Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on Claude Code, portable across Codex, Cursor & other Skills hosts.
open-source machine-learning skills data-analysis ai-agents claude literature-review scientific-writing red-teaming prompt-engineering anthropic llm-agents agentic-workflows agent-skills claude-code subagents autoresearch agentic-loops ml-autoresearch
-
Updated
Jun 30, 2026 - Python