Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/auto-review-loop-llm
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".
Passed 12 of 16 test cases with the skill, and 4 of 16 without it.
and 15 more in the full report
12 fixed4 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Before executing Phase A on a newly initiated agent session, what step must be taken during the Initialization step regarding disk state?
| Checked | Without skill | With skill |
|---|---|---|
| Check REVIEW_STATE.json for existing state during initialization. | Missed | Passed |
The instructions your model reads when the skill loads.
Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.
AUTO_REVIEW.md in project root (cumulative log)This skill uses any OpenAI-compatible API for external review via the llm-chat MCP server.
Add to ~/.codex/settings.json:
{
"mcpServers": {
"llm-chat": {
"command": "/usr/bin/python3",
"args": ["/Users/yourname/.codex/mcp-servers/llm-chat/server.py"],
"env": {
"LLM_API_KEY": "your-api-key",
"LLM_BASE_URL": "https://api.deepseek.com/v1",
"LLM_MODEL": "deepseek-chat"
}
}
}
}
| Provider | LLM_BASE_URL | LLM_MODEL |
|---|
test cases passed, vs 4 / 16 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.