dailypaper-skills is a collection of agent skills that automates a research-paper reading workflow. It finds recent papers from sources such as Hugging Face and arXiv, ranks them by the user’s interests, and creates structured notes in Obsidian, with optional Zotero support. The catalogue skills are the project’s own workflow components for coding agents.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/huangkiki/dailypaper-skillsnpx agentmods add skills/huangkiki/dailypaper-skills/paper-readerWrote 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/huangkiki/dailypaper-skills/paper-reader)<a href="https://agentmods.dev/skills/huangkiki/dailypaper-skills/paper-reader"><img src="https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/paper-reader/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/huangkiki/dailypaper-skills/paper-reader"><img src="https://agentmods.dev/badge/skills/huangkiki/dailypaper-skills/paper-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00157 | $0.02625 |
| Opus 5 | $0.00078 | $0.01313 |
| Sonnet 5 | $0.00031 | $0.00525 |
| Haiku 4.5 | $0.00016 | $0.00263 |
Grade A, and why
paper-reader 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.
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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
开始前: 先跟用户打个招呼 🐕
学术论文阅读助手 (Paper Reader)
专注 CV/DL 领域,支持 Zotero 集成和 Obsidian 笔记保存。
Step 0: 读取共享配置
先读取 ../_shared/user-config.json,如果 ../_shared/user-config.local.json 存在,再用它覆盖默认值。
显式生成并在后续统一使用这些变量:
VAULT_PATHNOTES_PATHCONCEPTS_PATHZOTERO_DBZOTERO_STORAGEAUTO_REFRESH_INDEXESGIT_COMMIT_ENABLEDGIT_PUSH_ENABLED
其中:
NOTES_PATH = {VAULT_PATH}/{paper_notes_folder}CONCEPTS_PATH = {NOTES_PATH}/{concepts_folder}GIT_PUSH_ENABLED只有在GIT_COMMIT_ENABLED=true时才可能为真
后续统一使用上面的变量。
1. 接收论文
| 输入方式 | 示例 | 处理方法 |
|---|---|---|
| PDF 路径 | /path/to/paper.pdf |
直接 Read |
| arXiv 链接 | https://arxiv.org/abs/xxxx |
WebFetch |
| Zotero 分类 | "VLA 分类的论文" | 查询数据库 → 列出 → 用户选择 |
| Zotero 搜索 | "Zotero 里的 π0.5" | 搜索标题 → 找到 PDF |
| 无 PDF | Zotero 条目无附件 | 从网上获取(见下方) |
无 PDF 时的获取流程
python3 assets/zotero_helper.py info {item_id}获取论文信息- 按优先级获取:arXiv HTML > arXiv PDF > DOI > WebSearch 标题
- 判断 arXiv ID:从 URL / Zotero extra 字段 / 标题搜索
- 推荐直接 WebFetch
https://arxiv.org/html/{arxiv_id},无需下载 - 跳过条件:既无 PDF 也无在线来源 / 非论文内容
Zotero 详细操作见
references/zotero-guide.md
2. 阅读模式
| 模式 | 触发词 | 输出 |
|---|---|---|
| 快速摘要 | "快速看一下"、"quick" | 3-5 句核心贡献 |
| 完整解析 | "详细分析"、默认 | 结构化笔记(用模板) |
| 批判分析 | "批判性分析"、"critique" | 方法论优缺点评估 |
| 知识提取 | "提取公式"、"技术细节" | 公式 + 算法伪代码 |
3. 笔记生成
模板: 严格遵循 assets/paper-note-template.md,不可自行简化。
核心质量规则
- 零遗漏: 论文中所有 Figure、所有公式、所有 Table 必须全部出现在笔记中
- 内联概念链接: 正文中首次出现的技术术语必须用
[[概念]]链接,不仅仅是结尾 - 严禁 ASCII 流程图: 用结构化 Markdown 列表 +
$数学符号$描述架构 - 公式完整性: 每个公式必须有名称(
[[概念|名称]])、LaTeX 公式、含义、符号说明 - 图片外链优先: arXiv HTML / 项目主页 / GitHub,找不到再本地下载
公式/图片/表格的详细质量规范见
references/quality-standards.md
图片获取流程(多源 fallback)
目标: 确保笔记中包含论文的所有 Figure,先统计论文 Figure 总数再逐一获取。
- WebSearch
"{论文标题} arxiv"获取 arXiv ID - 来源 A — arXiv HTML(首选):
- WebFetch
https://arxiv.org/html/{arxiv_id}提取所有<figure>的标题与 img src URL - 统计论文 Figure 总数,确认提取数量是否完整
- WebFetch
- 来源 B — 项目主页(HTML 404 或图片不全时):
- 从摘要/HTML 中查找项目主页 URL(常见模式:
project page、github.io、our website) - WebFetch 项目主页,提取展示图片(通常包含 teaser / demo 图)
- 从摘要/HTML 中查找项目主页 URL(常见模式:
- 来源 C — PDF 提取(前两者都失败时):
pdfimages -png从 PDF 中提取,筛选 >10KB 的有效图片
- 笔记中用
外链嵌入 - 验证:外链可加载 / 本地文件 >10KB
- URL 去重(必做):写入前检查每个 URL,如果
https://arxiv.org/html/后出现了连续两段相同的 arxiv_id(如2607.04988v1/2607.04988v1/),删除重复段。这是高频 bug,详见references/image-troubleshooting.md- 原因:arXiv HTML 中 img src 已含
{id}v1/前缀,拼接时不要再加一次 - 正确:
https://arxiv.org/html/+ src(如https://arxiv.org/html/2607.04988v1/x1.png) - 错误:
https://arxiv.org/html/2607.04988v1/+ src(导致路径重复,返回 404)
- 原因:arXiv HTML 中 img src 已含
What ships with it
9 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.
- assets/paper-note-template.md 4.9 KB
- assets/reorganize_notes.py 15 KB runs code
- assets/zotero_helper.py 15 KB runs code
- paper_daemon.py 26 KB runs code
- references/concept-categories.md 2.0 KB
- references/cv-dl-terminology.md 18 KB
- references/image-troubleshooting.md 3.5 KB
- references/quality-standards.md 2.7 KB
- references/zotero-guide.md 3.0 KB
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.
- 11d ago First seen · 211 lines · 157 tokens per session scan A 59015f1461e3
paper-reader is a skill published in the GitHub repository huangkiki/dailypaper-skills (1,217 stars, last pushed 19d ago), licensed Apache-2.0. It adds 157 tokens to every session and 2,625 once invoked, about $0.0008 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.