Step 2: Protect the parts only you can do.

Defend

Once decomposition has handed AI the chores, what remains is the methodological judgment AI cannot yet replicate — knowing when an analysis plan is statistically optimistic, when a regulatory submission has a subtle methodological flaw, when a trial design is underpowered for the actual question. Defend track covers academic-to-industry transitions, demonstrating ROI to non-PhD managers, managing visa status risk, and building the operational resilience to survive a volatile bio/pharma job market.

Data Defend

obra/superpowers

/test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

tddtestingengineering
Data Defend

obra/superpowers

/systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

debuggingengineeringroot-cause
Data Defend

obra/superpowers

/requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

code-reviewcommunicationprofessional
Data Defend

obra/superpowers

/receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

code-reviewfeedbackcommunication
Data Defend

skillcreatorai/Ai-Agent-Skills

/code-review

Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.

code-reviewengineeringquality
Data Defend

sickn33/antigravity-awesome-skills

/code-review-checklist

Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability

code-reviewengineeringchecklist