domains / families / research / auto-review-loop-llm

auto-review-loop-llm

combined

Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".

When to use

• autonomous research review loop
• iterative research improvement
• external LLM review
• research submission readiness assessment

Skill page

Conflict

Both copies implement the same review→fix→re-review loop with the same MCP/curl configuration, provider table, state file, and phase structure. They disagree on the stop condition (AND vs OR, and the verdict vocabulary), on file paths (review-stage/ vs project root), and the wanshuiyin copy adds a strong anti-wrapping constraint and legacy fallbacks that the brycewang copy lacks. Crowning one would hide a real alternative, so the combined instruction preserves both variants and flags the conflicts.