paper-disclose SKILL.md skillB

paper-disclose from cabbage2000-lab/paper-tutor-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cabbage2000-lab/paper-tutor-skills/paper-disclose@v0.1.8

Pins v0.1.8 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
cabbage2000-lab/paper-tutor-skills
Path
skills/paper-disclose/SKILL.md
Versions recorded
3
Latest version
v0.1.8, committed Oct 10, 2026
First version recorded
Jul 27, 2026
Size
25,585 bytes
Repository stars
46
License
a license file GitHub does not identify

Paper AI 使用说明生成命令(披露汇编器)。当用户要写论文投稿的 AI 使用说明、AI 使用披露、AI 辅助声明、学位论文 AIGC 使用报告,或说"帮我生成 AI 使用说明""要交一份 AI 披露""答辩材料要附 AI 使用情况""AIGC 检测把我误判了要申诉"时使用——即使用户只说"列一下我用了哪些 AI""整理下 AI 使用记录""要交 AI 使用情况说明"也应使用。行为铁律:只读 .paper/ 真实留痕、按 PRD 四级辅助级别(构思讨论 / 大纲结构 / 成句生成 / 语言润色)汇编成可对外披露的 AI 使用说明,绝不编造未发生的留痕;用户可选择隐去某条但顶部强制覆盖声明、不抹除痕迹;不下「AI 占比 X%」价值判断;段落级读者标签服务导师 / 研究生院 / 期刊 / AIGC 检测四类读者;确认前零落盘。不替用户实际跑命令产生留痕(.paper/ 空则让路)、不编造留痕、不下价值结论。"帮我编一份让 AI 看起来用得少的留痕""帮我改 AI 承担字段"走三段式转化。.

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

# paper-disclose:AI 使用说明(披露汇编器)

帮用户把使用 paper 套件过程中**沉淀进 `.paper/`** 的全部结构化留痕,**按 PRD 四级辅助级别**汇编成一份可对外披露的 AI 使用说明。你(执行本 skill 的宿主 agent)做的事:**扫 `.paper/` 留痕 → 按「辅助级别」字段归类到四级 → 摆骨架填条目 → 加段落级读者标签 → 停检查点等用户逐条确认 → 落 HTML+MD 双产物**。

本 skill 覆盖学术研究「5 阶段 23 环节」标尺中**阶段 E|发表与发表后**的**环节 21(署名 / 基金声明 / AI 披露)**;**不覆盖**环节 20 投稿准备(归 `/paper-submit`)、环节 22 发表后传播(项目不覆盖)、环节 23 发表后监测(项目不覆盖)。上游消费所有已发布 / 规划中的产物型 paper 命令(topic / search / verify / outline / draft / abstract / review / revise)写进 `.paper/` 的留痕。本 skill 是**产物型** skill——会往 `submission/` 落一份 HTML AI 使用说明(+ `.md` 兜底)、往 `.paper/` 写元留痕;无网络依赖,断网宿主照常可用。

**核心立场(这条决定本 skill 长什么样)**:disclose 是**留痕汇编器**,不是**留痕生成器**——只读不写、只整理不评判。AI 扫 `.paper/` 已有留痕、按四级归类、如实陈列条目;**取舍权在用户**(可选择隐去某条,但顶部强制覆盖声明)、**事实底线在系统**(不编、不美化、不下价值结论)。这既是项目「核心分工原则」(AI 负责效率、人负责研究决策)在披露环节的落地,也是本 skill 区别于裸模型的核心差异化:裸模型面对「帮我写份 AI 使用说明」会忍不住凭记忆编一份漂亮的「我用了 X 次检索、Y 次整理」,本 skill **只汇编真实留痕**、缺什么标什么、绝不凭记忆补全。

## 三条不变(优先级最高,高于本文其余一切)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add cabbage2000-lab/paper-tutor-skills/paper-disclose@sha256:01f4f21fc99baedd

The line at the top of this page pins the label v0.1.8, 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_rq6alflestglg7kn.svg)](https://markdownregistry.com/a/art_rq6alflestglg7kn)

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

Versions

The registry has recorded 3 versions of this file, between Jul 27, 2026 and Oct 10, 2026, about one every 37 days.

versioncommittedcommitsizeaudit
v0.1.8 latest2026-10-10 f5460b7 25,585 BB view · diff
git:20260729.2a5a7fb2026-07-29 2a5a7fb 25,406 BB view · diff
git:20260727.4c674fa2026-07-27 4c674fa 25,417 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No script tag (matched: <script)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (25585 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

cabbage2000-lab/paper-tutor-skills · 46 stars · license a license file GitHub does not identify · pushed 2026-10-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rq6alflestglg7kn
GET https://markdownregistry.com/api/v1/resolve?ref=cabbage2000-lab/paper-tutor-skills/paper-disclose
GET https://markdownregistry.com/api/v1/blob/01f4f21fc99baedd6f649cfc4607ebe91aa17c0be185b765df43a89d433d7e3a

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 cabbage2000-lab/paper-tutor-skills

CLAUDE.md CLAUDE.md file
cabbage2000-lab/paper-tutor-skills · CLAUDE.md
git:20261010.f5460b7 · audit A · 46 stars
paper-abstract SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-abstract/SKILL.md · Paper 摘要提炼命令(正文→摘要提炼器)。当用户已有论文正文要写摘要、提炼摘要、凝练摘要、生成 abstract、整理论文摘要、学位论文摘要、期刊投稿摘要、关键词,或说"帮我写摘要""从正文提炼摘要""摘要怎么写""我的论文摘要""ab…
v0.1.8 · audit B · 46 stars
paper-anchor SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-anchor/SKILL.md · 文献支撑补齐命令(论断—支撑对照器)。当导师或审稿人说"这段缺文献支撑""文献综述不足""缺少与已有研究的对比", 或用户要给已写好的论断补引用、问"这句话需要引用吗""哪些段落没引用""帮我找支撑这个观点的文献""我这个论断有没有文献支持…
v0.1.8 · audit A · 46 stars
paper-daily SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-daily/SKILL.md · Paper 每日学术雷达命令(抢发检测 + 新发泛读)。当用户手头有研究想法(RQ / 方法 / 想投的会议)、想确认是不是已被人抢发、或想每天泛读该方向新发论文时使用——即使用户只说"今天 arXiv…
v0.1.8 · audit A · 46 stars
paper-doctor SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-doctor/SKILL.md · Paper 环境就绪度体检命令。当用户要检查 Paper 核验/检索环境能不能用、数据源通不通、凭证配没配、运行环境是否满足要求,或说 doctor / 体检 / 自检 / 环境检查 / 能不能用 / 跑不跑得起来 / 为什么核验不了…
v0.1.8 · audit A · 46 stars
paper-draft SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-draft/SKILL.md · Paper 分段正文共写命令(段落正文初稿共写器)。当用户已有论文大纲(/paper-outline 产物或手写大纲)、要逐段展开正文、起草段落、写论文正文、把大纲要点展开成段,或说"帮我把这段引言写一下""这段正文怎么展开""基于大纲写一…
v0.1.8 · audit B · 46 stars
paper-figure SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-figure/SKILL.md · Paper 图表可视化辅助命令(B 诊断 + C 设计建议双模式自适应)。当用户要查图表、图表诊断、图表设计、画图建议、该用什么图、图注怎么写、配色选什么、色盲友好、坐标轴规范、误差棒标注,或说"帮我看看这张图""图表有什么问题""我该画什…
v0.1.8 · audit B · 46 stars
paper-help SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-help/SKILL.md · Paper 命令导航器。当用户问 Paper 能做什么、有哪些命令、该用哪个命令,或说 help / 帮助 / 怎么用 / 命令一览 / 不知道从哪开始时使用——即使用户只说"我想写论文但不知道用什么"也应使用。行为铁律:一轮提问摸清用户当…
v0.1.8 · audit A · 46 stars
paper-import SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-import/SKILL.md · Paper 题录导入命令(题录整理器 + 题录-草稿一致性核对器)。当用户有从知网/Zotero/EndNote 导出的题录要批量整理、整理参考文献、题录入库、做题录与草稿引用的一致性核对、查哪些草稿引用有对应题录、查题录与草稿字段差异,或…
v0.1.8 · audit B · 46 stars
paper-init SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-init/SKILL.md · 为研究项目搭建标准科研工作目录的脚手架命令。当用户要开始一个新研究项目或新论文、想初始化或规范科研项目的目录结构、要搭多项目科研工作区,或提到 paper-init、科研工作目录时使用——即使用户只是说"帮我建个放论文材料的文件夹"也应使用…
v0.1.8 · audit A · 46 stars
paper-logic SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-logic/SKILL.md · Paper 论证链检查命令(结构对应检查器)。当用户已有论文大纲、要查论证逻辑、查 RQ 与方法结果结论是否对应、查论证链是否闭环、查论文逻辑结构,或说"帮我查查论证有没有问题""我的逻辑完整吗""RQ…
v0.1.8 · audit A · 46 stars
paper-method SKILL.md skill
cabbage2000-lab/paper-tutor-skills · skills/paper-method/SKILL.md · Paper 研究设计参谋命令(方法-RQ 匹配检查器 + 方法类引导器)。当用户已有研究问题(RQ)要定研究方法、检查方法能否回答 RQ、选什么方法类、查方法与 RQ…
v0.1.8 · audit B · 46 stars

Every file in cabbage2000-lab/paper-tutor-skills

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