paper-screen SKILL.md skillA
paper-screen 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-screen@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-screen/SKILL.md- Versions recorded
- 3
- Latest version
- v0.1.8, committed Oct 10, 2026
- First version recorded
- Jul 27, 2026
- Size
- 15,962 bytes
- Repository stars
- 46
- License
- a license file GitHub does not identify
Paper 系统综述筛选命令（PRISMA 2020 筛选台账 + 流程图生成器）。当用户要做系统性文献综述、做 PRISMA 筛选、定纳入排除标准、两轮筛选文献、文献去重、要 PRISMA 流程图、要数据提取表、要偏倚风险评估清单、要 PRISMA 报告规范自查，或说"帮我做系统综述""这批文献怎么筛""纳排标准怎么定""要画 PRISMA 流程图""筛选流程图的数字对不上"时使用——即使用户只说"系统综述筛一下""PRISMA 走一遍""meta 分析前面那步文献筛选"也应使用。行为铁律：纳入/排除由用户逐篇拍板，AI 只陈列该文与每条纳排标准的对应事实 + ❓，产物中绝不出现"建议纳入/建议排除"；流程图每一级数字一律由 `scripts/screen.py` 从筛选台账机械算出并通过守恒校验，LLM 不手写任何一个数字、脚本报错就不出图；台账每行必指 `literature/文献笔记表.md` 的真实条目，排除理由必是用户原话或用户选的理由码；确认前零落盘。不替用户判纳排、不编文献、不算元分析统计量（效应量/异质性 I²）、不自动判定 PRISMA 27…
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-screen：系统综述筛选（PRISMA 2020 台账与流程图） 帮用户把**已检索到的一批文献**按自己定的纳排标准筛成综述的纳入集，并产出经得起审稿的 PRISMA 记录。你（执行本 skill 的宿主 agent）做的事：**读 `literature/` 笔记表与检索日志 → 判学科梯队 → 引导用户逐条定纳排标准 → 建筛选台账、逐篇陈列该文与各条标准的对应事实 → 用户逐篇拍板 → 跑 `scripts/screen.py` 机械算数并校验守恒 → 落 HTML+MD 双产物 + 台账 + 提取表**。 本 skill 覆盖学术研究「5 阶段 23 环节」标尺中**阶段 A｜选题与立项**的**环节 3（文献回顾）里的系统性文献综述**这一段；**不覆盖**检索本身（归 `/paper-search`）、综述结构化写作（归 `/paper-outline`，其骨架库已有「系统性综述（PRISMA）」专节）、引用存在性核验（归 `/paper-verify`）、元分析统计合成（**明确不做**，见「越界转化」）。上游消费 `/paper-search` 的 `literature/文献笔记表.md` 与 `literature/检索日志.md`（PRISMA-lite）。本 skill 是**产物型 + 脚本型** skill——会往 `literature/` 落台账与报告、往 `.paper/` 写使用留痕。**筛选与计数无网络依赖**，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），与其余报告型命令一致。 **核心立场（这条决定本 skill 长什么样）**：系统综述的可信度全在**筛选过程的可追溯**与**计数的守恒**。系统是一个**筛选台账管理器 + 机械计数器**——主动陈列每篇文献与每条标准的对应事实、机械算出各级计数、把数字对不上的台账拦下来，但**每一篇纳不纳入的判断交回用户**。裸模型面对"帮我筛这批文献"会直接给出纳入清单、并顺手编一张数字自洽但与实际不符的流程图；本 skill 把对应事实**陈列**出来、把判定**留**给研究者，并且让**脚本**而不是模型来数数。 ## 三条不变（优先级最高，高于本文其余一切） ① **不替用户判纳排**。逐篇只陈列「该文与每条纳排标准的对应事实」（例：「标准 3 要求 RCT；该文摘要含 randomized controlled trial」），纳入/排除由用户逐篇拍板、每篇标 ❓。**产物中不得出现「建议纳入」「建议排除」「符合纳入条件」及任何等价表述**。筛选是研究决策，落在用户一侧。 …
Read the whole file at its exact version.
How to install
mdr add cabbage2000-lab/paper-tutor-skills/paper-screen@sha256:5c4bf472a1663d4bThe 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_iz4kq7fmd7alrevp)
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 | 15,962 B | A | view · diff |
| git:20260729.2a5a7fb | 2026-07-29 | 2a5a7fb | 15,767 B | A | view · diff |
| git:20260727.4c674fa | 2026-07-27 | 4c674fa | 15,780 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 (15962 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_iz4kq7fmd7alrevp GET https://markdownregistry.com/api/v1/resolve?ref=cabbage2000-lab/paper-tutor-skills/paper-screen GET https://markdownregistry.com/api/v1/blob/5c4bf472a1663d4b82b99439c826812141f0843e280d1645da9e1515921694b9
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.