Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    banger r runner

    1

    You have data to analyze but no local R environment, or you are blocked from installing new packages on a locked-down machine.

    Free

    Security scanned
    banger r runner

    banger r runner

    Example session with this skill installed

    Run a quick linear regression on the built-in mtcars dataset comparing mpg to wt and hp, and show me the summary and a scatter plot.

    • Read your context and instructions
    • Compiled the banger r runner

    I have executed the regression analysis on rdrr.io using R 4.0.3. The analysis used the built-in mtcars dataset to model the relationship between fuel efficiency, weight, and horsepower.

    Linear Regression Analysis: mtcars

    The model shows that both weight (wt) and horsepower (hp) are significant predictors of miles per gallon (mpg), with weight having the stronger negative impact.

    | Predictor | Estimate | Std. Error | t value | Pr(>|t|) |
    | :--- | :--- | :--- | :--- | :--- |
    | (Intercept) | 37.2273 | 1.5988 | 23.285 | < 2e-16 *** |
    | weight (1000 lbs) | -3.8778 | 0.6327 | -6.129 | 1.12e-06 *** |
    | horsepower | -0.0318 | 0.0090 | -3.519 | 0.00145 ** |

    Residual standard error: 2.593 on 29 degrees of freedom
    Multiple R-squared: 0.8268, Adjusted R-squared: 0.8148

    
    # R Script executed on rdrr.io
    library(ggplot2)
    set.seed(42)
    
    # Model summary
    model <- lm(mpg ~ wt + hp, data = mtcars)
    print(summary(model))
    
    # Visualization
    p <- ggplot(mtcars, aes(x = wt, y = mpg, color = hp)) +
      geom_point(size = 3) +
      geom_smooth(method = "lm", formula = y ~ x, se = FALSE, color = "black") +
      labs(title = "Fuel Efficiency vs Weight and Horsepower",
           x = "Weight (1000 lbs)", y = "MPG") +
      theme_minimal()
    print(p)
    
    cat("\nSession Info:\n")
    print(sessionInfo())
    

    Next steps

    • Review the Residuals vs Fitted plot to check for non-linearity.
    • Add an interaction term wt * hp to see if the effect of weight changes at higher horsepower.
    • Test the model against the cars or iris datasets for different statistical patterns.

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

    About this skill

    You have data to analyze but no local R environment, or you are blocked from installing new packages on a locked-down machine. This skill allows your agent to write and execute R code via the rdrr.io Snippets service, providing instant access to ~19,800 CRAN and Bioconductor packages without local configuration.

    What it does

    • Instant execution writes and runs R scripts on a remote server with no local dependencies.
    • Statistical analysis performs t-tests, regressions, ANOVA, and survival analysis using established libraries.
    • Data visualization generates and returns PNG plots from ggplot2 or base R graphics.
    • Package testing evaluates CRAN or Bioconductor packages before you commit to a local installation.
    • Simulation runs power calculations and Monte Carlo simulations within a 60-second execution window.

    How it works

    1. Script generation creates an R script using R 4.0.3 syntax, ensuring compatibility with the remote environment.
    2. Execution sends the script and any inline data to the rdrr.io public API for processing.
    3. Result retrieval captures the console output, warnings, and generated plot images.
    4. Reporting presents the statistical interpretation, the raw output, and the full script for your records.

    Frameworks & tools

    The skill utilizes R 4.0.3 with a library of nearly 20,000 packages including ggplot2, dplyr, survival, and Bioconductor tools. It interfaces with the rdrr.io service using a Python-based runner.

    Why this beats prompting it yourself

    Writing R code that actually runs on a 2020-era remote server requires specific knowledge of version-locked syntax, like avoiding the native pipe operator. This skill handles the environment-specific boilerplate, package checks, and plot retrieval that a standard LLM often gets wrong.

    Use cases

    • Run quick regressions or statistical checks on small datasets.
    • Generate high-quality plots when you only have access to a tablet or browser.
    • Verify textbook examples or statistical claims using a clean R environment.
    • Prototype complex Bioconductor workflows before setting up a local pipeline.

    Known limitations

    All data sent is public. No internet access from within scripts. Limited to R 4.0.3 syntax and 60 seconds of compute. Data must be provided inline (under 200 KB).

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

    Data and scripts are public. Requires R 4.0.3 syntax (no native pipe). 60s timeout. Max 200KB inline data. No outbound network access from R.

    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 4 days ago

    • Free with an Agensi account

    Accounts
    Rdrr
    Software
    Python
    Optional
    Browser

    Free, as R should be! Optional: Browser automation (fallback only).

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    Allowed Hosts

    rdrr.io
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    This skill eliminates the need for a local R installation or manual package management by executing code via the rdrr.io service, providing instant access to nearly 20,000 CRAN and Bioconductor packages directly within your agent workflow.

    The skill uses R version 4.0.3 and includes a massive library of ~19,800 packages, including popular tools like ggplot2, dplyr, and the Bioconductor suite for bioinformatics.

    Yes, the skill is specifically designed to capture and return PNG images generated by ggplot2 or base R graphics, displaying them alongside the console output in your agent's interface.

    Because the skill utilizes the public rdrr.io Snippets service, you should only process non-sensitive data; additionally, scripts must complete within 60 seconds and data must be provided inline (under 200 KB).

    No local R environment or API keys are required; once the skill is added to your agent, it handles all the boilerplate, environment-specific syntax, and remote execution automatically.

    No account needed Code runs on the free public rdrr.io Snippets service, so the agent needs internet access to rdrr.io. Python only runs the small bundled runner; no R install required.

    New in Research & Analysis

    Free