deathscy3708/claude-code
Explore deobfuscated Claude Code source code with readable TypeScript, module structure, and tool implementations for analysis and study
Explore deobfuscated Claude Code source code with readable TypeScript, module structure, and tool implementations for analysis and study
npx skills add deathscy3708/claude-codeExplore deobfuscated Claude Code source code with readable TypeScript, module structure, and tool implementations for analysis and study
Structured 10-step diagnostic for go/no-go feature evaluation in production ML pipelines. Covers outcome gradient, coverage gaps, entropy/gain ratio, conditional MI, incremental CV AUC, and 9-point temporal safety. Claude Code skill.
30 open-source AI agent skills across research, marketing, product, and meta. ~150 sub-agents. Distributed via npm and Claude Code plugin marketplace.
Recently updated agent-skill-related GitHub repository: backyes/claude-skill-paper-analyzer.
Demonstrate black-box adversarial attacks on LLM tool-calling to bypass safety and execute remote code using CMA-ES optimization.
The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions.
Unity MCP acts as a bridge, allowing AI assistants (like Claude, Cursor) to interact directly with your Unity Editor via a local MCP (Model Context Protocol) Client. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.