Loading...
Loading...
Found 8 Skills
Orchestrate autonomous ML research workflows with cross-model review loops, idea discovery, and experiment automation using Claude Code and Codex MCP
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
Deep analysis and investigation
Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
Get a second opinion via Codex MCP. Use for stress-testing ideas, getting fresh perspective, steelmanning arguments, or iteratively refining work through expert back-and-forth. Invoke for ANY request involving external review, feedback, or consultation.
Manage MCP servers in Codex quickly and safely. Use this skill when the user asks to add, update, remove, inspect, or troubleshoot MCP servers, especially from a GitHub URL. The skill enforces scope selection (project `./.codex/config.toml` vs global `~/.codex/config.toml`), checks for existing entries, and asks the user to choose required options before making changes.