1306+ expert skills across 17 categories

Expert guidance on Git merge strategies and their implications for team workflows. Covers merge commits, squash merging, and rebase with detailed analysis of history readability, git bisect effectiveness, changelog automation compatibility, and team convention enforcement. Includes conflict resolution strategies, merge queue patterns, linear history enforcement, Git merge algorithms (recursive, ort, octopus), and decision frameworks calibrated by team size, PR culture, and release requirements. Grounded in DORA research and GitHub/Atlassian documentation.

Expert guidance for monorepo management at scale. Covers Nx and Turborepo selection, CODEOWNERS configuration, path-based CI triggers, dependency graph analysis, build caching strategies, task orchestration, selective testing with affected computation, release versioning with Changesets, and merge queue patterns. Provides team-size-aware recommendations grounded in DORA research, from solo developers through 200+ engineer organizations.

A meta-skill that makes AI coding assistants think strategically before acting. Implements a 5-factor risk heuristic (Reversibility, Blast Radius, Coupling, Stakes, Uncertainty) to determine whether a code change needs shallow execution, medium analysis, or deep pre-mortem reasoning. Based on cognitive science, game theory, and software engineering economics research.

Expert guidance for designing production-grade Zod schemas with TypeScript type inference, schema composition, error handling, and full-stack integration patterns.

Master XGBoost for tabular data problems including hyperparameter optimization, feature engineering, SHAP-based interpretability, and production deployment with drift monitoring.

A generalist skill that helps users interact with AI safely across all sensitive domains. Covers health, finance, legal, mental health, nutrition, parenting, relationships, and general AI literacy. Teaches critical evaluation of AI outputs, recognizes when professional help is needed, and prevents over-reliance on AI for consequential decisions.