export
Skill585 starsChanged 3 months agoMITView on GitHub
Use when the user needs BibTeX, RIS, Markdown reference lists, filtered citation exports, custom citation styles, or a Markdown-to-DOCX export for sharing.
- Installs packages
24 other projects use a version of this.
Adopted by
Most recently taken up by
- fjwood69/moritheir own version, first seen Nov 8, 2026
- soilmass/motion-design-agenttheir own version, first seen Nov 8, 2026
- hiddenjobs/job-search-mcptheir own version, first seen Nov 1, 2026
- FiredMosquito831/my-writing-companiontheir own version, first seen Nov 1, 2026
- otisbase/otis-agent-plugintheir own version, first seen Nov 1, 2026
- Anglesite/anglesite-skillstheir own version, first seen Oct 27, 2026
Used with
Projects with it also use menu, preview and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
sasly2048Skillmenu
Point the user to cc-atlas's full interactive menu (dashboard, project comparison, session replay, team activity, anomalies, goals) — screens that need a real terminal.
Also in 3 projects that use this
kv0906Skillpreview
Render vault notes as styled HTML and open in browser. Turn markdown docs, decisions, progress reports into readable previews. Use for "/preview docs/project-a/checkout-flow.md", "/preview progress all", "/preview decide auth-approach", or when user wants to see a doc before sharing.
Also in 3 projects that use this
GoogleSkilldashboard
Configures and launches the GKE Capacity & Triage Dashboard scoped to a GCP project ID, GKE cluster name, or target ML workload ID. Uses the configure-and-launch-dashboard action and launch-workload-dashboard workflow to verify local dashboard health, discover cluster capacity, trigger live scans, and generate deep-linked URLs. Use when the user types "/dashboard", says "launch dashboard", "open dashboard", "show capacity", or "view triage dashboard" with a project, cluster, or workload. Don't use for general workload log querying or automated failure attribution (use the troubleshoot skill).
Also in 4 projects that use this
MicrosoftSkillreport
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.
Also in 4 projects that use this
GitHubSkillprd
Generate high-quality Product Requirements Documents (PRDs) for software systems and AI-powered features. Includes executive summaries, user stories, technical specifications, and risk analysis.
Also in 3 projects that use this
SentrySkillreview
Fixture review skill.
Also in 4 projects that use this
Other versions24 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 24
- pytorch/executorch★ 5.2ksame name
- Zafer-Liu/Data-Analysis-Agent★ 2.6ksame name
- with-pebbly/aseprite-ai-artist★ 473same name
- ai-analyst-lab/ai-analyst★ 304same name
- yha9806/academic-writing-toolkit★ 54same name
- spmtitsolution/OpenBA-Kit★ 38same name
- fjwood69/mori★ 32same name
- hiddenjobs/job-search-mcp★ 25same name
- spotify/ads-agentic-tools★ 20same name
- Anglesite/anglesite-skills★ 15same name
14 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/scholaraio.mdcCursor rule
- academic-writingSkill
- arxivSkill
- auditSkill
- backupSkill
- bioinformaticsSkill
- citation-checkSkill
- citationsSkill
- documentSkill
- drawSkill
- enrichSkill
- exploreSkill
- graphSkill
- gromacsSkill
- importSkill
- indexSkill
- ingestSkill
- insightsSkill
- lammpsSkill
- literature-reviewSkill
- metricsSkill
- nature-workflowSkill
- openfoamSkill
- paper-guided-readingSkill
- paper-writingSkill
- patent-fetchSkill
- patent-searchSkill
- posterSkill
- publishSkill
- quantum-espressoSkill
- renameSkill
- research-gapSkill
- review-responseSkill
- scientific-runtimeSkill
- scientific-tool-onboardingSkill
- scrubSkill
- searchSkill
- setupSkill
- showSkill
- technical-reportSkill
- topicsSkill
- translateSkill
- workspaceSkill
- writing-polishSkill
The file
Files
导出论文与文档
将本地论文库导出为标准引用格式,或将任意 Markdown 内容转换为 Word 文件。
支持的导出格式
| 格式 | 命令 | 用途 |
BibTeX .bib | export bibtex | LaTeX 写作引用 |
RIS .ris | export ris | Zotero / Endnote / Mendeley 导入 |
| Markdown 文献列表 | export markdown | 直接粘贴到文档、综述草稿 |
| Word DOCX | export docx | 分享给同事、导师,任意 Markdown 内容 |
BibTeX 导出
# 导出全部论文到屏幕
scholaraio export bibtex --all
# 导出全部论文到文件
scholaraio export bibtex --all -o workspace/library.bib
# 导出指定论文
scholaraio export bibtex "Smith-2023-Turbulence" "Doe-2024-DNS"
# 按年份筛选导出
scholaraio export bibtex --all --year 2020-2024 -o workspace/recent.bib
# 按期刊筛选导出
scholaraio export bibtex --all --journal "Fluid Mechanics" -o workspace/jfm.bibRIS 导出(Zotero / Endnote / Mendeley)
# 导出全部论文
scholaraio export ris --all -o workspace/library.ris
# 导出指定论文
scholaraio export ris "Smith-2023-Turbulence" "Doe-2024-DNS" -o workspace/refs.ris
# 按年份筛选
scholaraio export ris --all --year 2022-2024 -o workspace/recent.ris导出后可直接在 Zotero 中:File → Import → 选择 .ris 文件
Markdown 文献列表导出
内置格式(--style)
| 格式名 | 说明 | 典型场景 |
apa(默认) | APA 7th 作者-年份 | 社科、心理、教育 |
vancouver | Vancouver/ICMJE 编号 | 医学、生命科学 |
chicago-author-date | Chicago 17 作者-年份 | 人文、社科 |
mla | MLA 9th | 文学、语言学 |
<自定义> | 期刊专属格式 | 见下方「自定义格式」 |
# 导出全部论文(APA 风格,默认)
scholaraio export markdown --all
# 指定引用格式
scholaraio export markdown --all --style vancouver
scholaraio export markdown --all --style chicago-author-date
scholaraio export markdown --all --style jcp # 自定义格式
# 导出到文件
scholaraio export markdown --all --style apa -o workspace/references.md
# 无序列表
scholaraio export markdown --all --bullet
# 按年份筛选
scholaraio export markdown --all --year 2020-2024 -o workspace/recent_refs.md查看可用格式
scholaraio style list # 列出全部格式(内置 + 自定义)
scholaraio style show jcp # 查看某个自定义格式的代码自定义期刊引用格式(Agent 精确控制)
原理
自定义格式以 Python 文件存储在配置的 citation styles 目录中。fresh 默认是
data/libraries/citation_styles/<name>.py。如果用户仍有旧版
data/citation_styles/ 内容,先通过 scholaraio migrate upgrade --migration-id <id> --confirm
迁移后再导出。格式文件必须实现一个函数:
def format_ref(meta: dict, idx: int | None = None) -> str:
"""
meta 字段:title, authors (list), year, journal, volume, issue,
pages, doi, publisher, paper_type, ...
idx: 有序列表的编号(None = 无序/bullet)
返回:格式化后的 Markdown 引用字符串
"""Agent 工作流:为指定期刊生成格式
当用户说「导出成 JCP 格式」「帮我按 Physical Review Letters 格式导出」:
- 检查是否已有缓存
如果已有scholaraio style listjcp或目标格式名,直接跳到第 4 步。 - 获取期刊官方格式说明
- 搜索:
<journal name> citation style guide或<journal name> reference format - 或从 CSL 仓库获取标准定义:
https://raw.githubusercontent.com/citation-style-language/styles/master/<slug>.csl - CSL 搜索:
https://github.com/citation-style-language/styles/(支持 10,000+ 期刊)
- 搜索:
- 写 Python 格式化函数并保存
- 根据格式说明写
format_ref(meta, idx)函数 - 保存到当前
cfg.citation_styles_dir / "<name>.py"(fresh 默认data/libraries/citation_styles/<name>.py) - 可同时保存同目录的
<name>.json(记录来源和示例)
- 根据格式说明写
- 导出
scholaraio export markdown --all --style <name> -o workspace/refs.md
示例:JCP 格式文件(fresh 默认 data/libraries/citation_styles/jcp.py)
# Journal of Chemical Physics / AIP Publishing 编号格式
# 来源:https://publishing.aip.org/wp-content/uploads/2021/05/JCP_Style_Guide.pdf
def format_ref(meta: dict, idx: int | None = None) -> str:
authors = meta.get("authors") or []
def _fmt(name):
parts = name.split(",", 1)
if len(parts) == 2:
last, first = parts[0].strip(), parts[1].strip()
initials = " ".join(f"{w[0]}." for w in first.split() if w)
return f"{initials} {last}"
return name
if len(authors) == 1:
author_str = _fmt(authors[0])
elif len(authors) <= 3:
fmt = [_fmt(a) for a in authors]
author_str = ", ".join(fmt[:-1]) + f", and {fmt[-1]}"
elif authors:
author_str = _fmt(authors[0]) + " et al."
else:
author_str = "Unknown"
title = meta.get("title") or "Untitled"
journal = meta.get("journal") or ""
volume = meta.get("volume") or ""
pages = meta.get("pages") or ""
year = meta.get("year") or "n.d."
doi = meta.get("doi") or ""
start_page = pages.split("-")[0].strip() if pages else ""
ref = f'{author_str}, "{title},"'
if journal: ref += f" *{journal}*"
if volume: ref += f" **{volume}**,"
if start_page: ref += f" {start_page}"
ref += f" ({year})."
if doi: ref += f" doi:{doi}"
prefix = f"{idx}. " if idx is not None else "- "
return prefix + ref输出示例:
1. A. Vaswani et al., "Attention Is All You Need," *Advances in Neural Information Processing Systems* **30**, 5998 (2017). doi:10.48550/arXiv.1706.03762DOCX 导出(任意 Markdown → Word)
# 将 Markdown 文件导出为 Word
scholaraio export docx --input workspace/literature_review.md --output workspace/review.docx
# 添加文档标题
scholaraio export docx --input workspace/report.md --output workspace/report.docx --title "研究报告"
# 从 stdin 读取(配合 Claude 生成内容直接导出)
echo "# 标题\n内容..." | scholaraio export docx --output workspace/doc.docx支持的 Markdown 元素:标题(H1-H9)、段落、粗体、斜体、列表、表格、代码块、引用块
依赖:需安装 pip install python-docx
高级排版:
export docx仅做简单 Markdown → Word 转换。需要自定义样式、嵌入图片、表格等高级排版时,请使用/documentskill(直接调用 python-docx API)。
示例
用户说:"把我所有论文导出成 BibTeX"
→ 执行 export bibtex --all
用户说:"导出成 RIS,我要导入 Zotero"
→ 执行 export ris --all -o workspace/library.ris
用户说:"给我一份 Markdown 格式的参考文献列表"
→ 执行 export markdown --all
用户说:"按 Vancouver 格式导出文献列表"
→ 执行 export markdown --all --style vancouver
用户说:"按 JCP 格式导出,我要投 Journal of Chemical Physics"
→ 先 style list 检查,若无则获取 JCP 格式说明、写入当前 citation styles 目录(fresh 默认 data/libraries/citation_styles/jcp.py),再 export markdown --all --style jcp
用户说:"把这篇文献综述导出成 Word 文件"
→ 执行 export docx --input workspace/review.md --output workspace/review.docx
用户说:"导出 DNS 相关的论文引用"
→ 先用 usearch "DNS" 搜索,从结果中提取目录名,再 export markdown <dir1> <dir2> ...
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

