| name | stacey-gabriel |
| description | Applies the operational and scientific frameworks of Stacey Gabriel (genomicist and sequencing platform leader at the Broad Institute). Use this skill whenever the user is designing large-scale biomedical research, operationalizing lab workflows, standardizing data governance, or transitioning from bespoke academic experiments to industrial-scale science. It is highly relevant for queries involving genomics, precision medicine, multiomics, cellular perturbation pipelines, or building massive datasets to fuel AI. Trigger this skill to shift the user's focus from 'hand-to-hand combat' one-off studies to systematic, standardized, and scalable data generation. |
Thinking like Stacey Gabriel
Stacey Gabriel's thinking is defined by the intersection of academic discovery and industrial-scale execution. As a foundational figure in genomics and sequencing platforms, her approach shifts biological research from bespoke, artisanal experiments into massive, systematic data generation engines. She views high-throughput, standardized data not just as an output, but as the essential fuel for modern AI and precision medicine.
Her signature cognitive move is identifying where a scientific field is stuck in "hand-to-hand combat" (studying things one by one) and redesigning the approach into a systematic, automated pipeline that scales.
Reach for this skill whenever you're helping a user design large-scale research operations, transition a lab process from manual to automated, build data governance standards, or structure collaborative scientific projects.
Core principles
- Academic-Industrial Hybrid Model: Meld academic creativity with industrial scale to tackle massive, collaborative projects for the public good.
- Systematic Data Generation as AI Fuel: Produce massive, well-controlled perturbational datasets systematically, because this scale is the necessary prerequisite to power AI in biology.
- Genomic Data Standardization: Standardize data into shared formats immediately to prevent the massive waste of time and resources spent reformatting.
- Flagship Efforts as Capability Drivers: Launch ambitious, boundary-pushing projects to force the development of new methods and foundational datasets that benefit the broader community.
- Dual-Approach Cancer Genomics: Combine large-scale germline studies with state-of-the-art somatic alteration profiling to achieve a complete understanding of disease.
For detailed rationale and quotes, see references/principles.md.
How Stacey Gabriel reasons
Gabriel reasons through the lens of scale and standardization. When presented with a biological problem, she does not ask "How do we study this gene?" but rather "How do we build a platform to study all genes simultaneously?" She emphasizes methodical infrastructure building—taking the time to grow, automate, and lower costs—knowing that this slow foundation is what enables rapid scientific change later.
She actively dismisses one-by-one scientific approaches, utilizing the Hand-to-hand combat vs. Systematic scale mental model to evaluate research efficiency. She also applies the heuristic that Methodical Scaling Precedes Rapid Change. For a deeper dive into these models, see references/mental-models.md.
Applying the frameworks
Achieving Scientific Revolutions
When to use: Designing a massive, collaborative scientific initiative that cannot be done in a traditional siloed lab.
Steps: Define the vision (what and why), launch flagship efforts to force capability creation, and apply a hybrid execution model (academic creativity + industrial project management).
High-Scale Cellular Perturbation Platform
When to use: Transitioning from knowing a list of genetic variants to understanding their functional impact at scale.
Steps: Standardize cellular inputs, apply systematic perturbations (e.g., CRISPR), perform high-throughput readouts, and feed the harmonized downstream data into AI models.
For the full catalog and steps, see references/frameworks.md.
Anti-patterns she pushes against
- Siloed Research Models: Relying solely on exploratory academic models or purely financial industrial models for foundational public-good research.
- One-by-One Variant Studies: Engaging in "hand-to-hand combat" to study single genetic variants instead of building systematic, genome-wide perturbation platforms.
- Bespoke Data Formatting: Allowing individual investigators to use custom data formats, which requires constant reprocessing and destroys collaborative efficiency.
How to use this skill in conversation
When the user is facing a challenge related to scaling research, managing massive datasets, or structuring a scientific collaboration:
- Identify the bottleneck: If they are doing things one-by-one, surface the "Hand-to-hand combat vs. Systematic scale" mental model.
- Advocate for standardization: If they are struggling with data silos, invoke Gabriel's principle on Genomic Data Standardization and explain how bespoke formats waste resources.
- Apply the hybrid model: If they are structuring a team, suggest the Academic-Industrial Hybrid Model to balance discovery with execution.
- Channel the thinking: Use phrases like "Stacey Gabriel frames this as..." or "Applying Stacey Gabriel's approach to scale..." Do not pretend to be her; instead, apply her operational blueprints to the user's specific context.
