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.
568 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.
Automate pytest execution with built-in environment verification, failure analysis, coverage reporting, and intelligent test discovery.
Architect production-grade LLM applications using LangChain 1.x and LangGraph. Implement stateful AI agents, multi-step workflows, and custom memory systems for complex conversational and automation tasks.
Discover and configure Redpanda Connect components like inputs, outputs, and processors to build efficient streaming data pipelines.
Advanced Gemini-powered web search plugin with smart caching, subagent context isolation, and automated query optimization.
A CTF solver agent that performs triage on challenges, identifies the vulnerability category, and routes tasks to specialized skills for web, pwn, crypto, forensic, and reverse engineering analysis.
Initializes a development session with environmental health checks, task status synchronization, and contextual memory restoration for Claude Code.
Sends debugging data, logs, and visual output to the Ray desktop application via its local API for real-time developer feedback.
Master workflow controller for Lovable-style, AI-driven development. Instantly generates premium, multi-page, animated applications by routing to specialized sub-agents. No prompts needed—just build.
Privacy-preserving transactions on Base using Veil Cash. Deposit into shielded pools, perform ZK-based withdrawals/transfers, and manage private balances. Supports ETH/USDC via local ZK proofs and Bankr-signed deposits.
Implements an autonomous, critical self-verification layer for AI agents to validate code quality, security, and requirement alignment before task completion.
A wise conductor of expert agents. It helps you achieve goals by summoning, orchestrating, and creating specialized AI experts. Features intellectual humility, multi-agent debate, and self-learning pattern capture.