weak-area analysis.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more
    EA

    english-assessment

    Example session with this skill installed

    Test my English level / give me an English assessment.

    • Read your context and instructions
    • Compiled the english-assessment

    A scored test report with CEFR level estimate, weak-area breakdown, and a saved mistake notebook for retests.

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

    About this skill

    A companion-style English proficiency assessment skill at college level (CEFR B1-C2). Generates random test papers (default 25-40 questions or quick 21, 7-10 question types from a pool of 12, 100 points total) covering vocabulary, grammar, multiple choice, error correction, reading comprehension and translation. Adaptive difficulty based on history. Silent scoring during the test, then a final score with weak-area analysis. Supports a mistake notebook, mistake retests, explanations, full question deep-dives, learning progress tracking, and data import/export. Security notes: no dynamic code execution, no data exfiltration (all data stays local), tool scope declared via allowed-tools. Works with Claude Code, Cursor, OpenClaw, Codex and any agent that reads SKILL.md.Security: read-only public question-bank fetches only, no localhost calls, no credential operations, no user data uploads. All outbound hosts documented in SKILL.md Network Access Disclosure.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    No audio support for listening exams. Requires local file access for progress persistence. Initial difficulty defaults to B1-C1 if no history exists.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 14 days ago

    • Free with an Agensi account

    Permissions

    Network Access
    Listed14 days ago

    What's inside

    Frequently Asked Questions

    Unlike static prompts, this skill uses local state management to remember your mistakes and ensure you aren't tested on the same vocabulary or grammar points too frequently, providing a structured curriculum rather than random questions.

    The skill is optimized for Feishu/Lark environments and requires local filesystem permissions to store your JSON progress records and error banks.

    The skill covers CEFR levels from B1 (Intermediate) to C2 (Proficient) and includes 12 question types, such as reading comprehension, translation, and grammar, modeled after exams like the CET, GRE, and CAE.

    Your purchase includes the full adaptive testing logic, integrated web-search capabilities for real-time exam sourcing, and the persistent error-tracking system for long-term progress analysis.

    Currently, this skill is focused on text-based proficiency, including reading and writing; it does not support audio-based listening exercises or live oral speaking evaluations.

    Free