paper-revise SKILL.md skillA
paper-revise from cabbage2000-lab/paper-tutor-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cabbage2000-lab/paper-tutor-skills/paper-revise@v0.1.8Pins v0.1.8 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cabbage2000-lab/paper-tutor-skills
- Path
skills/paper-revise/SKILL.md- Versions recorded
- 5
- Latest version
- v0.1.8, committed Oct 10, 2026
- First version recorded
- Jul 27, 2026
- Size
- 23,477 bytes
- Repository stars
- 46
- License
- a license file GitHub does not identify
Paper 修订辅助命令（修订建议对照表 + 逐点回复信起草器）。当用户投稿/答辩后收到审稿意见要写回复信、要逐点回复审稿人、要改稿、要准备 point-by-point response、要 response letter、要修订建议、要把审稿意见逐条回应、或说"帮我写回复信""审稿意见怎么回""逐点回复怎么写""这些意见怎么改""改稿建议""答辩意见回复"时使用——即使用户只说"帮我修订""回复审稿人""revise 一下""改稿"也应使用。行为铁律：基于用户已有研究事实起草候选回复措辞（不编新结果/不引未读文献/不夸大）、修订方向陈列（改哪段+修订要点、不代写整段新正文）、采纳决定由用户逐条拍板（每条标 ❓ 待用户决定）、不替用户定采纳/拒绝、不替用户写整段新正文（归 /paper-draft）。两路输入：真实审稿意见粘贴 + paper-review 模拟下游（自动判别）；确认前零落盘。"帮我编数据应付审稿人""帮我忽略不利意见""帮我整段新正文直接写了""帮我替他人在审稿件写审稿意见"走硬拒绝或让路。.
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-revise：修订辅助（修订建议对照表 + 逐点回复信起草器） 帮用户从**已完成的 draft 正文 + 评审意见**出发，逐条产「修订建议对照表 + 逐点回复信初稿」。你（执行本 skill 的宿主 agent）做的事：**读 draft 正文 + 读评审意见（两路自动判别）+ 读 verify/outline（可选）→ 判学科 + 意见归类 → 逐条起草对照表（修订方向 + 候选回复措辞）+ 逐点回复信初稿 → 停检查点等确认 → 落 Markdown 产物 + 渲染 HTML 视图**。 本 skill 覆盖学术研究「5 阶段 23 环节」标尺中**阶段 D｜评审与修订**的**环节 18（修订辅助）**；**不覆盖**环节 17 模拟评审（归 `/paper-review`）、引用存在性核验（归 `/paper-verify`）、结论夸大检查（归 `/paper-claim`）、整段新正文共写（归 `/paper-draft`）、投稿准备（归 `/paper-submit`）。上游消费 draft 正文（必要）+ paper-review 模拟意见（可选）+ verify 产物（可选）；下游供 draft（修订段落共写）+ logic / verify（修订后复查）。本 skill 是**产物型** skill——会往 `review/` 落一份 Markdown 修订与回复档案（+ 由脚本渲染的 `.html` 视图）、往 `.paper/` 写「成句生成」级使用留痕；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）**：投稿 / 答辩后逐点回复审稿人是修订闭环的关键，但**编数据应付 / 替用户定采纳 / 代写整段新正文**都是 AI 越界的高风险动作。系统是一个**对照表 + 回复信起草器**：把每条审稿意见 →「修订方向（改哪段 / 修订要点、可执行但不代写）+ 候选回复措辞（基于用户已有研究事实、可改写）」两栏陈列；**采纳决定由用户逐条拍板**（每条标 ❓ 待用户决定）、整段新正文交 draft。**起草由系统做、基于事实不编内容、定稿由用户拍板**。这既是项目「核心分工原则」在修订环节的落地，也是 revise 区别于裸模型的核心差异化：裸模型面对"帮我写回复信"会过度辩护（编依据、夸大已做工作）、或直接代写整段新正文（越 draft 边界）、或替用户下"这条不用理会"判断（替用户做研究决策）——任一动作都让回复信在编辑 / 答辩委员会对照正文与数据一查就穿帮。 ## 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
mdr add cabbage2000-lab/paper-tutor-skills/paper-revise@sha256:3fbbb0c129d4fb54The 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.
[](https://markdownregistry.com/a/art_wmkhbe6nhz7zh5qp)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 27, 2026 and Oct 10, 2026, about one every 19 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.8 latest | 2026-10-10 | f5460b7 | 23,477 B | A | view · diff |
| git:20260729.2a5a7fb | 2026-07-29 | 2a5a7fb | 23,279 B | A | view · diff |
| git:20260729.d04f4a5 | 2026-07-29 | d04f4a5 | 23,292 B | A | view · diff |
| git:20260729.5b6e794 | 2026-07-29 | 5b6e794 | 23,065 B | A | view · diff |
| git:20260727.4c674fa | 2026-07-27 | 4c674fa | 22,549 B | B | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (23477 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
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_wmkhbe6nhz7zh5qp GET https://markdownregistry.com/api/v1/resolve?ref=cabbage2000-lab/paper-tutor-skills/paper-revise GET https://markdownregistry.com/api/v1/blob/3fbbb0c129d4fb54920fc653c9a2111d90107fda0c6bb0b59ab90b26db6bdd44
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.