Research Review Agent Skill

> Override for Codex users who want Gemini, not a second Codex agent, to act as the reviewer. Install this package after skills/skills-codex/*.

Research Review via gemini-review MCP (high-rigor review)

> Gemini overlay assurance: review_independence: cross-family and acceptance_status: accepted.

Get a multi-round critical review of research work from an external LLM with maximum reasoning depth.

Constants

• REVIEWER_MODEL = gemini-review — Gemini reviewer invoked through the local gemini-review MCP bridge. Set GEMINI_REVIEW_MODEL if you need a specific Gemini model override.

Context: $ARGUMENTS

Prerequisites

• Install the base Codex-native skills first: copy skills/skills-codex/* into ~/.codex/skills/.
• Then install this overlay package: copy skills/skills-codex-gemini-review/* into ~/.codex/skills/ and allow it to overwrite the same skill names.
• Register the local reviewer bridge:

  codex mcp add gemini-review -- python3 ~/.codex/mcp-servers/gemini-review/server.py

• This gives Codex access to mcp__gemini-review__review_start, mcp__gemini-review__review_reply_start, and mcp__gemini-review__review_status.

Workflow

Step 1: Gather Research Context

Before calling the external reviewer, compile a comprehensive briefing:

• Read project narrative documents (e.g., STORY.md, README.md, paper drafts)
• Read any memory/notes files for key findings and experiment history
• Identify: core claims, methodology, key results, known weaknesses

Step 2: Initial Review (Round 1)

Send a detailed prompt with high-rigor review:

mcp__gemini-review__review_start:
  prompt: |
    [Full research context + specific questions]
    Please act as a senior ML reviewer (NeurIPS/ICML level). Identify:
    1. Logical gaps or unjustified claims
    2. Missing experiments that would strengthen the story
    3. Narrative weaknesses
    4. Whether the contribution is sufficient for a top venue
    Please be brutally honest.

After this start call, immediately save the returned jobId and poll mcp__gemini-review__review_status with a bounded waitSeconds until done=true. Treat the completed status payload's response as the reviewer output, and save the completed threadId for any follow-up round.

Step 3: Iterative Dialogue (Rounds 2-N)

Use mcp__gemini-review__review_reply_start with the saved completed threadId, then poll mcp__gemini-review__review_status with the returned jobId until done=true to continue the conversation:

For each round:

• Respond to criticisms with evidence/counterarguments
• Ask targeted follow-ups on the most actionable points
• Request specific deliverables: experiment designs, paper outlines, claims matrices

Key follow-up patterns:

• "If we reframe X as Y, does that change your assessment?"
• "What's the minimum experiment to satisfy concern Z?"
• "Please design the minimal additional experiment package (highest acceptance lift per GPU week)"
• "Please write a mock NeurIPS/ICML review with scores"
• "Give me a results-to-claims matrix for possible experimental outcomes"

Step 4: Convergence

Stop iterating when:

• Both sides agree on the core claims and their evidence requirements
• A concrete experiment plan is established
• The narrative structure is settled

Step 5: Document Everything

Save the full interaction and conclusions to a review document in the project root:

• Round-by-round summary of criticisms and responses
• Final consensus on claims, narrative, and experiments
• Claims matrix (what claims are allowed under each possible outcome)
• Prioritized TODO list with estimated compute costs
• Paper outline if discussed

Update project memory/notes with key review conclusions.

Key Rules

• Always ask the Gemini reviewer for strict, high-rigor feedback.
• Send comprehensive context in Round 1 — the external model cannot read your files
• Be honest about weaknesses — hiding them leads to worse feedback
• Push back on criticisms you disagree with, but accept valid ones
• Focus on ACTIONABLE feedback — "what experiment would fix this?"
• Document the completed threadId for potential future resumption
• The review document should be self-contained (readable without the conversation)

Prompt Templates

For initial review:

"I'm going to present a complete ML research project for your critical review. Please act as a senior ML reviewer (NeurIPS/ICML level)..."

For experiment design:

"Please design the minimal additional experiment package that gives the highest acceptance lift per GPU week. Our compute: [describe]. Be very specific about configurations."

For paper structure:

"Please turn this into a concrete paper outline with section-by-section claims and figure plan."

For claims matrix:

"Please give me a results-to-claims matrix: what claim is allowed under each possible outcome of experiments X and Y?"

For mock review:

"Please write a mock NeurIPS review with: Summary, Strengths, Weaknesses, Questions for Authors, Score, Confidence, and What Would Move Toward Accept."