Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
Long-running loops may hit the context window limit, triggering automatic compaction. To survive this, persist state to REVIEW_STATE.json after each round:
Write this file at the end of every Phase E (after documenting the round). Overwrite each time — only the latest state matters.
On completion (positive assessment or max rounds), set "status": "completed" so future invocations don't accidentally resume a finished loop.
Workflow
Initialization
Check for REVIEW_STATE.json in project root:
If it does not exist: fresh start (normal case)
If it exists AND status is "completed": fresh start (previous loop finished normally)
If it exists AND status is "in_progress" AND timestamp is older than 24 hours: fresh start (stale state from a killed/abandoned run — delete the file and start over)
If it exists AND status is "in_progress" AND timestamp is within 24 hours: resume
Read the state file to recover round, last_score, pending_experiments
Read AUTO_REVIEW.md to restore full context of prior rounds
If pending_experiments is non-empty, check if they have completed (e.g., check screen sessions)
Resume from the next round (round = saved round + 1)
Log: "Recovered from context compaction. Resuming at Round N."
Read project narrative documents, memory files, and any prior review documents
Identify current weaknesses and open TODOs from prior reviews
Initialize round counter = 1 (unless recovered from state file)
Create/update AUTO_REVIEW.md with header and timestamp
Loop (repeat up to MAX_ROUNDS)
Phase A: Review
Send comprehensive context to the external reviewer.
Check MCP availability first, then use appropriate method:
If MCP available (Primary):
Use mcp__minimax-chat__minimax_chat tool with:
- system: "You are a senior machine learning researcher serving as a reviewer for top-tier conferences like NeurIPS, ICML, and ICLR. Provide rigorous, constructive feedback."
- prompt: [Full review prompt with context]
- model: "MiniMax-M2.7"
If MCP NOT available (Fallback):
curl -s "https://api.minimax.io/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MINIMAX_API_KEY" \
-d '{
"model": "MiniMax-M2.7",
"messages": [
{
"role": "system",
"content": "You are a senior machine learning researcher serving as a reviewer for top-tier conferences like NeurIPS, ICML, and ICLR. Provide rigorous, constructive feedback."
},
{
"role": "user",
"content": "[Round N/MAX_ROUNDS of autonomous review loop]\n\n[Full research context: claims, methods, results, known weaknesses]\n[Changes since last round, if any]\n[For round 2+: Summary of previous review feedback and what was addressed]\n\nPlease act as a senior ML reviewer (NeurIPS/ICML level).\n\n1. Score this work 1-10 for a top venue\n2. List remaining critical weaknesses (ranked by severity)\n3. For each weakness, specify the MINIMUM fix (experiment, analysis, or reframing)\n4. State clearly: is this READY for submission? Yes/No/Almost\n\nBe brutally honest. If the work is ready, say so clearly."
}
],
"max_tokens": 4096
}'
Note: Each round is a standalone API call. For round 2+, include the summary of previous reviews and changes in the prompt itself.
Phase B: Parse Assessment
CRITICAL: Save the FULL raw response from the external reviewer verbatim (store in a variable for Phase E). Do NOT discard or summarize — the raw text is the primary record.
Then extract structured fields:
Score (numeric 1-10)
Verdict ("ready" / "almost" / "not ready")
Action items (ranked list of fixes)
STOP CONDITION: If score >= 6 AND verdict contains "ready" or "almost" → stop loop, document final state.
Phase C: Implement Fixes (if not stopping)
For each action item (highest priority first):
Code changes: Write/modify experiment scripts, model code, analysis scripts
Run experiments: Deploy to GPU server via SSH + screen/tmux
Analysis: Run evaluation, collect results, update figures/tables
Documentation: Update project notes and review document
Prioritization rules:
Skip fixes requiring excessive compute (flag for manual follow-up)
Skip fixes requiring external data/models not available
Prefer reframing/analysis over new experiments when both address the concern
Always implement metric additions (cheap, high impact)
Phase D: Wait for Results
If experiments were launched:
Monitor remote sessions for completion
Collect results from output files and logs
Phase E: Document Round
Append to AUTO_REVIEW.md:
## Round N (timestamp)### Assessment (Summary)- Score: X/10
- Verdict: [ready/almost/not ready]
- Key criticisms: [bullet list]
### Reviewer Raw Response<details><summary>Click to expand full reviewer response</summary>
[Paste the COMPLETE raw response from the external reviewer here — verbatim, unedited.
This is the authoritative record. Do NOT truncate or paraphrase.]
</details>### Actions Taken- [what was implemented/changed]
### Results- [experiment outcomes, if any]
### Status- [continuing to round N+1 / stopping]
Write REVIEW_STATE.json with current round, score, verdict, and any pending experiments.
Increment round counter → back to Phase A.
Termination
When loop ends (positive assessment or max rounds):
Update REVIEW_STATE.json with "status": "completed"
Write final summary to AUTO_REVIEW.md
Update project notes with conclusions
If stopped at max rounds without positive assessment:
List remaining blockers
Estimate effort needed for each
Suggest whether to continue manually or pivot
Key Rules
Large file handling: If the Write tool fails due to file size, immediately retry using Bash (cat << 'EOF' > file) to write in chunks. Do NOT ask the user for permission — just do it silently.
Anti-hallucination citations: When adding references, NEVER fabricate BibTeX. Use DBLP → CrossRef → [VERIFY] chain. Do NOT generate BibTeX from memory.
Be honest — include negative results and failed experiments
Do NOT hide weaknesses to game a positive score
Implement fixes BEFORE re-reviewing (don't just promise to fix)
If an experiment takes > 30 minutes, launch it and continue with other fixes while waiting
Document EVERYTHING — the review log should be self-contained
Update project notes after each round, not just at the end
For round 2+, always include previous review context in the prompt
Prefer MCP tool over curl when available (more reliable)
Prompt Template for Round 2+
MCP Method (Primary):
mcp__minimax-chat__minimax_chat:
model: "MiniMax-M2.7"
system: "You are a senior machine learning researcher serving as a reviewer for top-tier conferences like NeurIPS, ICML, and ICLR. Provide rigorous, constructive feedback."
prompt: |
[Round N/MAX_ROUNDS of autonomous review loop]
## Previous Review Summary (Round N-1)
- Previous Score: X/10
- Previous Verdict: [ready/almost/not ready]
- Previous Key Weaknesses: [list]
## Changes Since Last Review
1. [Action 1]: [result]
2. [Action 2]: [result]
3. [Action 3]: [result]
## Updated Results
[paste updated metrics/tables]
## Current Research Context
[brief summary of claims, methods, current state]
Please re-score and re-assess:
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.
curl Fallback:
curl -s "https://api.minimax.io/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MINIMAX_API_KEY" \
-d '{
"model": "MiniMax-M2.7",
"messages": [
{
"role": "system",
"content": "You are a senior machine learning researcher serving as a reviewer for top-tier conferences like NeurIPS, ICML, and ICLR. Provide rigorous, constructive feedback."
},
{
"role": "user",
"content": "[Round N/MAX_ROUNDS of autonomous review loop]\n\n## Previous Review Summary (Round N-1)\n- Previous Score: X/10\n- Previous Verdict: [ready/almost/not ready]\n- Previous Key Weaknesses: [list]\n\n## Changes Since Last Review\n1. [Action 1]: [result]\n2. [Action 2]: [result]\n3. [Action 3]: [result]\n\n## Updated Results\n[paste updated metrics/tables]\n\n## Current Research Context\n[brief summary of claims, methods, current state]\n\nPlease re-score and re-assess:\n1. Score this work 1-10 for a top venue\n2. List remaining critical weaknesses (ranked by severity)\n3. For each weakness, specify the MINIMUM fix\n4. State clearly: is this READY for submission? Yes/No/Almost\n\nBe brutally honest. If the work is ready, say so clearly."
}
],
"max_tokens": 4096
}'
