Haoqin860/auto-research-skill
Autonomous Goal-directed Iteration for Claude Code. Inspired by Karpathy's autoresearch. 9 modes: loop, plan, debug, fix, security, ship, scenario, predict, learn.
Autonomous Goal-directed Iteration for Claude Code. Inspired by Karpathy's autoresearch. 9 modes: loop, plan, debug, fix, security, ship, scenario, predict, learn.
npx add-skill Haoqin860/auto-research-skillAutonomous Goal-directed Iteration for Claude Code. Inspired by Karpathy's autoresearch. 9 modes: loop, plan, debug, fix, security, ship, scenario, predict, learn.
Claude Code plugins and Codex skills from Calif.io for AI-assisted security research and code auditing
Detect, redact, and block crypto private keys and seed phrases in text. Prevent sensitive secrets from leaking to LLMs, AI agents, logs, and external services
Multi-agent financial trading framework leveraging LLMs to simulate real-world trading firm dynamics
Codex skill and CLI for codebase complexity, security, architecture, dependency, and performance audits.
Agent Skill for Claude Code: reduce token consumption, lower AI costs, and get faster responses. Backed by real experiment data.
Vendor-neutral agent skills for multi-market financial research — Claude Code, Cursor, OpenCode, Codex CLI