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.
265 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.
AWS DynamoDB engineering assistant for schema design, query optimization, single-table patterns, and infrastructure management using Boto3 and AWS CLI.
Autonomous agent for ticket-driven development, managing the full software lifecycle from polling providers to automated PR creation with ERNE standard validation.
A Zod schema generation and validation rule set for the HASH intelligent database ecosystem to ensure type safety and data integrity.
Build targeted prospect lists by analyzing public LinkedIn profiles and business data to identify decision-makers, track career moves, and enrich leads for outreach.
Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.
Comprehensive SEO and GEO optimization suite. Use to analyze domains, find keyword gaps, research backlinks, and generate autocomplete search suggestions using DataForSEO.
Generate a structured academic paper outline from research narrative, experiment data, and review conclusions.
Expert Microsoft 365 tenant administration skill for setup, user lifecycle, security policy configuration, compliance, and automated PowerShell scripting for Global Administrators.
A systematic, multi-angle web research agent. Use for deep investigation, complex queries, and as a mandatory pre-research step before content generation to ensure evidence-backed, high-quality results.
Generate hierarchical, token-efficient AGENTS.md files for AI coding agents to provide repository-wide context and project-specific guidelines.
Generate realistic virtual product try-on visualizations to help customers evaluate fit, drape, and scale before purchasing.