Map biology and ML problems to Daphne Koller's frameworks for workflow-ready plans.
npx skills add https://github.com/K-Dense-AI/mimeographs --skill daphne-koller
Please help me install this Agent Skill. Skill: daphne-koller Source: https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/daphne-koller Command: npx skills add https://github.com/K-Dense-AI/mimeographs --skill daphne-koller
This Skill helps agents emulate Daphne Koller's pragmatic, cross-disciplinary approach to AI in biology and drug discovery, enabling teams to design fit-for-purpose data, bridge domain experts and engineers, and reason about causality vs. correlation in real-world systems.
Outline a data-generation plan for a biology project using Daphne Koller's "Data Printing Factory" approach to generate high-quality, domain-specific data for ML.
High-intent search queries and answers about installing and using this skill.
Designing a data generation plan for drug discovery involves mapping a problem to an interdisciplinary AI approach that builds a structured end-to-end pipeline. This plan emphasizes fit-for-purpose data, cross-functional roles, and specific success metrics for evaluating therapeutic hypotheses.
Structuring cross-functional teams for biology and machine learning projects requires fostering bilingual professionals who bridge domain experts and engineers. This approach aligns incentives, avoids data-siloing, and ensures the team can design data pipelines and reason about causality versus correlation.
Yes, evaluating causality versus correlation in biomedical data is a core application of this approach. It applies pragmatic AI-for-biology reasoning to real-world systems, helping teams move beyond elegant models to generate high-quality, domain-specific data that supports valid causal inference.
You need fit-for-purpose data for interdisciplinary AI applications when working at the intersection of biology and product development. It is required for forming cross-functional teams, designing data pipelines, and ensuring your machine learning models rely on high-quality, domain-specific data rather than generic datasets.
Building a data pipeline for biotech product development involves applying a data-generation factory approach to structure your workflow. You map therapeutic hypotheses to an end-to-end pipeline, defining specific data modalities, team roles, and success metrics throughout the process.
Interdisciplinary dataset design for real-world systems requires significant alignment between domain experts and engineers to avoid data-siloing. Limitations include the challenge of fostering bilingual professionals and the need to prioritize pragmatism over model elegance to ensure data quality and relevance.
hsigstadGenerate a new data pipeline directory structure with boilerplate documentation.
jmaglyAnalyze architecture change impact and generate ADRs and migration plans.
patrikboroschMigrate Synapse Data Factory pipeline artifacts to Microsoft Fabric Data Factory.
xlelibertyDesign experiments and build machine learning pipelines with Python.
