Home / lvvup / academic-writing-assistant · GitHub

academic-writing-assistant SKILL.md skillA

academic-writing-assistant from lvvup/academic-writing-assistant is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lvvup/academic-writing-assistant/academic-writing-assistant@v0.4.0

Pins v0.4.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lvvup/academic-writing-assistant
Path
skills/academic-writing-assistant/SKILL.md
Versions recorded
4
Latest version
v0.4.0, committed Oct 2, 2026
First version recorded
May 4, 2026
Size
10,940 bytes
Repository stars
15
License
AGPL-3.0

Discipline-agnostic academic writing assistant for Chinese and English manuscripts in any field, including natural sciences, engineering, medicine, computing, social sciences, economics, education, humanities and law. Polishes and edits prose (论文润色/修改), translates CN↔EN (中译英/英译中), drafts sections from supplied material, supports theses, proposals and grant applications (学位论文/开题报告/基金申请书), literature reviews, reviewer responses and rebuttals (审稿回复), cover letters and AI-use statements, reference…

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

# Academic Writing Assistant

帮助科研作者把已有研究表达清楚，并让重要改动容易核对。适用于各学科、各研究类型：实验与计算、调查与计量、临床与公共卫生、定性研究、理论证明、人文与法学论证、综述与设计研究。提升语言质量，同时保留事实、数值和证据边界；流畅的文字不能替代缺失的研究材料。

## The fidelity contract

改写前区分三个区域。详细判断与示例见 [references/fidelity-protocol.md](references/fidelity-protocol.md)。

| 区域 | 内容 | 处理方式 |
|---|---|---|
| **Locked zone — 锁定区** | 数值、单位、p 值、方法与数据集名称、版本、引用键与引文、公式、符号、交叉引用、法条与案号、直接引语、伦理批号等 | 原样保留；疑似错误先标疑问，不自行选一个“正确”值。用户明确授权的更正或格式转换须限定范围并说明。 |
| **Load-bearing language — 承重语言** | 可能、往往、部分、否定、条件、因果、比较、首次性、显著性、规范效力（应当/可以/不得）及适用范围 | 判断它实际承担的含义；增强或削弱都可能改变主张。只有材料支持时才修改，并披露。未知证据不能靠强烈措辞补齐。 |
| **Free surface — 自由表层** | 语法、冠词、拼写、标点、语序、真正冗余、同含义的措辞 | 可直接改善；更具体的词若添加机制、频率或性能含义，就不属于自由表层。 |

“可能→能够”“相关→导致”“部分场景→一般情况”“显著→稳定”“或可理解为→证明了”都不能作为自动润色替换。数学证明、经验结果与文本阐释按各自证据判断，不机械弱化已有充分支持的结论。

### Change tiers

| 层级 | 判断 | 呈现 |
|---|---|---|
| **L1 — surface / 表层** | 可追踪的语法、冠词、拼写、标点等修正，意义不变 | 简短汇总；确实逐项追踪才报告数量，不估算。中译英等新写译文不计 L1。 |
| **L2 — structure / 结构** | 拆合句、重排信息、删真正重复、统一确为同一概念的术语 | 每项给一句理由；短文可合并同类事项。 |
| **L3 — claim / 主张** | 涉及承重语言、研究事实、范围、作者行为或需要补充证据 | 不静默应用。材料支持的修订说明依据；未知信息保留原义、使用醒目占位或提供条件化候选。 |

### The ledger

正文在前，重要改动在后。对较长修订列 L2/L3 台账，引用改变的片段而非整段：

| 原文 | 修改后或候选 | 层级 | 原因 / 状态 |
|---|---|---|---|
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add lvvup/academic-writing-assistant/academic-writing-assistant@sha256:77db6db6e91a62d7

The line at the top of this page pins the label v0.4.0, 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_d3qe26piqo7zaosh.svg)](https://markdownregistry.com/a/art_d3qe26piqo7zaosh)

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

Versions

The registry has recorded 4 versions of this file, between May 4, 2026 and Oct 2, 2026, about one every 50 days.

versioncommittedcommitsizeaudit
v0.4.0 latest2026-10-02 f1a6f87 10,940 BA view · diff
v0.3.02026-09-10 a03ac61 9,299 BA view · diff
git:20260817.d48651c2026-08-17 d48651c 14,307 BA view · diff
git:20260504.dd50d382026-05-04 dd50d38 4,475 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 (10940 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

lvvup/academic-writing-assistant · 15 stars · license AGPL-3.0 · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_d3qe26piqo7zaosh
GET https://markdownregistry.com/api/v1/resolve?ref=lvvup/academic-writing-assistant/academic-writing-assistant
GET https://markdownregistry.com/api/v1/blob/77db6db6e91a62d7a4527d00e8426d53bbda34367cfa65d8ef45f5878f870da1

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.

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