paper-explainer

paper-explainer is a skill for Codex from sanqi-cd/Sanqi-Skills. It costs 107 tokens per session (1,975 once invoked), scanned A, original, MIT.

A workflow for turning a research paper into a standalone, plain-language Markdown study guide. It covers the paper's background, method, experiments, conclusions, limitations, and related work, with explanations of unfamiliar terms.

In plain words
What is it for?
Use it for a close reading of a paper provided as a PDF or arXiv link. It can explain formulas and methods, summarize experiments, note details needed for reproduction, and identify missing evidence.
Why use it?
It helps readers understand a paper without treating a short abstract as the whole study. It also marks what the authors claim, what the paper supports, and what is not known.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex; built for openclaw.

Good fit Use it for a close reading of a paper provided as a PDF or arXiv link. It can explain formulas and methods, summarize experiments, note details needed for reproduction, and identify missing evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sanqi-cd/sanqi-skills/paper-explainer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sanqi-cd/Sanqi-Skills --skill paper-explainer
Clone the repo
git clone --depth 1 https://github.com/sanqi-cd/Sanqi-Skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for paper-explainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/paper-explainer/github.svg)](https://agentmods.dev/skills/sanqi-cd/sanqi-skills/paper-explainer)
Your own site
<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/paper-explainer"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/paper-explainer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for paper-explainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/paper-explainer"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/paper-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,975 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.01975
Opus 5 $0.00053 $0.00988
Sonnet 5 $0.00021 $0.00395
Haiku 4.5 $0.00011 $0.00198

Measured 11d ago against content hash 31dd2173a85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

paper-explainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_note.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

paper-explainer/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

论文解读

目标

按「引言/方法/实验/结论」拆解论文,用通俗语言解读核心思想,标注可复现细节,输出一份结构化 Markdown 笔记。

开始前准备

  • 确认用户提供了 PDF 文件或 arXiv 链接
  • 仅给论文标题时,先搜索论文再让用户确认是哪篇,不要盲猜
  • 论文超过 50 页时,询问用户是否需要完整解读还是只解读核心部分
  • PDF 扫描件 OCR 质量太差无法提取正文时,告知用户并停止
  • 用户给多篇但未指定时,停下来确认

工作流程

Step 1: 获取论文全文

  • 如果是 PDF:提取正文(含标题、作者、摘要、所有章节)
  • 如果是 arXiv 链接:获取论文元数据和 PDF,提取正文
  • 仅给标题时:搜索 arXiv / Google Scholar,列出候选,请用户确认后再获取全文
  • 提取失败时明确告知原因,不编造内容

产出:论文完整正文 + 元数据(标题、作者、发表年份/会议、链接)

Step 2: 识别论文结构

通读全文,识别各章节对应关系。常见结构映射:

  • Introduction / 引言 / 背景 → 引言
  • Method / Proposed Approach / 方法 / 模型 → 方法
  • Experiment / Evaluation / Results / 实验 / 结果 → 实验
  • Conclusion / Discussion / 结论 / 讨论 → 结论

如果论文结构不标准,按最接近的逻辑归类,并在笔记中说明归类依据。

产出:章节映射表 + 每个章节的核心要点速记

先判断论文类型,再调整阅读重点:

  • 算法/模型论文:目标函数、模块关系、计算代价、消融和基线公平性。
  • 系统论文:工作负载、系统边界、吞吐/延迟、资源开销和故障条件。
  • 实证/社会科学论文:研究设计、样本、变量、效应量、稳健性和外推范围。
  • 综述论文:检索范围、分类框架、覆盖缺口和结论时效性。

Step 3: 逐章解读

对每个章节完成以下四项任务:

A. 核心内容简述:用 3-5 句话概括本章做了什么,不用术语堆砌 B. 通俗类比:至少给 1 个生活化类比帮助理解。如"注意力机制就像一个读者在翻译句子时,每写一个词都会回看原文中最相关的部分" C. 术语解释:本章首次出现的专业术语给出简明解释(一句话),后续出现不重复 D. 可复现标注(重点在方法&实验章节):标注数据集名称/规模、超参设置、硬件环境、关键实现细节。如缺信息则注明"论文未提及"

所有关键结论使用 作者陈述论文证据解读未知 标签,并附 [p. 7][§3.2][Figure 4][Table 2] 等定位符。不得把自己的推断写成作者结论。

产出:四个章节的解读草稿,每章含 A/B/C/D 四项

Step 4: 质量检查

对照质量标准逐项自检,不通过的章节回修:

  • 每个 section 有至少 1 个通俗类比
  • 方法章节标注了数据集、超参、环境等可复现细节
  • 结论章节区分了"作者声称"与"客观实验结果"
  • 首次出现的术语有简明解释
  • 实验局限性已标注(如有)
  • 关键结论有来源定位,且作者陈述、论文证据和解读已分开

references/quality-rubric.md 评分;总分低于 10/12 或“证据完整性”为 0 时必须回修。

产出:自检通过的解读终稿

Step 5: 输出 Markdown 笔记

按以下格式输出最终笔记:

# [论文标题]

**作者**: [作者] | **发表**: [会议/期刊, 年份] | **链接**: [arXiv/DOI]

## 来源与证据边界
[使用了全文/摘要/局部页面;缺失、OCR 不确定或无法访问的部分]

## 一句话速读
[不超过 80 字的核心贡献概括]

## 引言
[核心内容简述]
[通俗类比]
[关键术语解释]

## 方法
[核心内容简述]
[通俗类比]
[关键术语解释]
[可复现细节:数据集 | 超参 | 环境 | 实现要点]
[未提及的细节]

## 实验
[核心内容简述]
[通俗类比]
[主要结果]
[可复现细节]
[实验局限性(如有)]

## 结论
[作者声称的贡献]
[客观实验结果支撑了什么]
[未解决的问题/未来方向]

## 一句话总结
[论文最值得记住的一个点]

产出:符合格式的结构化 Markdown 笔记

Read the full file on GitHub · 167 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 167 lines · 107 tokens per session scan A 31dd2173a85e

Subscribe to this mod's changes

paper-explainer is a skill published in the GitHub repository sanqi-cd/Sanqi-Skills (27 stars, last pushed 9d ago), licensed MIT. It adds 107 tokens to every session and 1,975 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

study-strategy-selector

Recommend practical study strategies matched to the material, learning goal, assessment, time, and learner constraints. Use for revision planning, homework routines, independent study, replacing ineffective habits, or adapting recall, spacing, explanation, and practice activities.

iflytek/skillhub · 52 tokens

retrieval-practice-generator

Generate low-stakes retrieval-practice questions with grounded answer notes and implementation guidance. Use for quiz starters, revision activities, delayed recall, misconception checks, or adapting recall difficulty.

iflytek/skillhub · 41 tokens

exam-ready

Prepare a concise exam review from study materials and a syllabus supplied by the user. Use for topic summaries, recall questions, MCQ cues, and time-limited revision plans that must stay grounded in those materials.

iflytek/skillhub · 45 tokens

interview-prep

Technical interview preparation expert for algorithms, system design, and behavioral questions.

RightNow-AI/openfang · 18 tokens

Vibe Coding Mastery

The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testing strategies, debugging playbooks, and production graduation checklists. Works with Claude Code, Cursor, Windsurf, Copilot, and any AI coding tool.

LeoYeAI/openclaw-master-skills · 61 tokens

ai-shifu-course-creator

Convert raw course material into optimized, runnable MarkdownFlow teaching scripts and deploy them as live courses through a five-phase pipeline covering segmentation, orchestration, generation, optimization, and deployment.

LeoYeAI/openclaw-master-skills · 43 tokens