メニュー
Run a multi-persona simulated academic review for a LaTeX or PDF paper. Parses paper structure, prepares reviewer-specific prompts, then guides independent reviews, AC meta-review, revision roadmap, and consistency checks.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Aggregate Codex skill bundle for academic literature search, screening, citation traversal, research ideation, experiment planning, LaTeX lint/fix, bibliography verification, polishing, translation, and one-command paper checks.
Aggregate Codex skill bundle for academic literature search, screening, citation traversal, research ideation, experiment planning, LaTeX lint/fix, bibliography verification, polishing, translation, and one-command paper checks.
Run the full writing-quality pipeline for a LaTeX paper project: lint, auto-fix preview or apply, citation verification, and aggregated reporting. Use this when the user wants a submission-readiness check, a one-command writing QA pass, or a structured report summarizing lint and bibliography health.
Route a natural-language research request to the right Hypo-Research workflow. Use this when the user is unsure whether they need check, review, read, search, ideation, project management, or another expert skill. Can execute conservative safe paths with explicit inputs.
Run a unified pre-submission check pipeline for LaTeX papers, combining structure/format checks, LaTeX lint, and bibliography verification into one PASS/WARNING/FAIL report. Use when the user is preparing a paper submission, wants CI-friendly preflight checks, or asks for a complete submission-readiness report.
Ingest academic PDFs into structured read artifacts, render outlines, and extract heuristic evidence cards for methods, datasets, figures, and claims. Use this when the user wants to read, summarize, inspect, or deep-read a PDF.
| name | hypo-review |
| description | Run a multi-persona simulated academic review for a LaTeX or PDF paper. Parses paper structure, prepares reviewer-specific prompts, then guides independent reviews, AC meta-review, revision roadmap, and consistency checks. |
| license | MIT |
你是一个学术论文模拟审稿系统的控制器。目标是让 Agent 依次扮演多个虚拟审稿人，对同一篇论文给出独立、结构化、可执行的审稿意见。
$ARGUMENTS
.tex / .pdfdac, neurips, tcas1default / fullgentle / standard / harsh自动从 Semantic Scholar 检索与被审论文最相关的近期文献：
如果检索失败或使用 --no-literature 参数，将跳过此步骤继续审稿。
先运行：
uv run hypo-research review --parse-only <paper_path>
检查 PaperStructure 中的 title、abstract、sections、figures、tables、claims、references、inferred_domain 和 raw_text。若解析明显异常，先向用户说明并确认输入文件。
确认目标 venue、审稿团、苛刻程度和论文领域。用户已明确给出参数时，可以直接继续。
生成角色 prompt：
uv run hypo-research review <paper_path> \
--venue <venue> \
--panel <panel> \
--severity <severity> \
--prompts
依次切换为每个审稿人角色，基于 prompt 进行审稿。每个角色独立审稿，输出结构化审稿意见。
重要：审稿时你要完全进入该角色的性格和视角。每个 Weakness 必须同时给出具体问题、改进建议和重要程度理由。
审稿人角色：
在所有审稿人完成独立审稿后，切换回贺云翔 AC 角色：
MetaReview 结构在 Meta-Review 完成后，切换为“导师”角色：
RevisionRoadmap 结构对所有审稿意见进行规则检查：
ConsistencyReport，附在报告末尾将所有 SingleReview、MetaReview、RevisionRoadmap 和 ConsistencyReport 汇总为最终 Markdown 报告。CLI 可生成报告框架：
uv run hypo-research review <paper_path> --output review_report.md
机器可读输出：
uv run hypo-research review <paper_path> --json
每个审稿人输出：
[Major] 或 [Minor]，且必须可操作）最终报告必须包含总体评分表、AC Meta-Review（如适用）、Major/Minor/Strengths 汇总、详细审稿、修改路线图（如适用）和一致性检查。
uv run hypo-research review paper.tex
uv run hypo-research review paper.tex --venue tcas1 --panel full
uv run hypo-research review paper.pdf --panel full --severity harsh
uv run hypo-research review paper.tex --reviewers lichaofan chenquanyu liyuxuan
uv run hypo-research review --list-reviewers
uv run hypo-research review --list-venues