Analyze and synthesize signals in the frequency domain using FFT and wavelet transforms.
npx skills add https://github.com/garochee33/DSH --skill frequency-garochee33
Please help me install this Agent Skill. Skill: Frequency Source: https://github.com/garochee33/DSH/tree/main/kb/skills/frequency Command: npx skills add https://github.com/garochee33/DSH --skill frequency-garochee33
This Skill helps you understand, generate, and manipulate signals in the frequency domain, making it easier to analyze patterns, resonance, and wave behavior that are hard to see in raw time-series data.
Ask the Frequency skill to compute the FFT spectrum of your signal and summarize the dominant frequencies in plain language.
High-intent search queries and answers about installing and using this skill.
To compute the FFT spectrum of a time-series signal, you apply a Fast Fourier Transform to convert raw waveform data into the frequency domain, identifying dominant peaks and spectral content for analysis.
Yes, you can model resonance and standing waves from raw waveform inputs by synthesizing harmonic stacks and applying wavelet transforms to visualize cymatics and specific frequency band behaviors.
The best way to classify signal data into known frequency bands is to perform spectral analysis using FFT, compare the extracted dominant peaks against predefined taxonomies like brainwave bands or Schumann resonance, and categorize accordingly.
Yes, signal processing in the frequency domain requires numerical waveform synthesis support to execute FFT, wavelet transforms, and frequency band definitions accurately within scientific and audio workflows.
You use wavelet transforms instead of FFT for spectral inspection when you need to analyze localized, non-stationary signal patterns in the frequency domain, whereas FFT is better suited for identifying global dominant frequencies.
GuitarAlchemistAnalyze and transform signals using FFT, filtering, wavelets, and Kalman filters.
dailycafiProcess GC-MS raw data into deconvolved spectra and library-matched compound annotations.
guccangGenerate spectrograms and feature visualizations from audio files.
GeneralReasoningDetect gravitational-wave signals in noisy detector data using PyCBC matched filtering.
