brycewang-stanford

Provides guidance on using the marginaleffects R and Python package for statistical model interpretation and causal inference.

Provides guidance on writing effective introductions for academic economics papers, enhancing clarity and engagement for readers.

This skill verifies the integrity and replicability of academic papers by auditing code, tables, and quantitative claims against source R scripts.

Provides a systematic debugging workflow for investigating and resolving code errors, exceptions, and failures.

Facilitates structured literature research in Industrial AI, focusing on predictive maintenance and smart manufacturing with tailored outputs.

Facilitates comprehensive audits of academic papers in LaTeX, Typst, and PDF formats, ensuring submission readiness and structured revisions.

Assists in compiling and auditing Typst academic papers, ensuring format compliance, grammar checks, and bibliography validation.

Facilitates literature reviews in communications research, retrieving relevant papers from various databases and local sources.

Facilitates autonomous design space exploration for computer architecture, optimizing parameters iteratively until objectives are met.

Facilitates the implementation and deployment of experiments from a structured plan, ensuring efficient GPU resource usage and initial result collection.

Generates and ranks research ideas based on user-defined directions, facilitating the exploration of publishable research topics.

Facilitates robotics idea discovery through a structured workflow, generating benchmark-grounded concepts for embodied AI applications.

Facilitates a comprehensive idea discovery process, transforming research directions into validated, pilot-tested ideas through a structured workflow.

This skill verifies the novelty of research ideas against recent literature, ensuring innovative contributions before implementation.

Generates pixel art SVG illustrations for documentation and presentations, enhancing visual appeal with customizable characters.

Generates rigorous mathematical proofs for ML/AI theories, ensuring clarity and correctness in formal arguments.

Facilitates the drafting of compliant rebuttals for academic submissions, ensuring coverage of reviewer concerns and adherence to venue limits.

Facilitates in-depth critical reviews of research projects using GPT via Codex MCP, enhancing feedback and experimental design.

Facilitates deployment and execution of ML experiments on local or remote GPU servers, optimizing resource usage and workflow.

Automates health checks during model training by monitoring WandB metrics to prevent wasted GPU hours on faulty runs.