/auto-review-loop-llm

name: auto-review-loop-llm
description: 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".
argument-hint: "[topic-or-scope]"
allowed-tools: Bash(*), Read, Grep, Glob, Write, Edit, Skill

Auto Review Loop (Generic LLM): Autonomous Research Improvement

> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** Like > `/auto-review-loop`, it already loops internally (review → fix → re-review), > feeding each round's prior-round summary into the next review prompt (the > backend is a stateless per-round API/MCP call, not a shared thread). An > external timer re-enters from the top each tick, dropping that accumulated > context and firing the verdict on wall-clock time instead of on artifact > change — zero new signal, full token cost. Schedule the *external wait that > precedes it*, not the verdict. See > [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).

Autonomously iterate: review → implement fixes → re-review, until the external reviewer gives a positive assessment or MAX_ROUNDS is reached.

Context: $ARGUMENTS

Constants

• MAX_ROUNDS = 4
• POSITIVE_THRESHOLD: score >= 6/10 **AND** verdict ∈ {"ready", "almost"} — **both** must hold, matching the operative STOP check below. Verdict vocabulary is {"ready", "almost", "not ready"}. (Earlier wording used `or` and a stale verdict set; the `AND` form is authoritative.)
• REVIEW_DOC: `review-stage/AUTO_REVIEW.md` (cumulative log) *(fall back to `./AUTO_REVIEW.md` for legacy projects)*

LLM Configuration

This skill uses **any OpenAI-compatible API** for external review via the `llm-chat` MCP server.

Configuration via MCP Server (Recommended)

Add to `~/.claude/settings.json`:

{
  "mcpServers": {
    "llm-chat": {
      "command": "/usr/bin/python3",
      "args": ["/Users/yourname/.claude/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"
      }
    }
  }
}

Supported Providers

| Provider | LLM_BASE_URL | LLM_MODEL | |----------|--------------|-----------| | **OpenAI** | `https://api.openai.com/v1` | `gpt-6.1-sol`, `gpt-6-astra` | | **DeepSeek** | `https://api.deepseek.com/v1` | `deepseek-chat`, `deepseek-reasoner` | | **MiniMax** | `https://api.minimax.io/v1` | `MiniMax-M3` | | **Kimi (Moonshot)** | `https://api.moonshot.cn/v1` | `moonshot-v1-8k`, `moonshot-v1-32k` | | **ZhiPu (GLM)** | `https://open.bigmodel.cn/api/paas/v4` | `glm-4`, `glm-4-plus` | | **SiliconFlow** | `https://api.siliconflow.cn/v1` | `Qwen/Qwen2.5-72B-Instruct` | | **阿里云百炼** | `https://dashscope.aliyuncs.com/compatible-mode/v1` | `qwen-max` | | **零一万物** | `https://api.lingyiwanwu.com/v1` | `yi-large` |

The `llm-chat` server defaults to `gpt-6.1-sol`. When `LLM_FALLBACK_MODEL` is unset, the 504-timeout fallback inherits `LLM_MODEL` (so it is not a fixed, different model). Calls to `api.openai.com` automatically use `max_completion_tokens`; third-party OpenAI-compatible endpoints use `max_tokens`. Set `LLM_MAX_TOKENS_FIELD=max_tokens` or `LLM_MAX_TOKENS_FIELD=max_completion_tokens` to override that automatic choice.

API Call Method

**Primary: MCP Tool**

mcp__llm-chat__chat:
  prompt: |
    [Review prompt content]
  model: "deepseek-chat"
  system: "You are a senior ML reviewer..."

**Fallback: curl**

For third-party OpenAI-compatible endpoints, use `max_tokens`:

curl -s "${LLM_BASE_URL}/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${LLM_API_KEY}" \
  -d '{
    "model": "${LLM_MODEL}",
    "messages": [
      {"role": "system", "content": "You are a senior ML reviewer..."},
      {"role": "user", "content": "[review prompt]"}
    ],
    "max_tokens": 4096
  }'

For a direct OpenAI call, use `max_completion_tokens` instead:

curl -s "https://api.openai.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${LLM_API_KEY}" \
  -d '{
    "model": "gpt-6.1-sol",
    "messages": [
      {"role": "system", "content": "You are a senior ML reviewer..."},
      {"role": "user", "content": "[review prompt]"}
    ],
    "max_completion_tokens": 4096
  }'

State Persistence (Compact Recovery)

Persist state to `review-stage/REVIEW_STATE.json` after each round:

{
  "round": 2,
  "status": "in_progress",
  "last_score": 5.0,
  "last_verdict": "not ready",
  "pending_experiments": [],
  "timestamp": "2026-03-15T10:00:00"
}

**Write this file at the end of every Phase E** (after documenting the round).

**On completion**, set `"status": "completed"`.

Workflow

Initialization

1. **Check `review-stage/REVIEW_STATE.json`** for recovery *(fall back to `./REVIEW_STATE.json` if not found — legacy path)* 2. Read project context and prior reviews 3. Initialize round counter

Loop (up to MAX_ROUNDS)

Phase A: Review

**If MCP available:**

mcp__llm-chat__chat:
  system: "You are a senior ML reviewer (NeurIPS/ICML level)."
  prompt: |
    [Round N/MAX_ROUNDS of autonomous review loop]

    [Full research context: claims, methods, results, known weaknesses]
    [Changes since last round, if any]

    1. Score this work 1-10 for a top venue
    2. List remaining critical weaknesses (ranked by severity)
    3. For each weakness, specify the MINIMUM fix
    4. State clearly: is this READY for submission? Yes/No/Almost

    Be brutally honest. If the work is ready, say so clearly.

**If MCP NOT available:** For third-party OpenAI-compatible endpoints use `max_tokens`; for direct OpenAI calls use `max_completion_tokens` instead.

curl -s "${LLM_BASE_URL}/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${LLM_API_KEY}" \
  -d '{
    "model": "${LLM_MODEL}