learn-skill

Build and evolve domain skills inside Codex using isolated subagents, file-based handoffs, live web research, and persistent memory. Use when the user wants Codex to learn a bounded professional workflow, distill it into a reusable skill package, and iteratively improve it through closed-book evaluation without writing a custom orchestrator.

Scenario pack for Chinese public-opinion risk analysis under learn.skill. Use when the orchestration skill needs domain-specific rules, eval sets, and memory for event-pack based public-opinion assessment.

Closed-book execution bundle for event-pack based Chinese public-opinion risk analysis. Use only for analysis of the current case pack. Do not rely on outside memory, hidden gold, or corpus files.