paper-close-read SKILL.md skillA
paper-close-read from daylily-huang/scholarflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add daylily-huang/scholarflow/paper-close-read@git:20261102.7bdf3e0Pins git:20261102.7bdf3e0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- daylily-huang/scholarflow
- Path
skills/paper-close-read/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261102.7bdf3e0, committed Nov 2, 2026
- First version recorded
- Oct 23, 2026
- Size
- 25,006 bytes
- Repository stars
- 41
- License
- MIT
将一篇学术论文制作成离线 HTML 带读页（实证、质性、理论、历史与文本阐释），帮助不愿或难以开始读文献的科研人从问题入门，沿证据路线读懂，再按需逐段对照原文、翻译和批注。适用于无痛读文献、论文拆解、逐段精读、概念图解；不替代多篇综述或正式科学裁定。.
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
# 科研文献轻负担带读 帮助读者跨过论文省略的理解步骤：数据长什么样，作者遇到了什么问题，为什么采用这个方法，结果怎样回答问题。白话要像一位读懂论文的同学在带读，先把事情讲通。保留原文/译文、按需图解和批注；正文默认展开，允许手动折叠。 ## 默认行为 - 已有论文就开始；只有缺少/混淆目标论文、原文获取权限或会改变交付范围时才问。 - 默认保留逐段精读主视图，并在首屏顶部提供不打扰的**渐进带读入口横幅**，引导畏难读者按 **3 分钟入门 → 10 分钟读懂 → 逐段精读** 拾级而上（各路线底部均配下一步衔接按钮）；三分钟按初学读者能在180秒内把握整篇骨架的目标设计，十分钟展开理解所需的中间推理步骤，中文解释、动画手动播放。 - 主阅读区遵循文章实际章节和论证方式；实证文关注摘要、引言、方法、结果与讨论，理论、历史和阐释文章保留其问题、争论、材料与推论结构。题名、作者、单位、日期简列；致谢、书目和出版声明置于末尾。范围、来源和核验记录集中放在页末“来源说明”，顶部只留入口。 - 逐段目录保留原文章节层级；原文缺少小标题或正文跨度较大时，按真实主题用 `guide.reading_outline` 增加二级“阅读分段”，正文对应位置标明“整理者添加”。不能把整篇实质正文压成一个无法定位的入口，也不为了目录整齐改原文段落/顺序/ID。题名作者、单位、致谢与书目归辅助区，见[内容契约](references/content-contract.md#逐段阅读目录与分段)。 - 默认正文18px，支持16/18/20px；英文正体。主要正文按“英文常显＋独立中文译文 → 白话解释 → 逻辑要点”排列；译文、白话和逻辑各自默认展开，可分别点击标题收起，收起中文不隐藏英文；独立公式默认折叠原始 LaTeX 代码，核心独立公式（`eq`）与关键结果表（`table`）在 `translations.json` 中就地补齐「公式白话拆解」（一句总直觉＋关键符号点名）和「读表抓手」（先看哪行哪列、跟哪个基准比）。白话用具体对象、操作与现象补足理解步骤，读者无需先懂术语才看懂解释。逻辑要点共同服务本段论证：前一条的前提、发现或缺口怎样引出后一条；比较段可分支后汇合，不能把并列研究强接成因果。长短、条数由实际推理决定，不固定两条，也不机械改成三条；一句能讲完的承接不硬拆。元信息不做分析。 - 易错点按需写：已经在白话讲清的区别不再重复警告。局部原文疑点在对应处说明；一般来源说明统一放页末。不要按“不能/不等于”等关键词自动搬运旧讲解，也不要给每段补泛化免责声明。 …
Read the whole file at its exact version.
How to install
mdr add daylily-huang/scholarflow/paper-close-read@sha256:35995b9c468fab20The line at the top of this page pins the label git:20261102.7bdf3e0, 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_hge2s5zeibonanc7)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Oct 23, 2026 and Nov 2, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261102.7bdf3e0 latest | 2026-11-02 | 7bdf3e0 | 25,006 B | A | view · diff |
| git:20261031.d2ac39d | 2026-10-31 | d2ac39d | 22,745 B | A | view · diff |
| git:20261030.4cf3946 | 2026-10-30 | 4cf3946 | 21,599 B | A | view · diff |
| git:20261026.a092899 | 2026-10-26 | a092899 | 20,398 B | A | view · diff |
| git:20261023.b8d31fe | 2026-10-23 | b8d31fe | 19,010 B | A | view · diff |
| git:20261023.8093b63 | 2026-10-23 | 8093b63 | 17,633 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 (25006 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
daylily-huang/scholarflow · 41 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hge2s5zeibonanc7 GET https://markdownregistry.com/api/v1/resolve?ref=daylily-huang/scholarflow/paper-close-read GET https://markdownregistry.com/api/v1/blob/35995b9c468fab20f01cecbde94a4db75d8af07d53c0b1d51d1c1d9783d0006a
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.