Skill UI

Autonomously orchestrates multi-round research reviews via Codex MCP: review, implement fixes, and re-review until the reviewer declares the work ready or the max rounds expire. Logs progress, maintains compact/recoverable state, and optionally adds human checkpoints for iterative improvement requests.

Orchestrates iterative research review, fix, and re-review cycles with OpenAI-compatible LLMs, persisting reviewer state and documentation until approval or max rounds.

Autonomous loop that submits research context to MiniMax-M2.7, parses reviewer feedback, and iterates through fixes until a positive assessment or max rounds is reached, using compact state persistence for long runs.

A multiagent adversarial verification workflow that runs generation through dual independent reviewers, a verdict gate, and fix cycles to ensure publishable outputs meet compliance, accuracy, and brand constraints before shipping to users.