thesis-defense SKILL.md skillA
thesis-defense 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-defense@git:20260704.1ab6c99Pins git:20260704.1ab6c99 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-defense/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260704.1ab6c99, committed Jul 4, 2026
- First version recorded
- Jul 4, 2026
- Size
- 9,087 bytes
- Repository stars
- 4
- License
- a license file GitHub does not identify
ZJU MEM 答辩准备一站式，覆盖**中期答辩 / 预答辩 / 盲审 / 最终答辩**全部环节 — 评委视角主线审计 (30秒扫骨架+三连接测试+题目/目录/摘要可扫描性)、答辩策略、预测问答、套官方模板做PPT (桥接 report-ppt-builder)、从真实答辩录像提取老师问答(桥接 video-transcribe-analyze)、 把材料压成≤2页高密度答辩手卡并打印；**中期答辩模式**另含 ZJU 中期报告会五段 PPT 逐页结构、 讲稿与 100 分制评审打分。触发词：答辩准备、中期答辩、中期报告会、中期汇报PPT、预答辩、 盲审准备、最终答辩、答辩PPT、模拟问答、defense、midterm defense、答辩策略、主线梳理、答辩手卡、答辩打印。 先读 references/midterm-playbook-实战.md（通用打法）；中期材料结构见 references/midterm-defense-ppt.md。.
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
# 答辩准备 为 ZJU MEM 实践导向论文提供完整的答辩准备方案。核心原则：重点防范预答辩/盲审常见风险（数据真实性、实用性不足、AI 工具使用伦理、格式不规范），输出帮助用户自信应对 15-20 分钟陈述 + 专家提问。 > **⭐ 先读实战 Playbook**：`references/midterm-playbook-实战.md`——含**评委真实阅读模型**(30秒扫骨架→追因果线→三连接测试)、**主线重建 + 导航图可扫描性审计**、**答辩手卡高密度打印做法**、**从答辩录像提取老师问答**(桥接 video-transcribe-analyze)、**MEM 三致命定调问题通用答法**。通用打底看 `defense-strategy.md`，实战方法看本 playbook；**中期答辩模式**的 ZJU 五段 PPT 逐页结构/讲稿/中期特有问答/评审打分见 `references/midterm-defense-ppt.md`。 ## 触发场景 - 用户说"预答辩准备""盲审模拟""答辩 PPT""常见问题""模拟问答""答辩策略" - 中期报告通过后或盲审前需要准备 - 论文主体完成后需要答辩材料 ## 流程 ### Step 1: 确认阶段与材料 确认当前论文阶段（中期后/预答辩/盲审/最终答辩），扫描已有材料： - 论文章节完成情况 - 图表、数据分析结果 - 已有 PPT 或答辩材料 ### Step 2: 加载答辩策略 读取 `references/defense-strategy.md`，获取完整答辩指导： - 答辩陈述框架（15-20分钟时间分配） - 核心创新点提炼方法（四维创新框架） - 实践价值论述模板（三段式） - 局限性应对话术（承认-转化-弥补） - 8-12个常见问题分类（方法论/数据/创新/实践/局限性） - PPT大纲模板（25-30页结构） - 模拟问答技巧 ### Step 3: 生成答辩策略文档 基于论文实际内容，生成个性化答辩策略，写入 `.project/08_答辩准备/答辩策略.md`： - **陈述框架定制**：按论文实际章节填充时间分配 - **创新点提炼**：用四维框架分析论文创新点 - **实践价值论述**：基于论文实际数据和效果撰写三段式论述 - **局限性预案**：识别论文3-5个实际局限，逐条准备应对话术 ### Step 4: 生成预测问答 生成 15-20 个答辩常见问题，覆盖 5 大类别，写入 `.project/08_答辩准备/预测问答.md`： **方法论类（3-4题）：** - 为什么选择 PDCA 而非其他方法论？ - 数据采集的科学性如何保证？ - 研究方法的局限性及弥补方案？ **数据类（3-4题）：** …
Read the whole file at its exact version.
How to install
mdr add gxgeek-n/wenqu-mem/thesis-defense@sha256:16f3c5abd03354acThe line at the top of this page pins the label git:20260704.1ab6c99, 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_5ejxdywfgvczhftj)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, all committed on Jul 4, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260704.1ab6c99 latest | 2026-07-04 | 1ab6c99 | 9,087 B | A | view · diff |
| git:20260704.1171a86 | 2026-07-04 | 1171a86 | 9,174 B | A | view · diff |
| git:20260704.eb9bb8b | 2026-07-04 | eb9bb8b | 7,598 B | A | view · diff |
| git:20260704.d00de62 | 2026-07-04 | d00de62 | 7,359 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 (9087 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_5ejxdywfgvczhftj GET https://markdownregistry.com/api/v1/resolve?ref=gxgeek-n/wenqu-mem/thesis-defense GET https://markdownregistry.com/api/v1/blob/16f3c5abd03354ac06027fcdfbfdbd7e4854239c4caf64e126c2971995e21119
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.