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 wpsnote/wpsnote-skills --skill paper-researchergit clone --depth 1 https://github.com/wpsnote/wpsnote-skillsWrote 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/wpsnote/wpsnote-skills/paper-researcher)<a href="https://agentmods.dev/skills/wpsnote/wpsnote-skills/paper-researcher"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/paper-researcher/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/wpsnote/wpsnote-skills/paper-researcher"><img src="https://agentmods.dev/badge/skills/wpsnote/wpsnote-skills/paper-researcher.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 | $0.00137 | $0.01808 |
| Opus 5.5 | $0.00055 | $0.00723 |
| Sonnet 5.5 | $0.00027 | $0.00362 |
| Haiku 4.5 | $0.00014 | $0.00181 |
Grade A, and why
paper-researcher 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 1mo 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Researcher — 论文全流程助手
前置检查
启动本 Skill 的第一步，检查 wpsnote-cli 是否可用：
wpsnote-cli status --json
- 可用 → 后续 WPS 笔记操作全部使用
wpsnote-cli命令 - 不可用 → 降级使用 MCP 工具（
user-wpsnote服务）操作 WPS 笔记
CLI 工具约定（wpsnote-cli 可用时）
wpsnote-cli <子命令> [参数]
# 复杂参数一律通过 --json-args 传入
wpsnote-cli <子命令> --json-args '{"key": "value"}'
| 操作 | CLI 命令 |
|---|---|
| 搜索笔记 | wpsnote-cli search-notes --query "关键词" --json |
| 列出笔记 | wpsnote-cli list --json |
| 读取笔记全文 | wpsnote-cli read --note_id <id> --json |
| 新建笔记 | wpsnote-cli create --json-args '{"title":"标题","content":"<h1>...</h1>"}' |
| 插入 block | wpsnote-cli edit --json-args '{"note_id":"...","op":"insert","anchor_id":"...","content":"<p>...</p>"}' |
| 获取标签列表 | wpsnote-cli tags --json |
核心脚本
搜索与下载操作通过 scripts/paper.py 完成，路径：<skill目录>/scripts/paper.py。
# 首次使用安装依赖
pip install arxiv markitdown pymupdf
# 搜索（默认 arXiv，推荐英文关键词）
python3 /path/to/scripts/paper.py search "transformer attention" --top 5
python3 /path/to/scripts/paper.py search "LoRA fine-tuning" --source openalex --top 5
python3 /path/to/scripts/paper.py search "diffusion model" --category cs.CV
# 下载 PDF 并转 Markdown
python3 /path/to/scripts/paper.py get 1706.03762 --markdown
python3 /path/to/scripts/paper.py get 1706.03762 --output ~/papers --markdown
脚本实际路径：读取本 SKILL.md 的目录下的 scripts/paper.py，执行前先用 ls 确认路径存在。
PDF → Markdown 转换说明
加 --markdown 参数后，脚本按以下顺序尝试转换，成功即停止：
- markitdown（首选）：调用
MarkItDown().convert(pdf_path)，转换质量最高，保留结构 - pymupdf（备选）：逐页提取文字，拼接为
## Page N格式的 Markdown - 两种方法均失败 → 打印警告，返回空字符串（通常是扫描版 PDF）
转换结果保存为同名 .md 文件，路径与 PDF 相同，如 ~/papers/1706.03762.md。
转换完成后，用 Shell cat 命令读取 .md 文件内容，再进行分析。
工作流程
场景 A：搜索 + 精读（最常见）
1. 运行 paper.py search → 展示结果，请用户选择
2. 用户确认后，运行 paper.py get <ID> --markdown
3. Shell 读取生成的 .md 文件：cat ~/papers/<ID>.md
4. 按分析框架输出结构化摘要
5. 存入 WPS 笔记（CLI 优先，见存档流程）
场景 B：用户直接提供 PDF 路径
1. 用 Read 工具读取 PDF（Cursor 内置支持）
2. 若内容为空 → 运行 paper.py get <id> --markdown 转换后再读
3. 分析并存档
What ships with it
1 file 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.
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.
- 1mo ago First seen · 178 lines · 137 tokens per session scan A dc40b3b5b5f7
paper-researcher is a skill published in the GitHub repository wpsnote/wpsnote-skills (183 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 1,808 once invoked, about $0.0005 per session on Opus 5.5. 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
pdf-image-text-extractor
A tool for reading text from images and PDF files, including scanned documents. OCR means recognizing printed or handwritten characters in an image and turning them into editable text.
dsh-paddleocr-skills-setup
Install and configure the native PaddleOCR plugin for DeepSeek Harness (DSH) from the Settings → PaddleOCR GUI. Use for OCR and image-to-text from screenshots, scans, and PDFs; Chinese/CJK text; PDF-to-Markdown; structured document parsing with tables, formulas, layout, and reading order; or DSH endpoint, credential…
dsh-office-artifacts
Create, repair, transform, or verify XLSX, DOCX, PPTX, and PDF deliverables with format-aware tools and reopen or render checks.
paddleocr-doc-parsing
Use the native DeepSeek Harness PaddleOCR tool to parse document layout and Markdown.
paddleocr-text-recognition
Use the native DeepSeek Harness PaddleOCR tool to extract text from an image or PDF.
nutrient-document-processing
Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images. Use when converting, OCRing, extracting from, redacting, signing, or filling documents via the Nutrient DWS API.