manuscript-diagnosis SKILL.md skillA

manuscript-diagnosis from qiaomiaojoe/ai-academic-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add qiaomiaojoe/ai-academic-workflow/manuscript-diagnosis@v1.2.0

Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
qiaomiaojoe/ai-academic-workflow
Path
skills/manuscript-diagnosis/SKILL.md
Versions recorded
3
Latest version
v1.2.0, committed Oct 27, 2026
First version recorded
Oct 16, 2026
Size
12,109 bytes
Repository stars
10
License
a license file GitHub does not identify

初稿诊断(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。对人文社科初稿做论证与证据诊断:论证角色逐段查主张、推理和适用边界(质性原创研究另按 Q1–Q3 三标准),证据角色回原文核查文献声明;产出带原文定位、稳定问题 ID、修改建议和作者决定栏的诊断表,作者批准的问题交 manuscript-revision 改稿。保留核心观点,没问题不凑条数。Trigger on:"诊断这份初稿"、"看看这篇稿子论证和证据有什么问题"、"改稿前先诊断"、"保留我的核心观点给修改建议"、"diagnose my manuscript draft"、"check the argument and evidence of my draft"。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 初稿诊断

方法版本:1.2.0;固化日期:2026-09-11;工作流位置:投稿与审稿 · 01 初稿诊断;旧工作台编号 s02。
安装位置:全局 skills 文件夹(`~/.claude/skills/manuscript-diagnosis/` 或 `~/.codex/skills/manuscript-diagnosis/`);项目里另有 `skills/manuscript-diagnosis/SKILL.md` 时以项目那份为准。状态:方法已按作者确认的设计定稿,并纳入作者指定的质性三标准;还没有用真实投稿任务检验过效果。

## 适用范围与来源

初稿改写之前,或作者改变核心观点、诊断范围后重新诊断。本 skill 形成修改建议,作者批准后由 `manuscript-revision` 实施。

来源为本项目设计、项目规则与投稿审稿规范,适用于人文社科作者改稿、投稿和返修工作。设计新增方法是 AI 提案经作者接受的项目方案,不冒充教科书、期刊指南或成功案例。来源路径、原始方法和适用范围见 [来源依据](references/source-basis.md),执行前读取其中对应角色原文,结合本场景边界使用;原始跨场景职责不扩大本次任务。将来引入指南须记录机构/期刊、版本/日期、查阅日期与实际位置;案例限定为个案经验,口述可直接提炼、不强制 PDF;核心判断未明确就标待补。

新增文献依据及适用边界见 [质性三标准](references/qualitative-criteria.md)。采用质性分支前必须读取;这是方法文献的主张,不是所有期刊的统一规定。

## 输入要求

基准稿全文;作者核心观点及允许范围;本轮重点章节;实际可读的文献原文/证据;可选作者或合作者反馈。质性诊断另核对稿件声明的研究取向、资料来源与生成情境、资料范围及分析过程;仅检查实际提供的稿件和附件,不要求公开私人原始资料,不把报告缺项等同于研究未实施。

先实际读取 `submission-task-intake` skill(和本 skill 装在同一个 skills 文件夹;项目里有 `skills/submission-task-intake/SKILL.md` 时用项目那份)并执行前置核实;本轮已有有效登记可按其规则复用。该文件缺失时只核对材料与缺项,停止依赖它的业务执行,不凭 skill 名猜方法。

## 执行方法

1. 执行共用入口核实;列本轮实际可读的诊断范围与基准版本。缺稿件时只做核对,不凭标题诊断。
2. 论证角色梳理研究问题、中心主张、论据、推理、结论与适用边界;逐段看功能,核对概念用法和结论是否超出证据。每项判断附位置及依据。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add qiaomiaojoe/ai-academic-workflow/manuscript-diagnosis@sha256:d0e67edbe164c8f0

The line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_23sdbyp75n2ippq7.svg)](https://markdownregistry.com/a/art_23sdbyp75n2ippq7)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Oct 16, 2026 and Oct 27, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
v1.2.0 latest2026-10-27 4032a1b 12,109 BA view · diff
v1.2.02026-10-24 9392fe3 11,394 BA view · diff
v1.2.02026-10-16 51b11d1 11,231 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12109 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

qiaomiaojoe/ai-academic-workflow · 10 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_23sdbyp75n2ippq7
GET https://markdownregistry.com/api/v1/resolve?ref=qiaomiaojoe/ai-academic-workflow/manuscript-diagnosis
GET https://markdownregistry.com/api/v1/blob/d0e67edbe164c8f037a71c81a2eec75fb04af005b5f5495cc5cd5233cddce30f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from qiaomiaojoe/ai-academic-workflow

academic-project-init SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/academic-project-init/SKILL.md · AI 学术研究项目初始化(乔淼PhD · AI学术训练营 · AI学术工作流)。为一篇论文写项目说明 AGENTS.md(含「文件放哪」表:选题/ 文献/(PDF/、知识模块/)方法/ 数据/ 写作/ skill源材料/)+…
git:20261024.d6cd910 · audit A · 10 stars
analyze-qualitative-data SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/analyze-qualitative-data/SKILL.md · Use when analyzing qualitative social science data following Neuman's Social Research Methods Ch 14 — three-stage…
git:20260428.41cccf2 · audit A · 10 stars
analyze-quantitative-data SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/analyze-quantitative-data/SKILL.md · Use when analyzing quantitative social science data following Neuman's Social Research Methods Ch 12 — codebook…
git:20260428.41cccf2 · audit A · 10 stars
article-framework SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/article-framework/SKILL.md · 文章框架反推(乔淼PhD · AI学术训练营 · AI学术工作流 · 全文初稿步骤)。基于 Model Paper 拆解报告反推新论文的完整框架(5 Part:四象限定位 / 虚实三过程 / 引用角色配置与承重比例 / 各节段落骨架 /…
git:20260720.26d5eef · audit A · 10 stars
cnki SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/cnki/SKILL.md · 知网检索与核对(乔淼PhD · AI学术训练营 · AI学术工作流)。用学员自己电脑上的浏览器查中国知网:按主题 / 篇名 / 关键词 / 作者 / 来源检索,可限年份、核心期刊(CSSCI / 北大核心 / CSCD…
git:20261102.a9ed8b4 · audit A · 10 stars
critical-paper-reading SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/critical-paper-reading/SKILL.md · 单篇论文批判性阅读(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。基于 UOW (University of Wollongong) Critical Analysis 框架 —— 三层升级…
git:20261027.4032a1b · audit A · 10 stars
data-analysis-round SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/data-analysis-round/SKILL.md · 数据分析 · 跑一轮(乔淼PhD · AI学术训练营 · AI学术工作流)。三种分支:定量(调 analyze-quantitative-data,Neuman Ch12)/ 定性(调…
git:20260720.26d5eef · audit A · 10 stars
findings-synthesis SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/findings-synthesis/SKILL.md · 综合研究发现(乔淼PhD · AI学术训练营 · AI学术工作流 · 数据分析终点)。把多轮/多 skill 的数据分析产出整合成对应研究问题的研究发现:逐子问题/假设给结论判定 + 证据整合(定量 effect size…
git:20260720.26d5eef · audit A · 10 stars
fulltext-draft SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/fulltext-draft/SKILL.md · 全文初稿扩写(乔淼PhD · AI学术训练营 · AI学术工作流 · 全文初稿步骤 · 管线终点)。把 文章框架.md 的段落骨架扩写成可打磨的全文段落初稿:正文语言最高优先级规则、方法论节直接采用研究设计初稿、结果节据 研究发现.md…
git:20260720.26d5eef · audit A · 10 stars
journal-rank SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/journal-rank/SKILL.md · 查期刊级别(乔淼PhD · AI学术训练营 · AI学术工作流)。输入刊名或 ISSN,查这本英文期刊被哪些库收录(SCIE / SSCI / AHCI / ESCI / EI)、最新影响因子、JCI、JCR 学科和分区、分区(大类学科…
git:20261103.34046b9 · audit A · 10 stars
journal-requirements-check SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/journal-requirements-check/SKILL.md · 期刊要求核对(乔淼PhD · AI学术训练营 · AI学术工作流 · 投稿与审稿)。从作者指定期刊实际读到的要求(作者指南、模板、投稿系统说明、编辑信)逐条提取,记录来源位置、适用范围、强制还是建议,与确认稿逐项比对差距,形成可追溯的期刊要…
v1.1.0 · audit A · 10 stars
knowledge-module-gen SKILL.md skill
qiaomiaojoe/ai-academic-workflow · skills/knowledge-module-gen/SKILL.md · 知识模块生成(乔淼PhD · AI学术训练营 · AI学术工作流 · 文献分析步骤)。按知识模块清单逐模块读全文生成 M_n.md:机械抽取模块 prompt(不改写不补全)、flag 而非 ask、map-reduce…
git:20261024.d6cd910 · audit A · 10 stars

Every file in qiaomiaojoe/ai-academic-workflow

Browse by kind, by grade A, or by owner.