thesis-style SKILL.md skillA
thesis-style from gxgeek-n/wenqu-mem is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add gxgeek-n/wenqu-mem/thesis-style@git:20260807.c0a57aaPins git:20260807.c0a57aa in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- gxgeek-n/wenqu-mem
- Path
skills/thesis-style/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260807.c0a57aa, committed Aug 7, 2026
- First version recorded
- Jul 4, 2026
- Size
- 14,256 bytes
- Repository stars
- 4
- License
- a license file GitHub does not identify
浙大MEM学位论文中文语体skill。以多篇通过答辩的同类MEM学位论文为体裁基准，提炼其句式节奏、段落形态、引号纪律等语体规律，并据此校准"何为真AI痕迹"。 只管"句子怎么写"：句式节奏、段落形态、图表引出、数据表述、引号纪律、小结与局限写法。 不管"写什么"：目录结构、章节安排、数据、引用一律不动（以本论文现有结构和 CLAUDE.md 为准）。 用途：修改论文正文措辞、诊断模板化表达、语体审查、按范文口吻改写段落、清理交付物中的路径与内部生产过程泄漏。 当用户说"按范文写法改""去AI腔""润色正文""这段像AI写的""对标范文""清理路径/内部提示词/生产痕迹"时使用；/thesis-check 做语体维度审查时也应参照本skill。 分工（表达风险三角）：判定"像不像AI"→ thesis-deai-review；AIGC 检测报告复核→ aigc-reduce-playbook； 本 skill 只管**语体写法**（怎么把句子写得像范文）。范文的结构/章节对比 → thesis-ref-analysis。.
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
# thesis-style · MEM范文语体 > 真人论文的"人味"不在精致，在平实：因果链推进、数字带毛边、敢写副作用、允许克制的不完美。AI稿暴露的恰恰是过于顺滑工整。 ## 硬约束（先读这个） 1. **结构不动**：目录、章节、小节安排按本论文现状（CLAUDE.md 各结构规范优先于范文——例如本论文 Ch2-6 每章保留承上启下引言段，尽管部分参考论文开门见山，范文H公司是有引言段的，跟范文）。 2. **数据不动**：任何数字、统计量、引用不因改写而变；严禁编造。 3. **禁止整段LLM重写**：只做定点替换与句式微调（AIGC检测铁律：全量重写会叠加AI指纹）。 4. 范文本身有笔误和语病（"股那里计划""做为"）——**取其平实，不模仿其错误**。 ## 核心认知（排他性洞察，三组语料交叉验证） 1. **因果顺承链驱动，不靠转折**。真人论文用"为了→通过→从而/所以/由此可见"推进，"然而/不过"在6篇中为0或近0，"但"≤1/千字。发现文字靠"然而""但是"频繁转弯，就是改写信号。 2. **真人比AI"糙"**。长短句悬殊（同段20字句与120字句混排）、段落长短不齐（80字与400字相邻）、数字带毛边（约/左右/将近/大概）。改稿时不要把这些"修整齐"。 3. **效果数字三件套**：改进前值 + 手段归因 + 改进后值，再加克制限定。范文句型："实施前平均定位时间为48小时，优化后通过与JIRA集成……定位时间缩短至4小时内""得到了一定的改善"。效果从不满打满算。 4. **引号纪律**：中文引号只给五类——①术语/问题首次定名（**定名后全文一字不改地复用**，这是范文的全文锚点技巧）②流程链/口号（"发现—记录—分配—解决—验证"）③访谈原话④系统界面字面量（"待整改"）⑤偶发借喻（"多米诺骨牌效应"）。**绝不给普通短语加引号强调**（10篇全零）。 5. **理论=判据，不=知识**。理论出场即干活："这与CMMI的'项目监控与控制（PMC）'过程域要求严重不符"；引文献立即消化转用当论证台阶，不做"某某认为…某某指出…"流水账（流水账只允许出现在§1.2综述小节内，且末尾必有述评）。 6. **禁止"评审补丁式改稿"（用户铁律）**。处理评审意见不得用括注免责补丁去堵。范文实测括注≈2.4/千字且内容全为技术记号（缩写展开/工具示例/数据来源/编号/统计量），**限定、免责、口径声明塞进句中括号的写法范文为0处**；逐条评审意见各打一个括号补丁，堆起来就是最重的AI味之一。正确做法按优先级：①改正文本身使其不再需要免责 ②写成独立正句（"该结果来自小样本回访，尚需更大样本复测"）③移入表注/脚注 ④别处已交代过的直接删。 …
Read the whole file at its exact version.
How to install
mdr add gxgeek-n/wenqu-mem/thesis-style@sha256:ebec827a0c8e8d40The line at the top of this page pins the label git:20260807.c0a57aa, 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_aqpg4qbn2az5qi2i)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 4, 2026 and Aug 7, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260807.c0a57aa latest | 2026-08-07 | c0a57aa | 14,256 B | A | view · diff |
| git:20260726.b8c0edb | 2026-07-26 | b8c0edb | 14,234 B | A | view · diff |
| git:20260726.6c7e134 | 2026-07-26 | 6c7e134 | 14,256 B | A | view · diff |
| git:20260726.6740b43 | 2026-07-26 | 6740b43 | 13,983 B | A | view · diff |
| git:20260704.1ab6c99 | 2026-07-04 | 1ab6c99 | 13,343 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 (14256 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
gxgeek-n/wenqu-mem · 4 stars · license a license file GitHub does not identify · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_aqpg4qbn2az5qi2i GET https://markdownregistry.com/api/v1/resolve?ref=gxgeek-n/wenqu-mem/thesis-style GET https://markdownregistry.com/api/v1/blob/ebec827a0c8e8d4093fead38a6fd04b5b9605b47ca40054e5c09de628c2c4ac4
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.