karpathy-guidelines
Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
434 skills found
Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.
Parallelize independent debugging or development tasks by delegating to specialized subagents with isolated context.
Manage PR review workflows, resolve threads, and handle discussion comments using specialized erk exec commands.
A professional UI/UX design guide for web and mobile. Features 50+ styles, 99 UX guidelines, and 97 color palettes. Supports multi-stack recommendations for React, Vue, Next.js, and more.
System detection and cross-platform command execution engine for managing OS-specific infrastructure and development environments.
Audit and validate Claude Code plugins for structural integrity, manifest compliance, and best practice adherence to ensure reliable agent and skill performance.
Decompose financial variances into drivers with narrative explanations and waterfall analysis. Optimize budget vs. actual reporting, P&L commentary, and forecast reconciliation.
Automated code review for STYLY-NetSync, enforcing protocol parity, thread safety, and Unity C#/Python conventions.
Validates Excel exports for Customer Feedback Analyzer with 7 specific view sheets, 36 columns, and precise color-coded formatting. Ensures zero errors in customer-facing deliverables.
Automate PR quality checks by reviewing CodeRabbit comments, validating PR descriptions, running pre-commit hooks, and executing test suites.
Native macOS/iOS app performance profiling via xctrace and CLI-based hotspot analysis without opening the Instruments UI.
Creative research ideation partner for exploring interdisciplinary connections, challenging assumptions, and generating testable scientific hypotheses.