paper-style SKILL.md skillA
paper-style 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-style@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-style/SKILL.md- Versions recorded
- 3
- Latest version
- v0.1.8, committed Oct 10, 2026
- First version recorded
- Jul 27, 2026
- Size
- 19,410 bytes
- Repository stars
- 46
- License
- a license file GitHub does not identify
Paper 风格校准命令（全文风格一致性校准 + 个人风格基线 + AIGC 误判申诉特征陈列）。当用户要查全文文风是否一致、要校准各章语体、要建立自己的写作风格基线供后续起草复用、或论文被 AIGC 检测判为 AI 生成要向学校/期刊申诉时使用——即使用户只说"这几章读着不像一个人写的""帮我看看文风统不统一""我的句子是不是太长了""建立我的文风基线""这段被判成 AI 了怎么办"也应使用。行为铁律：五类风格特征（句长分布/虚词密度/引用位置/人称频次/四字格与术语密度）一律由 `scripts/style_metrics.py` 机械算出，LLM 只解读数字、绝不给"读起来像/不像 AI""文风不够学术"这类无依据判断；默认只陈列偏移与着力点、不代改一句定稿（用户明确要示例改法才给 1-2 句并标"示例、非定稿"）；术语密度与四字格为近似值（零第三方依赖不引分词）、每处必标"近似"；确认前零落盘。硬拒"帮我降 AI 率/躲过检测/改到检测不出来"——本命令服务全文一致性与误判申诉、不服务规避检测，指路 /paper-disclose…
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-style：风格校准（特征机械计算 + 章节间偏移陈列） 帮用户查**全文风格是否前后一致**、把自己的写作风格**沉淀成可复用的基线**、在被 AIGC 检测误判时**拿到客观特征作申诉材料**。你（执行本 skill 的宿主 agent）做的事：**读 `manuscript/` 正文 → 判学科梯队 → 与用户确认范围与模式 → 跑 `scripts/style_metrics.py` 机械算特征 → 按章节陈列特征表与偏移、每条着力点配疑问句 → 落 HTML+MD 双产物（模式 b 另落风格基线）**。 本 skill 覆盖学术研究「5 阶段 23 环节」标尺中**阶段 C｜成文**的**风格一致性**这一段；**不覆盖**段落起草（归 `/paper-draft`）、论证链检查（归 `/paper-logic`）、结论夸大检查（归 `paper-claim`）、AI 使用披露（归 `/paper-disclose`）、查重降重（PRD §446 明文不做，指路知网）。上游消费 `manuscript/` 下的正文（`paper-draft` 产的 `正文草稿.<章节路径>.md`，或用户自己写的任意 markdown）。本 skill 是**产物型 + 脚本型** skill——会往 `manuscript/` 落报告与风格基线、往 `.paper/` 写使用留痕。**特征计算无网络依赖**，断网照常可跑；HTML 产物的排版按仓库约定走 Tailwind CDN，断网时降级为无样式 HTML（内容可读、排版失效），与其余 15 个报告模板一致。 **核心立场（这条决定本 skill 长什么样）**：风格是**算出来的**，不是感觉出来的。系统是一个**特征计算器 + 偏移陈列器**——机械算出六组可测量的数字、按变异系数排出哪个特征在章节间抖得最厉害，但**是否要改、改哪里、改到什么程度全部交回用户**。裸模型面对"帮我看看文风一致吗"会张口就说"整体较为流畅、但第三章略显生硬"——这句话不可复现、无从追溯、且极易编。本 skill 用数字替换掉这句话，并且**明文禁止**它出现。 **它还解决一个上游痛点**：`paper-draft` 现状是每次会话都要用户重贴风格样本，给不出就落降级档。模式 b 把基线持久化成 `manuscript/风格基线.md` 后，draft 下次直接读——**把 draft 的常态降级档变成常态正常档**。 ## 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-style@sha256:c48660d164a9ba65The 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_igyud7r7xokcyhcs)
2 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.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.1.8 latest | 2026-10-10 | f5460b7 | 19,410 B | A | view · diff |
| git:20260729.2a5a7fb | 2026-07-29 | 2a5a7fb | 19,210 B | A | view · diff |
| git:20260727.4c674fa | 2026-07-27 | 4c674fa | 19,237 B | A | 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 (19410 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_igyud7r7xokcyhcs GET https://markdownregistry.com/api/v1/resolve?ref=cabbage2000-lab/paper-tutor-skills/paper-style GET https://markdownregistry.com/api/v1/blob/c48660d164a9ba65828adc3b9e93775dd0390c5de89f430e0c24d0ea886b226b
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.