Readable Code Review

    1

    Review code readability across eight dimensions with source evidence and focused recommendations.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    Review Python files, modules, and repositories from the perspective of someone taking over the code. Readable Code Review checks naming, control flow, data and state, abstraction, shared knowledge, implementation mechanisms, documentation, and local expression.

    Findings include source evidence, reading costs, reasonable exceptions, and focused improvement suggestions. Each applicable dimension receives its own 0-3 grade; missing context is stated explicitly, and grades are not combined into a total score.

    The review reads source without executing candidate code. Functional correctness, performance, and security are outside the scoring scope. Invoke it explicitly for a stage review or code handover.

    Includes the rubric in Markdown and JSON, references, and Codex metadata. Instructions and reference materials are written in Chinese. Free and MIT licensed, with no scoring API or runtime dependency required.

    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 any payment.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Read Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill evaluates code across eight dimensions—including naming, abstraction, and shared knowledge—to identify 'reading costs' that make maintenance difficult for new developers.

    This skill is designed specifically for Python codebases, ranging from individual files to full modules and repositories.

    No, the agent performs a static analysis of the source code without execution, ensuring a safe review process that doesn't require a sandbox or runtime dependencies.

    You will receive the full rubric in Markdown and JSON formats, comprehensive reference materials, and Codex metadata, all written in Chinese for clear integration.

    The skill provides individual grades (0-3) for each of the eight dimensions rather than a single total score, allowing you to identify specific areas for improvement without masking nuance.

    Because the skill is MIT licensed and has no API dependencies, you can easily integrate it into any AI agent platform that supports custom instructions and Markdown/JSON reference materials.

    New in Code Quality & Review

    Free