Design and analyze Claude-Light remote experiments with RGB inputs and spectral measurements.
npx skills add https://github.com/jkitchin/skillz --skill claude-light
Please help me install this Agent Skill. Skill: claude-light Source: https://github.com/jkitchin/skillz/tree/main/skills/programming/claude-light Command: npx skills add https://github.com/jkitchin/skillz --skill claude-light
Facilitates design and analysis of experiments using Claude-Light's RGB LED and spectral sensor, with data-handling, regression, optimization, and DOE workflows.
Use the Claude-Light API to run a 3-variable DOE with R, G, B in [0,1], collect spectra, and fit a simple linear model to a single channel.
High-intent search queries and answers about installing and using this skill.
Design-of-experiments (DOE) workflows optimize RGB inputs (R, G, B values 0–1) to target specific spectral outputs across ten channels (415nm to NIR). This Skill sweeps RGB combinations, collects spectra via the Claude-Light API, fits regression models to predict channel responses, and identifies optimal input settings for your desired measurement outcomes.
Yes. Regression modeling ingests RGB inputs and spectral measurements from all ten Claude-Light channels, computes statistical summaries (means, variance, confidence intervals), and builds predictive models. Results quantify how each RGB value drives response in target channels, enabling data-driven optimization.
Claude-Light provides ten spectral measurement channels—415nm, 445nm, 480nm, 515nm, 555nm, 590nm, 630nm, 680nm, clear, and near-infrared (NIR)—and accepts RGB inputs normalized to [0, 1]. This range covers visible and near-infrared wavelengths for material and biological characterization.
Collect spectra by sweeping RGB inputs via the Claude-Light API, then visualize response surfaces and build predictive models using Python data-science libraries. Surfaces show how spectral output varies across the RGB input space, revealing optimization targets and interaction patterns.
Basic familiarity with regression, optimization, and DOE concepts helps, but this Skill handles statistical computation—confidence intervals, model fitting, and optimization logic—using standard Python libraries. Start with a simple three-variable DOE (R, G, B) and linear model to a single channel.
Plan sweeps by defining the RGB input space (typically [0, 1] per channel), choosing a DOE strategy (factorial, response-surface, or custom grid), and mapping measurement points. This Skill automates API calls, data collection, and statistical analysis once the experimental grid is specified.
PiaoxuemoliExecute Python code incrementally with a stateful Jupyter kernel.
ncssm-roboticsProvide live telemetry dashboards and real-time configurables for FTC robots.
pluginagentmarketplacePerform descriptive statistics, hypothesis tests, and regression analysis with Python libraries.
naporin0624Document APC Mini MK2 velocity-to-color mappings and SysEx RGB encoding.
