Gabriel Asher
Community@gaasher
Senior Machine Learning Scientist @matterworksbio || Dartmouth '24 || DHMC Radiation Oncology Researcher
Agent Skills by Gabriel Asher
Showing 25 vetted skills indexed across 1 GitHub repositories.
research-question
Refine broad topics into specific research questions using rubric scoring and novelty checks.
claim-verify
Verify data-backed claims from markdown documents against datasets.
purple-team
Orchestrate red-team attacks and blue-team patches for security guardrails and APIs.
research-proposal
Evaluate and rewrite research proposals with iterative, literature-grounded feedback requiring Python 3.9+ and literature-search skill.
red-team
Generate adversarial inputs and log discrepancies between target systems and oracles.
hypothesis-gen
Generate literature-grounded research hypotheses using a multi-agent loop.
anomaly-investigation
Identify root causes of data anomalies by testing candidate causes.
scientific-writer
Coordinate expert judges, an independent grader, and a revising author to refine scientific writing.
tournament-autoresearch
Automate machine learning research with a tournament loop for architecture changes.
plan-loop
Decompose coding prompts into structured execution plans with schema validation.
blue-team
Apply patches to fix code failures from CI/CD test reports and create pull requests.
karpathy
Iterate training script changes to minimize a scalar metric.
swe-loop
Automate iterative coding task execution and verification with feedback loops.
tabular-cleanup
Automate iterative cleaning of tabular data to meet an inferred data contract.
scientific-figure
Generates publication-quality scientific figures from data using Python.
prompt-optimize
Iteratively refine prompts against custom evaluation metrics.
data-analysis
Run iterative hypothesis testing and re-computation for reproducible data analysis.
literature-search
Search academic papers and extract experimental results via citation graph traversal.
optimize-loop
Iteratively refine code modules or SQL queries under correctness constraints.
ml-autoresearch
Iteratively optimize machine learning models by analyzing behavior and integrating literature.
alpha-evolve
Automate population-based evolution of ML models within a fixed compute budget.
exploratory-autoresearch
Iteratively optimize machine learning experiments with exploration-first techniques in Python 3.9+.
dueling-autoresearch
Compare two approaches over time on a shared metric with Python 3.9+.
literature-survey
Automate literature surveys by iterating searches and synthesizing findings into an evidence/contradiction matrix.