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.
npx skills add stophobia/deerflow2.0-enhanced --skill paper-researchgit clone --depth 1 https://github.com/stophobia/deerflow2.0-enhancedWrote 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.
[](https://agentmods.dev/skills/stophobia/deerflow2.0-enhanced/paper-research)<a href="https://agentmods.dev/skills/stophobia/deerflow2.0-enhanced/paper-research"><img src="https://agentmods.dev/badge/skills/stophobia/deerflow2.0-enhanced/paper-research/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.
<a href="https://agentmods.dev/skills/stophobia/deerflow2.0-enhanced/paper-research"><img src="https://agentmods.dev/badge/skills/stophobia/deerflow2.0-enhanced/paper-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.01591 |
| Opus 5 | $0.00051 | $0.00796 |
| Sonnet 5 | $0.00020 | $0.00318 |
| Haiku 4.5 | $0.00010 | $0.00159 |
Grade A, and why
paper-research 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 9d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
学术论文调研技能 (Paper Research)
综合多学术数据库的论文调研技能，支持论文检索、引用分析、研究趋势追踪和文献综述生成。
概述
本技能整合多个学术数据源：
- arXiv 预印本论文
- Google Scholar 学术搜索
- Semantic Scholar 语义搜索
- 论文引用分析
- 研究趋势可视化
- 文献综述生成
使用场景
当用户提及以下内容时激活：
- "论文搜索"、"查找论文"
- "学术研究"、"文献调研"
- "arXiv 论文"
- "文献综述"、"综述"
- "研究趋势"、"领域动态"
- "论文推荐"、"相关工作"
- "引用分析"、"被引次数"
核心能力
1. 论文检索
- 关键词搜索
- 作者搜索
- 机构搜索
- 主题分类检索
- 日期范围筛选
- 相关论文推荐
2. 论文分析
- 论文摘要提取
- 核心贡献总结
- 方法论分析
- 实验结果解读
- 代码/数据集链接
3. 引用分析
- 论文引用关系图
- 高引用论文识别
- 研究影响力评估
- h-index 计算
- 领域重要论文
4. 研究趋势
- 年度发表趋势
- 关键词热度变化
- 新兴主题识别
- 技术演进路线
- 领域里程碑论文
5. 文献综述
- 相关工作整理
- 方法对比分析
- 技术路线总结
- 研究空白识别
- 未来方向建议
调研方法论
Phase 1: 需求确认
明确调研目标：
- 研究主题/关键词
- 需要什么类型的论文（理论/应用/综述）
- 时间范围要求
- 需要多少篇核心论文
Phase 2: 论文检索
数据源优先级：
- arXiv - 最新预印本，速度快
- Google Scholar - 最全，覆盖面广
- Semantic Scholar - 引用分析强
- PubMed - 生物医学领域
- IEEE Xplore - 工程领域
- ACM Digital Library - 计算机领域
检索策略：
# 基础检索
关键词1 AND 关键词2
# 扩展检索
关键词1 OR 关键词2
关键词1 NOT 关键词3
# 进阶检索
site:arxiv.org 关键词
"精确短语"
作者:姓名
Phase 3: 论文筛选
筛选标准：
- 相关性 - 与主题的直接关联度
- 质量 - 期刊/会议级别
- 引用数 - 影响力指标
- 时效性 - 最近3-5年为主
- 可获取性 - 是否有 PDF/代码
Phase 4: 分析整理
对筛选后的论文进行深度分析：
- 论文核心贡献
- 方法论特点
- 实验设置与结果
- 优点与局限性
- 与其他工作的关系
Phase 5: 报告生成
生成结构化报告：
- 执行摘要
- 领域概述
- 核心论文分析
- 技术路线演进
- 研究趋势
- 未来方向建议
- 参考文献
使用工具
检索阶段
web_search- 通用学术搜索web_fetch- 获取论文详情页arxiv_api- 直接查询 arXiv（如果有）
分析阶段
- 手动阅读摘要和结论
- 提取关键信息
- 对比分析方法
报告阶段
write- 生成 Markdown 报告chart-visualization- 生成趋势图表（如需要）
报告输出格式
文件命名
主题_论文调研_YYYYMMDD.md
主题_论文调研_YYYYMMDD.html
报告结构
# [主题] 论文调研报告
## 执行摘要
[1-2段概括调研目的、主要发现、核心论文]
## 一、领域概述
### 1.1 研究背景
### 1.2 研究意义
## 二、核心论文分析
### 2.1 基础理论
[奠基性论文]
### 2.2 重要进展
[里程碑论文]
### 2.3 最新成果
[近2年论文]
## 三、技术路线
### 3.1 方法论演进
### 3.2 主流方案对比
### 3.3 新兴方向
## 四、研究趋势
### 4.1 年度发表量
### 4.2 关键词热度
### 4.3 机构分布
## 五、文献目录
### 5.1 高影响力论文（按引用排序）
### 5.2 相关论文列表
## 六、未来研究方向
[基于调研的洞见和建议]
## 参考文献
[所有引用论文]
质量标准
- 来源可查 - 每篇论文标注来源链接
- 信息准确 - 摘要/结论需来自原论文
- 分类清晰 - 按主题/时间/方法分类
- 对比分析 - 横向对比不同论文
- 趋势洞察 - 基于数据的趋势判断
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.
- 9d ago First seen · 226 lines · 101 tokens per session scan A 8cb7d53a3492
paper-research is a skill published in the GitHub repository stophobia/deerflow2.0-enhanced (739 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 1,591 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…