CQ

    chart quality reviewer

    1

    Audits academic charts for label errors, truncated axes, and formatting defects using a structured risk report.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more
    CQ

    chart quality reviewer

    Example session with this skill installed

    Review a grouped bar chart for an academic submission. X-axis: Years (2018-2022), Y-axis: Growth rate. Legend: Series A (Blue), Series B (Red). The Y-axis starts at 5% to show the difference better.

    • Read your context and instructions
    • Compiled the chart quality reviewer

    I have audited the grouped bar chart description against academic publication standards. The review identified one severe error regarding the axis baseline and a suggested improvement for accessibility.

    Chart Quality Review Report

    CategoryFindingRisk LevelFix Suggestion
    Axis BaselineY-axis baseline is truncated (starts at 5%).Severe ErrorReset the Y-axis baseline to 0. Truncated axes exaggerate small differences and are considered misleading in academic contexts.
    Physical UnitsY-axis label "Growth rate" is missing specific units.Severe ErrorAppend the unit to the axis label, e.g., "Growth Rate (%)" or "Growth Rate (decimal)".
    AccessibilityBlue/Red color palette used for Series A and B.Suggested ImprovementReplace with high-contrast, color-blind friendly colors (e.g., Blue/Orange) or use distinct hatch patterns to differentiate bars.
    LegendSeries are identified but lack descriptive context.Suggested ImprovementEnsure the legend or caption explicitly defines what "Series A" and "Series B" represent (e.g., Control vs. Treatment).

    Summary
    This chart contains

    Severe formatting errors that are likely to cause a reviewer return. The most critical issue is the non-zero Y-axis baseline on a bar chart, which is a violation of standard data visualization ethics in academic publishing.

    Next steps

    1. Update the plotting code to set ylim(0, ...) for the Y-axis.
    2. Explicitly define the units in the axis label string.
    3. Change the color hex codes to a CVD-safe palette.

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

    About this skill

    Academic manuscripts and course reports often get rejected or flagged for avoidable chart formatting errors. This skill audits your statistical charts against academic publication standards to ensure labels, units, and axes meet rigorous submission requirements.

    What it does

    • Axis audit checks for missing labels, physical units, and baseline truncation issues.
    • Legend verification ensures every data series is clearly defined and explained.
    • Accessibility review identifies color palettes that may be unfriendly to color-blind readers.
    • Risk grading classifies findings into severe errors that mislead readers and minor polish improvements.
    • Actionable fixes provides specific instructions to correct every identified presentation defect.

    How it works

    1. Input description by providing your chart type, axis details, and legend information via text.
    2. Rule matching compares your chart structure against a fixed library of academic standards.
    3. Risk assessment categorizes every discrepancy by its impact on clarity and publication status.
    4. Report generation produces a structured review document with specific remediation steps.

    Frameworks & tools

    This skill utilizes a Python-based review helper to process chart metadata and applies standardized rules for academic formatting and data visualization ethics.

    Why this beats prompting it yourself

    Generic prompts often miss subtle academic requirements like physical unit notation or Y-axis baseline integrity. This skill uses a deterministic rule-based logic to ensure no presentation standard is overlooked during the review.

    Use cases

    • Reviewing thesis charts before final submission to a committee.
    • Checking manuscript figures for journal peer-review readiness.
    • Auditing student course reports for proper statistical visualization.
    • Verifying accessibility and clarity of grouped data plots.

    Known limitations

    Does not support image recognition or direct file uploads. User must provide text descriptions of chart elements. Statistical accuracy of the underlying data is not audited.

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

    Requires text description of chart elements; no image recognition. Does not audit statistical math or generate plotting code. Scope limited to 2D academic charts.

    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 today

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Listedtoday

    What's inside

    Frequently Asked Questions

    This skill identifies formatting defects that lead to rejection, such as truncated Y-axes, missing physical units, and color-blindness accessibility issues that manual reviews often overlook.

    No, you do not need to upload images. This skill audits the structure and metadata of your chart—such as labels, legend text, and axis scales—based on text descriptions you provide.

    The purchase includes the full logic for the 'Chart Quality Reviewer' skill, integration with its Python-based review helper, and the standardized library of academic formatting rules.

    This skill is designed for any AI agent capable of executing Python-based tools and can be integrated into your existing research or writing workflow on supported platforms.

    The skill evaluates the presentation, clarity, and ethical visualization of your chart, but it does not verify if the underlying statistical calculations or raw data points are accurate.

    Your purchase includes access to any future updates to the rule library, ensuring your charts remain compliant with evolving academic and accessibility standards.

    Free