Agent skill

Papercash

by Jesseovo in Jesseovo/PaperCash

论文全流程辅助: 8源检索、综述生成、查重预检、降AI率、参考文献格式化、Word导出. An agent skill from Jesseovo/PaperCash.

MITAuto-check passedResearch & Science

Install Papercash

skills CLI
$ npx skills add Jesseovo/PaperCash --skill papercash -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Jesseovo/PaperCash papercash --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
papercash
GitHub stars
152
Token cost
~714 tokens
SKILL.md length
218 words
Files
50 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

论文全流程辅助: 8源检索、综述生成、查重预检、降AI率、参考文献格式化、Word导出. An agent skill from Jesseovo/PaperCash.

  • Works in 7 steps: 论文检索 (search) → 文献综述 (review) → 写作辅助 (outline / expand / polish) → …
  • Tasks that involve Academic paper search
  • SKILL.md covers 触发方式, 核心能力, 配置诊断 and 数据源说明, plus 1 more section
  • Runs Python scripts from its folder; calls python

What it does

Papercash is an agent skill from Jesseovo/PaperCash. 论文全流程辅助: 8源检索、综述生成、查重预检、降AI率、参考文献格式化、Word导出

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. The skill folder holds 56 other files, including scripts (for example `.claude-plugin/plugin.json`, `AGENTS.md` and `README.md`).

It sits in Research & Science, covering Academic paper search. It works with Python. The repository describes itself as: 📄 论文全流程辅助 AI Skill — 检索 2 亿+论文、文献综述生成、写作润色、查重预检、降 AI 率改写、参考文献管理,4 源免费即用. The licence is MIT.

When your agent uses it

  • Tasks that involve Academic paper search

Example prompts

  • “/papercash”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. 论文检索 (search)
  2. 文献综述 (review)
  3. 写作辅助 (outline / expand / polish)
  4. 查重预检 (check)
  5. 降AI率改写 (humanize)
  6. 参考文献格式化 (cite)
  7. 格式检查 (format)

What it can do on your machine

Read from SKILL.md and the folder at commit da3590e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Papercash loads about 714 tokens when it runs. Until then it costs about 13 tokens; SKILL.md has 218 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~13
When it runs · the whole SKILL.md, loaded when a task matches
~714

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Jesseovo/PaperCash at commit da3590e, republished under its MIT licence (© Jesseovo). 218 words, ~714 tokens.

Download SKILL.mdSave it as .claude/skills/papercash/SKILL.md (or your agent's skills folder). This skill also uses 49 other files; get the full folder from GitHub.
name
papercash
description
论文全流程辅助: 8源检索、综述生成、查重预检、降AI率、参考文献格式化、Word导出

PaperCash — 论文全流程辅助 Skill

论文检索、文献综述、写作辅助、查重预检、降AI率、参考文献管理 —— 一个 Skill 全搞定。

触发方式

当用户提到以下关键词时激活本技能:

  • "论文"、"paper"、"文献"、"查重"、"降重"、"降AI"、"参考文献"、"引用"、"综述"、"摘要"
  • "/papercash"、"papercash"

核心能力

搜索 Semantic Scholar、arXiv、CrossRef、百度学术等 8 大学术数据源,返回评分排序的论文列表。

调用方式:

/papercash search <研究主题>

示例:

/papercash search 深度学习在医学图像中的应用

Agent 执行步骤:

  1. 运行 python scripts/papercash.py search "<主题>" --emit compact
  2. 将输出结果呈现给用户,包含论文标题、作者、年份、引用数、摘要摘录
  3. 可选 --export-docx 导出 Word 文档
  4. 提供后续建议:生成综述、格式化引用、深入某篇论文
2. 文献综述 (review)

基于检索结果,自动生成结构化文献综述。

调用方式:

/papercash review <研究主题> [--format gb7714|apa]

Agent 执行步骤:

  1. 运行 python scripts/papercash.py review "<主题>" --format gb7714
  2. 脚本自动完成检索 + 综述生成,输出结构化综述:
    • 研究背景与现状
    • 国内外研究对比
    • 研究方法分类
    • 研究空白与不足
    • 每段附带真实引用 [作者, 年份]
  3. 可选 --export-docx 直接导出 Word 文档
3. 写作辅助 (outline / expand / polish)

生成论文大纲、段落扩写、学术润色。

调用方式:

/papercash outline <论文题目>
/papercash expand <关键点描述>
/papercash polish <待润色文本>

Agent 执行步骤:

  • outline: Agent 基于题目和检索到的相关文献,生成符合学术规范的多级大纲
  • expand: Agent 将关键点扩展为学术段落,附带文献支撑
  • polish: Agent 将口语化表达改为学术用语,保持原意不变
4. 查重预检 (check)

将论文拆成句子,逐句检索学术库,标记高相似度句子。

调用方式:

/papercash check <文件路径或粘贴内容>

Agent 执行步骤:

  1. 运行 python scripts/papercash.py check "<文件路径>" --emit json
  2. 呈现结果:标记高风险句子(相似度 > 70%)、中风险句子(50-70%)
  3. 对高风险句提供改写建议
  4. 重要提示:告知用户"这是预检工具,不替代知网/维普等正式查重"
5. 降AI率改写 (humanize)

通过句式变换、个人观点注入、学术语气调整,降低AI生成内容的检测率。

调用方式:

/papercash humanize <文件路径或粘贴内容>

Agent 执行步骤:

  1. 运行 python scripts/papercash.py humanize "<文件路径>"
  2. 返回改写后的文本,并标注修改点
  3. 改写策略:
    • 被动改主动、长句拆短句
    • 注入"笔者认为"、"从实践角度看"等个人视角
    • 替换AI高频套话("综上所述"→具体总结)
    • 增加领域特有细节
6. 参考文献格式化 (cite)

从 DOI/URL 提取文献信息,输出 GB/T 7714、APA、BibTeX 等格式。

调用方式:

/papercash cite <DOI或URL> [--style gb7714|apa|bibtex]

Agent 执行步骤:

  1. 运行 python scripts/papercash.py cite "<DOI>" --style gb7714
  2. 返回格式化的引用条目
  3. 支持批量输入(多个 DOI 用空格分隔)
7. 格式检查 (format)

检查论文是否符合常见高校格式要求。

调用方式:

/papercash format <Word文件路径>

Agent 执行步骤:

  1. 运行 python scripts/papercash.py format "<文件路径>"
  2. 返回格式检查报告:字体、字号、行距、页边距、参考文献格式等

配置诊断

/papercash setup    # 交互式配置向导
/papercash diagnose # 检查数据源可用状态

数据源说明

数据源覆盖范围需要配置
Semantic Scholar2亿+论文,全领域无需(免费API)
arXivSTEM预印本无需(免费)
CrossRef1.4亿DOI元数据无需(免费)
百度学术中文论文元数据无需(公开搜索)
Google Scholar全领域可选(需代理)
PubMed生物医学可选(免费)
知网 CNKI中文核心期刊需Cookie
万方中文学术需Cookie

重要约束

  1. 学术诚信:本工具辅助写作,不鼓励学术不端。生成内容需用户审核修改。
  2. 查重声明:查重预检仅供参考,正式查重请使用学校指定系统。
  3. 引用真实性:所有引用来自真实学术数据库检索结果,但 Agent 应提醒用户核实。
  4. 降AI率说明:改写结果仅供参考,最终文本需体现学生本人的思考和理解。

© Jesseovo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 49 other files (scripts) in the repository root of Jesseovo/PaperCash.

  • SKILL.md
  • .augment/skills
  • .claude-plugin/plugin.json
  • .gitignore
  • .windsurf/skills
  • AGENTS.md
  • LICENSE
  • README.md
  • agents/openai.yaml
  • clawhub.json
  • docs/user_feedback_report.md
  • fixtures/sample_search.json
  • gemini-extension.json
  • hooks/session_start.py
  • … and 36 more

Open the folder on GitHubat commit da3590e

Compare with similar skills

Papercash next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Papercash compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Papercash this skillJesseovo/PaperCash152—~714Automated safety check: PassMIT
Citation ManagementK-Dense-AI/claude-scientific-writer2.4k2 repos~3.9kAutomated safety check: NotesMIT
Preprint Search on bioRxivLigphiDonk/Oh-my--paper73912 repos~3.7kAutomated safety check: PassMIT
Paper2codePrathamLearnsToCode/paper2code1.5k—~1.3kAutomated safety check: PassMIT
Paper Research on arXivXiaomiMiMo/MiMo-Code14k—~1.5kAutomated safety check: PassMIT
Conference Paper Recommenderjuliye2025/evil-read-arxiv1.7k—~2.5kAutomated safety check: PassNone

Similar skills

  • Citation Management

    K-Dense-AI/claude-scientific-writer

    Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.

    2.4k GitHub starsUsed in 2 repos~3.9k tokens
    Research & ScienceAuto-check: notes
  • Preprint Search on bioRxiv

    LigphiDonk/Oh-my--paper

    Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.

    739 GitHub starsUsed in 12 repos~3.7k tokens
    Research & ScienceAuto-check passed
  • Paper2code

    PrathamLearnsToCode/paper2code

    Converts an arxiv paper into a minimal, citation-anchored Python implementation.

    1.5k GitHub stars~1.3k tokensUpdated 6 mo ago
    Research & ScienceAuto-check passed
  • Paper Research on arXiv

    XiaomiMiMo/MiMo-Code

    Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.

    14k GitHub stars~1.5k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed
  • Conference Paper Recommender

    juliye2025/evil-read-arxiv

    Searches DBLP for papers from top conferences such as CVPR, ICLR and NeurIPS, adds Semantic Scholar data, scores them and writes a yearly Obsidian note.

    1.7k GitHub stars~2.5k tokensUpdated 26 days ago
    Research & ScienceAuto-check passed
  • Autonomous Research

    federicodeponte/opendraft

    An 18-agent pipeline that turns one topic line into a drafted research paper, literature review, or thesis chapter.

    507 GitHub stars~8.2k tokensUpdated 9 days ago
    Research & ScienceAuto-check passed

Works with

Questions about Papercash

What does Papercash do?

论文全流程辅助: 8源检索、综述生成、查重预检、降AI率、参考文献格式化、Word导出. An agent skill from Jesseovo/PaperCash. Papercash is an agent skill from Jesseovo/PaperCash.

When should I use Papercash?

Papercash fits situations like: tasks that involve Academic paper search.

How do I install Papercash in Claude Code?

Run `npx skills add Jesseovo/PaperCash --skill papercash -a claude-code`. Or copy the skill folder (the Jesseovo/PaperCash repository) into .claude/skills/papercash in your project. Claude Code loads it when a task matches its description.

How do I install Papercash in Codex?

Run `npx skills add Jesseovo/PaperCash --skill papercash -a codex`. Or copy the skill folder (the Jesseovo/PaperCash repository) into .agents/skills/papercash in your project. Codex loads it when a task matches its description.

Can I use Papercash in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Jesseovo/PaperCash --skill papercash -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/papercash, .gemini/skills/papercash, .github/skills/papercash and .opencode/skills/papercash in your project.

What does Papercash need to run?

Going by SKILL.md and its folder, Papercash needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Papercash access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Papercash safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Papercash use?

Papercash is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Papercash use?

About 714 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Papercash?

Skills that share tags, products or a category with Papercash: Citation Management (K-Dense-AI/claude-scientific-writer, 2.4k stars), Preprint Search on bioRxiv (LigphiDonk/Oh-my--paper, 739 stars), Paper2code (PrathamLearnsToCode/paper2code, 1.5k stars) and Paper Research on arXiv (XiaomiMiMo/MiMo-Code, 14k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Papercash?

Jesseovo (a GitHub user) maintains it in Jesseovo/PaperCash, which has 152 GitHub stars. The repository was last updated on April 7, 2026.

Source: Jesseovo/PaperCash on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.