Back to Details

submission-audit

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Submission Audit

提交预审检查

Overview

概述

Use this skill for late-stage manuscript QA. It is narrower than 
manuscript-optimizer
: do not use it to redesign a paper from scratch. Use it when the structure mostly exists and the main task is to catch the failures that survive normal revision cycles.
The core rule is simple: never treat a clean-looking manuscript as submission-ready until the front half, figures, legends, methods, supplement, and venue expectations have been checked against each other.
Use the helper script when you want a fast local pass over figure citations:
bash
python ~/.codex/skills/submission-audit/scripts/check_figure_refs.py path/to/manuscript.md
本技能用于稿件后期质量检查。它的适用范围比
manuscript-optimizer
更窄：请勿用它从头重写论文。当稿件结构基本确定，主要任务是找出常规修订流程中遗漏的问题时，可使用本技能。
核心规则很简单：在完成对稿件前半部分、图表、图例、方法、补充材料以及目标期刊要求的交叉检查之前，绝不要认为看似完善的稿件已准备好提交。
若需快速本地检查图表引用，可使用辅助脚本：
bash
python ~/.codex/skills/submission-audit/scripts/check_figure_refs.py path/to/manuscript.md

Claude Code (global install): replace ~/.codex/skills with ~/.claude/skills

Claude Code (global install): replace ~/.codex/skills with ~/.claude/skills

Claude Code (project-local install): replace ~/.codex/skills with .claude/skills

Claude Code (project-local install): replace ~/.codex/skills with .claude/skills

undefined
undefined

When To Use

适用场景

Use this skill when:
  • The draft is near submission, resubmission, or internal circulation
  • Figures and legends are mostly finalized
  • The paper needs a last pass for overclaim, missing references, or cross-section drift
  • A revision round compressed the prose and may have dropped supporting detail
  • The supplement exists and may no longer match the main text
Do not use this skill for:
  • Early brainstorming
  • Initial section drafting
  • Citation discovery from scratch
  • Heavy structural rewrites that belong in 
    manuscript-optimizer
以下情况可使用本技能：
  • 稿件接近提交、重新提交或内部传阅阶段
  • 图表及图例已基本定稿
  • 稿件需要最后一轮检查，排查过度夸大论点、缺失引用或内容不一致的问题
  • 一轮修订压缩了文本内容，可能遗漏了支撑细节
  • 补充材料已存在，但可能与正文不再匹配
以下情况请勿使用本技能：
  • 早期头脑风暴阶段
  • 初始章节起草阶段
  • 从零开始查找引用
  • 需要大幅结构重写的场景（此类需求应使用
    manuscript-optimizer
    ）

Audit Order

检查顺序

  1. Front-half alignment
    • check title, abstract, introduction, and discussion against the actual Results
    • flag any claim stronger than the downstream evidence
  2. Figure and legend coverage
    • verify that every main-figure panel and supplementary panel cited in the paper actually exists
    • verify that panel letters, metrics, datasets, and numbers agree across figure, legend, and main text
  3. Methods and supplement anchoring
    • check that methods are cited where needed from Results
    • check that supplementary figures, tables, and notes are referenced precisely enough to be usable
  4. Terminology and metrics
    • enforce one canonical name per concept
    • check abbreviations, metric naming, domain-shift labels, cohort names, and model names
  5. Risk pass
    • overclaim
    • evidence gaps
    • unsupported mechanism language
    • venue-specific style drift
  6. Nature Portfolio preflight when relevant
    • reporting-summary readiness
    • data and code availability statements
    • accession IDs, repositories, and disclosure of sharing restrictions
    • image-integrity and raw-data readiness
    • AI-use disclosure
    • preprint, related-manuscript, and conference-proceedings disclosure
  7. Reviewer-side rejection pass
    • contribution sufficiency
    • writing clarity and reproducibility
    • empirical strength
    • evaluation completeness
    • design or framework soundness
  1. 前半部分一致性检查
    • 核对标题、摘要、引言和讨论部分与实际研究结果是否一致
    • 标记任何研究结果无法支撑的夸大论点
  2. 图表与图例覆盖检查
    • 验证文中引用的所有主图面板和补充图面板是否真实存在
    • 确保图表、图例和正文中的面板编号、指标、数据集及数值一致
  3. 方法与补充材料关联检查
    • 检查研究结果部分是否在需要处引用了方法内容
    • 检查补充图表、表格和注释的引用是否足够精确，便于查阅
  4. 术语与指标检查
    • 确保每个概念使用唯一的标准名称
    • 检查缩写、指标命名、领域转换标签、队列名称和模型名称的一致性
  5. 风险排查
    • 过度夸大论点
    • 证据缺失
    • 无支撑的机制性表述
    • 不符合目标期刊的风格偏差
  6. 针对Nature Portfolio的预审检查（如适用）
    • 报告摘要是否准备就绪
    • 数据与代码可用性声明是否完善
    • 登录号、存储库及共享限制披露是否完整
    • 图像完整性与原始数据是否准备就绪
    • AI使用情况披露是否完成
    • 预印本、相关稿件及会议论文披露是否完整
  7. 审稿人视角拒稿风险排查
    • 研究贡献是否充分
    • 写作清晰度与可重复性
    • 实证研究强度
    • 评估完整性
    • 研究设计或框架合理性

Required Checks

必查项

  • Does every substantive abstract claim map to a figure, table, or supplement item?
  • Does every Results subsection cite the correct panel range?
  • Does every figure legend still reflect the current plot content?
  • Are 
    Methods
    cross-references present where interpretation depends on setup or metric definition?
  • Is the supplement indexed precisely enough, including panel letters when needed?
  • Are strong causal or mechanism words used only where direct evidence exists?
  • Are title, abstract, and discussion consistent about the paper's actual contribution type?
  • If the target is 
    Nature Portfolio
    , are the reporting-summary inputs, data/code statements, image-integrity materials, and disclosure items actually ready rather than merely planned?
  • If a submission form or portal draft already exists, do the title, abstract, keywords, availability statements, and related metadata still match the manuscript exactly?
  • Has the paper been pressure-tested against the main rejection dimensions: insufficient contribution, weak clarity, weak empirical effect, incomplete evaluation, and questionable design?
  • 摘要中的每个实质性论点是否都对应到图表、表格或补充材料中的内容？
  • 研究结果的每个小节是否引用了正确的面板范围？
  • 每个图表图例是否仍能反映当前图表内容？
  • 在依赖实验设置或指标定义进行解读的地方，是否存在
    方法
    部分的交叉引用？
  • 补充材料的索引是否足够精确，必要时是否包含面板编号？
  • 强因果或机制性词汇是否仅在有直接证据的地方使用？
  • 标题、摘要和讨论部分对论文实际贡献类型的表述是否一致？
  • 若目标期刊为Nature Portfolio，报告摘要输入内容、数据/代码声明、图像完整性材料及披露项是否已实际准备就绪，而非仅处于计划阶段？
  • 若已填写提交表单或门户草稿，标题、摘要、关键词、可用性声明及相关元数据是否与最新稿件完全匹配？
  • 稿件是否针对主要拒稿维度进行了压力测试：贡献不足、清晰度差、实证效果弱、评估不完整及设计存疑？

Finding Format

发现报告格式

Report findings in this order:
  • High: submission-blocking or claim-distorting issues
  • Medium: credibility or reader-friction issues
  • Low: consistency and polish issues
Each finding should include:
  • exact file reference
  • what is wrong
  • why it matters
  • the minimum safe fix
If no major problems exist, say that explicitly and then list only the residual risks or final checks still worth doing.
报告发现应按以下顺序排列：
  • 高优先级：阻碍提交或扭曲论点的问题
  • 中优先级：影响可信度或增加读者理解障碍的问题
  • 低优先级：一致性与润色问题
每个发现应包含：
  • 精确的文件引用
  • 问题描述
  • 问题影响
  • 最低风险的修复方案
若未发现重大问题，需明确说明，然后仅列出剩余风险或仍需完成的最终检查项。

Common Failure Modes

常见问题类型

  • Abstract promise stronger than Results support
  • Figure panel mentioned in text but not actually indexed or explained
  • Legend still describing an old version of the plot
  • Supplementary figure cited at whole-figure level when the argument depends on one panel
  • Metric names drifting between sections
  • Discussion slipping into mechanism-level language not earned by the evidence
  • Nature Portfolio submission blocked late by missing accession IDs, undeclared sharing restrictions, undisclosed AI use, or missing raw image support
  • Submission-form title or abstract drifting away from the latest manuscript
  • The manuscript reading cleanly on the surface while still failing a reviewer-style contribution or evaluation check
  • 摘要承诺的内容超出研究结果支撑范围
  • 文中提及的图表面板未实际索引或解释
  • 图例仍描述图表的旧版本内容
  • 当论证依赖单个面板时，却仅引用了整个补充图
  • 不同章节中指标名称不一致
  • 讨论部分出现研究证据无法支撑的机制性表述
  • 因缺失登录号、未披露共享限制、未披露AI使用或缺失原始图像支持，导致Nature Portfolio提交受阻
  • 提交表单中的标题或摘要与最新稿件不一致
  • 稿件表面看似完善，但从审稿人视角看仍存在贡献或评估方面的问题

Output Standard

输出标准

End the audit with:
  • a one-sentence readiness assessment
  • the top remaining risk
  • the next highest-leverage fix before submission
预审检查结束时需包含：
  • 一句话就绪评估
  • 首要剩余风险
  • 提交前优先级最高的修复建议