Analyzes ML literature and synthesizes evidence-based research plans.
npx skills add https://github.com/henrycashe26/my_skills --skill ml-research-henrycashe26
Please help me install this Agent Skill. Skill: ml-research Source: https://github.com/henrycashe26/my_skills/tree/main/ml/ml-research Command: npx skills add https://github.com/henrycashe26/my_skills --skill ml-research-henrycashe26
This skill solves the problem of information overload and lack of focus when exploring complex machine learning topics, helping you move from a vague question to a concrete, actionable research plan.
Use the ml-research skill to survey the current state-of-the-art techniques for ternary weight quantization in transformer models and build a knowledge base.
High-intent search queries and answers about installing and using this skill.
To conduct a literature review for machine learning model architectures, systematically evaluate academic papers and GitHub repositories to identify landmark research threads and current state-of-the-art techniques. This process extracts critical implementation details and empirical performance metrics to form an evidence-based knowledge base.
Mapping the landscape of state-of-the-art techniques involves surveying current academic papers and empirical performance metrics to identify key research threads. This synthesis generates a structured knowledge base detailing landmark architectures and training methodologies for your specific subfield.
Yes, you can compare quantization, distillation, and pruning techniques by systematically evaluating academic literature and empirical performance metrics. This process synthesizes critical implementation details and failure modes to provide evidence-based recommendations for optimizing transformer models.
Building a knowledge base for machine learning implementation requires synthesizing findings from academic papers into structured research documents. It extracts critical implementation details, hyperparameter sensitivities, and failure modes, converting vague questions into actionable experiments.
Limitations of automated literature reviews include missing nuanced failure modes and hyperparameter sensitivities buried in academic papers. Systematic manual evaluation of empirical performance metrics and GitHub repositories is often required to ensure accurate, evidence-based model architecture recommendations.
matthew-johnsonDraft ML research papers with structured citations and reproducibility artifacts.
handsomelong922Translate specifications into structured implementation plans with tasks and file changes.
henrique-simoesSummarize research literature into source-backed Nuggets, Facts, Insights, and Recommendations.
ragnarokhaaAutomate ML/AI research paper writing with literature review and citation verification.
