Citation Management
neflibata-feng/MyArxiv-Agent
Comprehensive citation management for academic research. An agent skill from neflibata-feng/MyArxiv-Agent.
中文文献检索、筛选、批量采集和合法全文获取助手。用于用户需要查找论文、下载可合法获取的 PDF/HTML/XML 全文、生成关键词和检索式、查询 DOI/PMID、筛选高影响因子或高分区期刊、检查开放获取、做引用链扩展、批量文献候选表、下载日志、去重清单、Zotero/BibTeX 整理,或解决文献难下载问题;禁止绕过付费墙、盗版下载、共享账号或规避版权限制。
$ npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Lucaswangzcx/literature-downloader-skill literature-downloader --agent claude-codeProject 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/
Install the "literature-downloader" agent skill from https://github.com/Lucaswangzcx/literature-downloader-skill/tree/main into .claude/skills/literature-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "literature-downloader", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Lucaswangzcx/literature-downloader-skill literature-downloader --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "literature-downloader" agent skill from https://github.com/Lucaswangzcx/literature-downloader-skill/tree/main into .agents/skills/literature-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "literature-downloader", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Lucaswangzcx/literature-downloader-skill literature-downloader --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "literature-downloader" agent skill from https://github.com/Lucaswangzcx/literature-downloader-skill/tree/main into .cursor/skills/literature-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "literature-downloader", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Lucaswangzcx/literature-downloader-skill literature-downloader --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "literature-downloader" agent skill from https://github.com/Lucaswangzcx/literature-downloader-skill/tree/main into .gemini/skills/literature-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "literature-downloader", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Lucaswangzcx/literature-downloader-skill literature-downloaderInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "literature-downloader" agent skill from https://github.com/Lucaswangzcx/literature-downloader-skill/tree/main into .github/skills/literature-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "literature-downloader", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Lucaswangzcx/literature-downloader-skill literature-downloader --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "literature-downloader" agent skill from https://github.com/Lucaswangzcx/literature-downloader-skill/tree/main into .opencode/skills/literature-downloader/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "literature-downloader", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
literature-downloader中文文献检索、筛选、批量采集和合法全文获取助手。用于用户需要查找论文、下载可合法获取的 PDF/HTML/XML 全文、生成关键词和检索式、查询 DOI/PMID、筛选高影响因子或高分区期刊、检查开放获取、做引用链扩展、批量文献候选表、下载日志、去重清单、Zotero/BibTeX 整理,或解决文献难下载问题;禁止绕过付费墙、盗版下载、共享账号或规避版权限制。
Literature Downloader is an agent skill from Lucaswangzcx/literature-downloader-skill. 中文文献检索、筛选、批量采集和合法全文获取助手。用于用户需要查找论文、下载可合法获取的 PDF/HTML/XML 全文、生成关键词和检索式、查询 DOI/PMID、筛选高影响因子或高分区期刊、检查开放获取、做引用链扩展、批量文献候选表、下载日志、去重清单、Zotero/BibTeX 整理,或解决文献难下载问题;禁止绕过付费墙、盗版下载、共享账号或规避版权限制。
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files, including scripts and reference files (for example `.github/ISSUE_TEMPLATE/bug_report.yml`, `.github/pull_request_template.md` and `CONTRIBUTING.md`).
It sits in Research & Science, covering Citation management, Academic paper search and PDF. It works with Zotero, LaTeX and PubMed. The repository describes itself as: A Chinese Codex skill for academic literature search, lawful full-text downloading, readable reports, and student-friendly paper lists. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 0e8f306. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Literature Downloader loads about 1.4k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 203 words of instructions outside code blocks.
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.
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.
The full file from Lucaswangzcx/literature-downloader-skill at commit 0e8f306, republished under its MIT licence (© Lucaswangzcx). 203 words, ~1,358 tokens.
.claude/skills/literature-downloader/SKILL.md (or your agent's skills folder). This skill also uses 26 other files; get the full folder from GitHub.用中文和用户协作,把“找文献、筛文献、判断期刊质量、获取合法全文、整理记录”做成一条可复现流程。
不要提供或推荐盗版、绕过付费墙、共享学校账号、破解 DRM、影子图书馆等做法。遇到无法直接下载的文献,改用合法路线:出版社页面、开放获取版本、PubMed Central、Europe PMC、Unpaywall、预印本、机构仓储、作者主页、学校图书馆、馆际互借、邮件联系作者。
影响因子、JCR 分区、Scopus/SJR、收录状态、撤稿/更正、全文可用性都会变化。只要用户要“最新”“高影响因子”“近五年”“能下载全文”,先核对来源,再给结论。
references/search-strategy.md。references/source-quality.md。references/full-text-access.md 的顺序找 PDF/HTML/XML 或记录下一步合法获取方式。references/organization.md。先用 scripts/litplan.py 生成中文可读的检索入口、Boolean 检索式和追踪表:
python scripts/litplan.py --topic "LLM 在环境领域中的应用" --keywords "large language model|LLM|ChatGPT,environmental science|climate|sustainability,application|decision support" --years 2021-2026
python scripts/litplan.py --doi "10.1038/s41545-025-00509-8"
python scripts/litplan.py --title "ChatGPT and Environmental Research"这个脚本不绕过付费墙,也不盗版下载。它只生成合法检索路线和可复现记录表。
Codex 可以原生识别本 skill,并使用 Use $literature-downloader ... 触发。Claude Code、Trae、CodeBuddy、Cursor 等工具不一定识别 Codex Skill 自动触发机制,但仍然可以把本仓库当作“agent 指令文件 + 脚本工具包”使用。
给其他 agent 的推荐提示词:
请阅读当前仓库的 README.md 和 SKILL.md,并严格按其中的 literature-downloader 工作流执行。
我的任务是:下载“[研究主题]”的近五年文献,优先高影响因子,最多 [数量] 篇,下载到 <下载目录>。
要求:
1. 只允许使用合法可访问的全文来源,不要绕过付费墙,不要使用盗版来源。
2. 先创建批量采集任务目录。
3. 生成候选文献表,并在每篇文献行中列出题名、年份、期刊或来源、影响因子/分区、指标年份、指标来源、DOI、文章地址、全文状态和下一步建议。
4. 尝试下载开放 PDF、HTML 或 XML;遇到登录页、403、订阅页、短 HTML 跳转页时,不要算成功,写入待处理清单。
5. 最后运行 scripts 生成中文下载报告、文章地址总表、已下载文献清单、待处理文献清单,并整理输出目录。结论:Codex 是原生 Skill 体验;其他工具是“读 README/SKILL.md + 调 scripts”的体验。
用户要“找 20 篇”“批量下载”“做一个文献包”“保存日志”时,使用批量采集模式。先读 references/batch-harvest.md。
python scripts/prepare_harvest_run.py --topic "LLM 在环境领域中的应用" --keywords "large language model|LLM|ChatGPT,environmental science|climate|sustainability" --years 2021-2026 --output-root literature_runs --run-name llm_environment_20260426candidate_table.csv。来源可以是 Crossref、OpenAlex、PubMed、Europe PMC、Zotero 导出、出版社页面或人工核对结果。python scripts/rank_candidates.py --run-root literature_runs/llm_environment_20260426python scripts/download_accessible_fulltexts.py --run-root literature_runs/llm_environment_20260426 --retry-failedpython scripts/generate_readable_report.py --run-root literature_runs/llm_environment_20260426 --title "LLM 在环境领域中的应用:文献下载报告" --pdfjournal_metrics.csv 或候选表里的 impact_factor、jcr_quartile、metric_year、metric_source、indexing。不要让脚本凭空猜指标。下载报告.pdf 或 下载报告.html,再给 CSV 日志路径。报告里要说明候选总数、成功 PDF、HTML/XML 全文、无法访问数量、失败原因、影响因子/分区来源和下一步合法获取路线。下载脚本不会绕过付费墙。它只保存能直接合法访问的 PDF/HTML/XML;如果遇到登录页、订阅页、403/401、付费墙,会记录为不可访问。
面向用户时,不要让用户先读 CSV。CSV 是技术日志,不是交付物。
优先交付:
下载报告.pdf:最适合普通用户查看和转发。下载报告.html:PDF 生成失败时的可读替代品,浏览器直接打开。README_先看我.md:短说明,告诉用户下载了什么、哪些没下成、下一步怎么办。downloaded_fulltexts/ 或用户指定目录:实际 PDF/HTML/XML 文件。文章地址总表.csv:只列题名、文章地址、是否下载成功、全文状态、DOI、下一步建议。候选文献总表.csv、高优先级文献.csv、已下载文献清单.csv、待处理文献清单.csv:所有列出文献的表都必须直接包含题名、年份、期刊或来源、影响因子/分区/指标来源、DOI、文章地址、全文状态和下一步建议。英文 CSV 只作为脚本兼容备份。除实际文献文件外,输出文件名默认用中文,让用户一眼知道用途:
README_先看我.md:最短说明。下载报告.pdf:主报告。下载报告.html:可在浏览器打开的报告。检索计划.md:关键词、检索式、数据库入口。配置文件.json:本次任务设置。文章地址总表.csv:题名、地址、是否下载成功。候选文献总表.csv:所有候选文献。高优先级文献.csv、中优先级文献.csv、低优先级文献.csv:筛选结果。期刊指标.csv:仅作为后台核验来源或临时模板,不作为主要交付物。下载日志.csv:下载尝试记录。总下载日志.csv:合并后的最终状态。去重清单.csv:重复文献处理依据。已下载全文/:PDF、HTML、XML 全文文件夹。内部数据_一般不用打开/:英文兼容文件、原始日志和中间数据。如果需要影响因子或分区,报告中显示“影响因子/分区”列。指标必须标注年份和来源;没有核验时显示“待核验”,不要编数字。
凡是列出文献的文件,都要把重要期刊指标并入每一行。不要让用户在文献清单和期刊指标表之间来回对照。
python scripts/make_student_outputs.py --run-root literature_runs/llm_environment_20260426
python scripts/organize_final_outputs.py --run-root literature_runs/llm_environment_20260426报告必须用中文解释状态:
success_pdf 写成“已下载 PDF”。success_html 写成“已保存网页全文”。success_xml 写成“已保存 XML 全文”。inaccessible 写成“平台限制直连下载,建议学校库/馆际互借/联系作者”。metadata_only 写成“只找到题录,尚未找到合法全文”。failed 写成“尝试失败,需人工复查入口”。把“为什么有些没下载成功”写清楚:这通常不是程序坏了,而是 ACS、Elsevier、SpringerLink 等平台对非订阅、非浏览器、非机构网络的下载限制。不要把失败包装成成功。
普通检索任务输出:
批量任务额外输出:
下载报告.pdf 路径;如果没有生成 PDF,则给 下载报告.html。README_先看我.md 路径。combined_download_log.csv 或 download_log.csv 路径。如果用户提供 DOI、PMID、题名或文献清单,先解析标识符和找全文,不要从泛泛关键词检索开始。
© Lucaswangzcx, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 26 other files (scripts, references) in the repository root of Lucaswangzcx/literature-downloader-skill.
Open the folder on GitHubat commit 0e8f306
Literature Downloader 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Literature Downloader this skillLucaswangzcx/literature-downloader-skill | 239 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Citation Managementneflibata-feng/MyArxiv-Agent | 126 | 19 repos | ~8.1k | Automated safety check: Notes | MIT | |
| Ref Downloaderltczding-gif/ref-downloader | 139 | — | ~5.9k | Automated safety check: Pass | MIT | |
| Nature Academic Searchjing1312/nature-figure-skill | 171 | — | ~1.3k | Automated safety check: Notes | MIT | |
| Gs Exportcookjohn/gs-skills | 527 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Literature ReviewNorman-bury/research-writing-skill | 3.4k | — | ~2.2k | Automated safety check: Notes | MIT |
neflibata-feng/MyArxiv-Agent
Comprehensive citation management for academic research. An agent skill from neflibata-feng/MyArxiv-Agent.
ltczding-gif/ref-downloader
A skill your agent uses when the user asks to batch-download academic PDFs with ref-downloader — either ALL references of one paper (Mode A: DOI or PDF input), OR a custom batch of papers (Mode B…
jing1312/nature-figure-skill
Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion)…
cookjohn/gs-skills
Export Google Scholar paper(s) to Zotero via BibTeX. An agent skill from cookjohn/gs-skills.
Norman-bury/research-writing-skill
A skill your agent uses when writing literature review sections - guides searching, organizing, and synthesizing academic sources
joshzyj/open-scholar-skill
Build and query a local vector database + GraphRAG over your entire reference library (Zotero or a PDF folder) for literature review.
Categories
中文文献检索、筛选、批量采集和合法全文获取助手。用于用户需要查找论文、下载可合法获取的 PDF/HTML/XML 全文、生成关键词和检索式、查询 DOI/PMID、筛选高影响因子或高分区期刊、检查开放获取、做引用链扩展、批量文献候选表、下载日志、去重清单、Zotero/BibTeX 整理,或解决文献难下载问题;禁止绕过付费墙、盗版下载、共享账号或规避版权限制。. Literature Downloader is an agent skill from Lucaswangzcx/literature-downloader-skill.
Literature Downloader fits situations like: tasks that involve Citation management; tasks that involve Academic paper search; tasks that involve PDF.
Run `npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a claude-code`. Or copy the skill folder (the Lucaswangzcx/literature-downloader-skill repository) into .claude/skills/literature-downloader in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a codex`. Or copy the skill folder (the Lucaswangzcx/literature-downloader-skill repository) into .agents/skills/literature-downloader in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Lucaswangzcx/literature-downloader-skill --skill literature-downloader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/literature-downloader, .gemini/skills/literature-downloader, .github/skills/literature-downloader and .opencode/skills/literature-downloader in your project.
Going by SKILL.md and its folder, Literature Downloader needs the command-line tools its instructions call (python). Our summary lists: Python 3.
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.
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.
Literature Downloader 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.
About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Literature Downloader: Citation Management (neflibata-feng/MyArxiv-Agent, 126 stars), Ref Downloader (ltczding-gif/ref-downloader, 139 stars), Nature Academic Search (jing1312/nature-figure-skill, 171 stars) and Gs Export (cookjohn/gs-skills, 527 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Lucaswangzcx (a GitHub user) maintains it in Lucaswangzcx/literature-downloader-skill, which has 239 GitHub stars. The repository was last updated on April 27, 2026.
Source: Lucaswangzcx/literature-downloader-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.