菜单
Simulate a Nature-style reviewer assessment for RL, MARL, LLM, and LLM Agent manuscripts. Use for pre-submission review, novelty assessment, technical soundness, reproducibility, benchmark fairness, safety, and reviewer-style critique.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Search, plan, and organize literature for RL, MARL, LLM, and LLM Agent research. Use for finding papers, building related-work maps, identifying baselines, benchmark provenance, citation gaps, and recent work tracking.
Build, audit, and organize citation evidence for RL, MARL, LLM, and LLM Agent manuscripts. Use for related work matrices, citation gaps, DOI/BibTeX checks, baseline provenance, benchmark provenance, and Nature-style support for claims.
Prepare Data Availability, Code Availability, Model Availability, Prompt Availability, and reproducibility statements for RL, MARL, LLM, and LLM Agent manuscripts.
Help legally obtain, organize, and archive academic papers, PDFs, BibTeX, supplementary files, code links, and benchmark documents for RL, MARL, LLM, and LLM Agent research. Do not bypass paywalls or access controls.
Create, revise, or audit Nature-style scientific figures for RL, MARL, LLM, and LLM Agent papers. Use for Python/R plotting, training curves, ablations, benchmark bars, architecture diagrams, agent workflow figures, trajectory visualizations, and publication export QA.
Build a repeatable literature discovery, scoring, reading, and archiving pipeline for RL, MARL, LLM, and LLM Agent research. Use for daily/weekly paper tracking, topic watchlists, benchmark monitoring, and research-note automation.
| name | nature-reviewer |
| description | Simulate a Nature-style reviewer assessment for RL, MARL, LLM, and LLM Agent manuscripts. Use for pre-submission review, novelty assessment, technical soundness, reproducibility, benchmark fairness, safety, and reviewer-style critique. |
| version | 2.0.0-agent-rl |
Return exactly three reviewer reports plus a cross-review synthesis unless the user requests another format. Ground the review only in the manuscript or notes supplied by the user.
Review setup
- Input scope:
- Assessment boundary:
- Shared manuscript claim:
- Visible evidence:
- Missing materials:
Reviewer 1 — significance and framing
- Overall assessment:
- Major strengths:
- Major concerns:
- Required revisions:
Reviewer 2 — method and experiments
[Same structure]
Reviewer 3 — reproducibility and safety
[Same structure]
Cross-review synthesis
- Consensus strengths:
- Consensus risks:
- Highest-priority fixes:
- Nature-style readiness score:
Do not invent reviewer identities, citations, experiments, decisions or confidential editorial processes. Do not say “accept” or “reject” as a final editorial decision; describe recommendation posture only.