Agent skill

Scipilot Cite Skill

by franklee16 in franklee16/academic-research-skills

SciPilot Skills 家族的文献检索与引用插入技能。支持两种输入模式—— 模式 A:读取用户的 Word(.docx) 或 LaTeX(.tex) 论文,在正文对应章节插入引用; 模式 B:接收用户给出的一段话/一个观点/一个论断,输出能支撑它的参考文献列表 (不修改文档)。两种模式都通过 Semantic Scholar、OpenAlex、Crossref 三源…

MITAuto-check passedResearch & Science

Install Scipilot Cite Skill

skills CLI
$ npx skills add franklee16/academic-research-skills --skill scipilot-cite-skill -a claude-code

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

GitHub CLI
$ gh skill install franklee16/academic-research-skills scipilot-cite-skill --agent claude-code

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

Manual copy
$ git clone --depth 1 https://github.com/franklee16/academic-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/reference-citation/scipilot-cite-skill-main .claude/skills/scipilot-cite-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

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

Facts

Skill name
scipilot-cite-skill
GitHub stars
223
Token cost
~1.9k tokens
SKILL.md length
573 words
Files
20 (incl. scripts, references, assets)
Skills in repo
1,617
Repo updated
First seen
Licence
MIT

At a glance

SciPilot Skills 家族的文献检索与引用插入技能。支持两种输入模式—— 模式 A:读取用户的 Word(.docx) 或 LaTeX(.tex) 论文,在正文对应章节插入引用; 模式 B:接收用户给出的一段话/一个观点/一个论断,输出能支撑它的参考文献列表 (不修改文档)。两种模式都通过 Semantic Scholar、OpenAlex、Crossref 三源…

  • Works in 8 steps: :信息收集(必须完成 — 主动逐项询问,禁止默默假设) → :论文分析 → :文献检索 → …
  • Tasks that involve Academic paper search
  • SKILL.md covers 概述, IRON RULES(不可违反的铁律), 触发条件 and 工作流程, plus 5 more sections
  • Runs Python scripts from its folder; calls python and pip; reaches doi.org

What it does

Scipilot Cite Skill is an agent skill from franklee16/academic-research-skills. SciPilot Skills 家族的文献检索与引用插入技能。支持两种输入模式—— 模式 A:读取用户的 Word(.docx) 或 LaTeX(.tex) 论文,在正文对应章节插入引用; 模式 B:接收用户给出的一段话/一个观点/一个论断,输出能支撑它的参考文献列表 (不修改文档)。两种模式都通过 Semantic Scholar、OpenAlex、Crossref 三源 并行检索真实文献,DOI + 多源交叉验证真实性,然后按用户指定格式(IEEE/APA/ Nature/Vancouver/GB-T-7714 等)输出。每次交付前都强制运行 Gate 8 末端幻觉 门控审计,FAIL 即拒绝交付。Stage 0 必须主动询问用户的多项偏好:篇数、格式、 年限、章节、期刊分区、作者偏好、机构偏好、是否含预印本等,禁止默默用默认值。 当用户提到以下任何情况时触发此技能:添加参考文献、插入引用、找文献、 citation、reference、加引用、补充参考文献、文献检索、add references、 find papers、insert citations、找文献支撑观点、用文献支撑这段话、 support…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including scripts, reference files and assets (for example `README.md`, `assets/format_templates/apa7.json` and `assets/format_templates/gb-t-7714.json`).

It sits in Research & Science, covering Academic paper search, LaTeX and Citation management. It works with Microsoft Word, LaTeX and Semantic Scholar. The repository describes itself as: Comprehensive collection of Claude Code skills for academic research in economics, finance, and social sciences. The licence is MIT.

When your agent uses it

  • Tasks that involve Academic paper search
  • Tasks that involve LaTeX
  • Tasks that involve Citation management

Example prompts

  • “帮我的论文加几篇参考文献”
  • “scipilot 帮我找文献”
  • “这个观点有文献支撑吗”
  • “/scipilot-cite-skill”

Requirements

  • Python 3

Workflow steps

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

  1. :信息收集(必须完成 — 主动逐项询问,禁止默默假设)
  2. :论文分析
  3. :文献检索
  4. :文献验证(关键步骤)
  5. :文献筛选与排序
  6. :引用插入 / 列表输出
  7. :格式化输出
  8. :最终检查与交付

What it can do on your machine

Read from SKILL.md and the folder at commit 9a4b2db. 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 4 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • pip

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • doi.org

    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

Scipilot Cite Skill loads about 1.9k tokens when it runs, and up to ~8k if it reads all its reference files. Until then it costs about 181 tokens; SKILL.md has 573 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~181
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8k

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 franklee16/academic-research-skills at commit 9a4b2db, republished under its MIT licence (© franklee16). 573 words, ~1,948 tokens.

Download SKILL.mdSave it as .claude/skills/scipilot-cite-skill/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.
name
scipilot-cite-skill
description
SciPilot Skills 家族的文献检索与引用插入技能。支持两种输入模式—— 模式 A:读取用户的 Word(.docx) 或 LaTeX(.tex) 论文,在正文对应章节插入引用; 模式 B:接收用户给出的一段话/一个观点/一个论断,输出能支撑它的参考文献列表 (不修改文档)。两种模式都通过 Semantic Scholar、OpenAlex、Crossref 三源 并行检索真实文献,DOI + 多源交叉验证真实性,然后按用户指定格式(IEEE/APA/ Nature/Vancouver/GB-T-7714 等)输出。每次交付前都强制运行 Gate 8 末端幻觉 门控审计,FAIL 即拒绝交付。Stage 0 必须主动询问用户的多项偏好:篇数、格式、 年限、章节、期刊分区、作者偏好、机构偏好、是否含预印本等,禁止默默用默认值。 当用户提到以下任何情况时触发此技能:添加参考文献、插入引用、找文献、 citation、reference、加引用、补充参考文献、文献检索、add references、 find papers、insert citations、找文献支撑观点、用文献支撑这段话、 support claim with literature、validate viewpoint with references, 或者用户上传了论文文件并要求增加文献引用,或者用户给一段话/观点并要求找文献 支撑。即使用户只是说"帮我的论文加几篇参考文献"或"scipilot 帮我找文献"或 "这个观点有文献支撑吗",也应该触发此技能。 属于 SciPilot Skills 科研技能家族。
license
MIT

SciPilot-cite-skill — 学术文献自动检索与引用插入

SciPilot Skills 家族成员 | 你的文献引用副驾驶

概述

SciPilot-cite 将真实、可验证的学术文献自动检索并插入用户论文。 所有文献必须来自学术数据库 API 的真实检索结果,严禁编造或虚构任何文献信息。

IRON RULES(不可违反的铁律)

  1. 真实性铁律:每一篇引用的文献必须通过 DOI 验证或至少两个独立学术数据库交叉确认。绝对不允许编造任何论文标题、作者、期刊、年份、DOI。如果无法验证某篇文献的真实性,必须丢弃它,宁缺毋滥。
  2. 顺序铁律:引用编号必须严格按照在正文中首次出现的顺序,从 [1] 开始递增。References 列表的排列顺序必须与正文引用编号完全一致。任何编号跳跃、重复或乱序都是严重错误。
  3. 时效铁律:默认只检索近 5 年的文献(用户可自定义)。每篇文献的发表年份必须在允许范围内,过期文献自动排除。
  4. 质量铁律:优先选择高引用量、发表在知名期刊/会议的文献。预印本(arXiv 等)仅在用户明确允许时才包含。
  5. 格式一致铁律:同一篇论文中所有引用必须使用完全相同的格式规范,不允许混用不同引用风格。
  6. 不破坏铁律:插入引用时不得修改论文的任何原有内容(文字、图表、公式等),只允许在合适位置添加引用标记和 References 章节。
  7. 证据账本铁律:最终 bibliography 中的每一篇文献都必须在工作目录的 verification_log.jsonl 中有对应 paper_id 条目,且 verdict ∈ {VERIFIED, LIKELY_REAL}。Stage 7 必须运行 scripts/audit_no_hallucination.py 做末端 100% 重验证 + 与日志对账,只有 audit 返回 PASS 才能交付;任何 FAIL 必须中断、向用户报告疑似幻觉条目,不得"凭印象"添加任何未经脚本验证的论文。

触发条件

当用户意图涉及以下任一场景时激活:

  • 为论文添加/补充参考文献
  • 检索特定主题的学术论文
  • 在论文中插入引用标记
  • 格式化已有的参考文献列表
  • 用户上传了 .docx 或 .tex 文件并提到"引用""参考文献""citation""reference"
  • 用户提到 "scipilot" 并涉及文献/引用相关内容

工作流程

下面 8 个 Stage 必须严格按顺序执行。每个 Stage 完成前,不得跳跃到后续 Stage。

Stage 0:信息收集(必须完成 — 主动逐项询问,禁止默默假设)

这是 Skill 的核心交互阶段。绝对禁止在任何必问项缺失时就开始检索;对有默认值的项也必须告知用户默认值再询问是否调整。

A. 输入模式(最先问)

询问 "这次的任务类型":

  • 模式 A — 完整论文模式:用户有 .tex 或 .docx 文件,要在文档中插入引用
  • 模式 B — 片段支撑模式:用户给一段话 / 一个观点 / 一个论断,要找真实文献支撑(输出参考文献列表,不修改任何文档)
B. 基础参数(两种模式都必问)
  1. 目标对象:
    • 模式 A → 论文文件路径(.tex 或 .docx)
    • 模式 B → 要支撑的文字片段(用户粘贴一段话即可)
  2. 文献数量:建议 5-30 篇;模式 B 通常 5-15 篇即足够
  3. 引用格式:
    • IEEE(默认,工程/计算机/通信)
    • APA 7th(心理学/社科)
    • Nature(自然科学顶刊,上标编号)
    • Vancouver(医学/生物)
    • GB/T 7714-2015(中文国标)
    • 自定义(用户提供规则)
C. 检索范围(必问,告知默认值)
  1. 年份范围:默认近 5 年(基于当前日期动态计算),用户可改(如 "近 3 年"、"2020-2026")
  2. 是否含预印本:默认 不含(arXiv / bioRxiv / medRxiv / SSRN 等),用户可改
D. 插入位置(仅模式 A 必问)
  1. 目标章节:用户希望在哪些章节插入?
    • 默认:所有相关章节自动判断(Introduction / Related Work / Method / Experiments / Discussion)
    • 可指定:"只在 Related Work 和 Method 加" / "排除 Conclusion 章节" / "重点加在 Introduction"
E. 质量与偏好(必主动询问,用户可逐项跳过)
  1. 必引论文:是否有必须引用的特定文献?必须由用户提供 DOI 或完整元数据——Skill 不会自己编一篇凑数
  2. 期刊/会议偏好:偏好哪些 venue?要排除哪些?(例:"偏好 Nature/Science/Cell"、"排除会议论文")
  3. 期刊分区:JCR Q1 / Q1-Q2 / 中科院 1 区 / 中科院 1-2 区 / 不限(默认不限)
    注:分区判断基于 LLM 对常见顶刊的认知做软过滤,非权威 ISSN-tier 数据库查询。如用户要求严格分区控制,需提供具体期刊白名单。
  4. 作者偏好:偏好引用某些作者或课题组?要排除某些作者?(例:"偏好 Yoshua Bengio 组"、"排除自引")
  5. 作者单位偏好:偏好哪些机构?要排除哪些?(例:"只要 MIT/Stanford/清华"、"排除商业公司")
  6. 额外检索关键词:自动从论文/片段抽取关键词后,用户可补充几个领域术语
F. 参数复述确认(必须执行)

收齐后必须向用户口头复述全部参数并等待确认,例:

我将处理 paper.tex(模式 A),在 Introduction + Related Work 中插入 15 篇 IEEE 格式文献,年份 2022-2026,不含预印本。 偏好:JCR Q1,机构含 MIT/清华,必引 [DOI: 10.1038/s41586-024-07421-0], 关键词补充 diffusion model / medical imaging。开始?

未获明确"开始"信号前,不进入 Stage 1。

Stage 1:论文分析

读取用户论文文件并提取结构。

  • .tex:直接读源码,识别 \section{}、\cite{},记录已有引用与 bibliography 类型。
  • .docx:用 python-docx 读取段落、Heading 样式、已有 References。

输出:论文标题、各章节列表、已有引用列表、核心关键词(自动 + 用户补充)。

Stage 2:文献检索

调用 scripts/search_papers.py。

  • 并行查询 Semantic Scholar / OpenAlex / Crossref
  • 每个 API 抓取 ceil(用户需求数量 × 3) 篇候选
  • 按引用量降序
  • 过滤年份范围
  • 若 include_preprint=False,剔除 venue 含 arxiv/biorxiv/medrxiv 的条目
  • DOI 主键去重;无 DOI 时按 (标题相似度 >0.9 + 同年份 + 同首作者姓) 合并
Stage 3:文献验证(关键步骤)

调用 scripts/verify_paper.py::batch_verify。

验证分级:

  • [OK] VERIFIED:DOI 可解析、Crossref 元数据匹配(标题相似度 ≥0.85,年份精确,首作者姓匹配)
  • [WARN] LIKELY_REAL:DOI 缺失或验证失败,但 Semantic Scholar 和 OpenAlex 都能搜到同一标题(≥0.85 相似)
  • [FAIL] UNVERIFIED:上述都不通过 → 直接丢弃,不得引用

只有 VERIFIED 和 LIKELY_REAL 的文献进入下一步。

Stage 4:文献筛选与排序

从候选中按以下加权挑选用户需要的数量:

  • 相关性 40%(文献摘要与论文章节的语义相关)
  • 质量 30%(引用量 + 期刊级别)
  • 时效 20%(越新越好)
  • 多样性 10%(避免同一作者团队集中)

向用户展示候选清单:每条含标题、作者、年份、venue、引用量、验证状态、建议章节。 等待用户确认或要求替换,若替换则回到 Stage 2。

Show full SKILL.md (245 more words)Show less
Stage 5:引用插入 / 列表输出

模式 A(论文插入):

  • .tex → scripts/insert_citations_latex.py:用 \cite{key} 插入,并维护 thebibliography 或 BibTeX .bib 文件
  • .docx → scripts/insert_citations_docx.py:插入 [N] 文本标记,在文末加 References 章节
  • 仅在 Stage 0 指定的目标章节内插入——不在用户排除的章节加引用

编号规则:从正文第一段开始按首次出现顺序分配 [1] [2] [3]...;已有引用从最大编号 +1 开始(或用户选择重新编号)。

插入位置规则:

  • 在相关论述句子末尾、句号之前
  • 一个位置可有多个引用:[3,5,7]
  • 禁止插入到图表标题、公式、章节标题中

模式 B(片段支撑列表输出):

  • 不修改任何文档;将候选文献按相关性 + Stage 0 偏好排序
  • 输出格式化的 References 列表到对话中,并可保存到 references_output.md
  • 每条引用前加编号 [1] [2] ...
  • 同时输出"该文献如何支撑用户的观点"的一句话简要说明(基于摘要)
Stage 6:格式化输出

调用 scripts/format_citation.py::format_citation(paper, style) 按用户指定格式生成每条参考文献。

格式样例(详见 references/citation-formats.md):

IEEE [1] A. Author, B. Author, "Title," *Journal*, vol. X, 2024, doi: 10.xxxx/xxxxx.
APA 7 Author, A., & Author, B. (2024). Title. *Journal*. https://doi.org/10.xxxx/xxxxx
Nature 1. Author, A., Author, B. Title. *Journal* 600, 1-10 (2024).
Vanc. 1. Author A, Author B. Title. Journal. 2024.
GB/T [1] 作者. 题名[J]. 刊名, 年, 卷(期): 起止页码.
Stage 7:最终检查与交付
第 0 项(阻塞性幻觉门控 — Gate 8)

这是第一项,先于其他自检执行,失败立即中断整个交付流程。

把最终采用的文献清单写到 final_papers.json,然后强制运行:

bash
python scripts/audit_no_hallucination.py final_papers.json \
       --log verification_log.jsonl \
       --report audit_report.json

捕获 exit code:

  • 0 → audit PASS,所有引用通过 100% 重验证 + 日志对账,继续后续自检
  • 2 → audit FAIL,立刻中断 Stage 7。读 audit_report.json 的 per_paper 段,把所有 pass=false 的条目逐条向用户报告(标题、DOI、失败原因),询问用户是要丢弃这些条目(推荐)、用替代论文重检(回 Stage 2)、还是放弃整次操作
  • 3 → 运行性错误(文件缺失/格式错误),修复后重跑

绝对不允许:跳过 audit、伪造 audit 报告、把 FAIL 条目当 PASS 处理。这条违反了 IRON RULE 7。

第 1-5 项(仅在第 0 项 PASS 后执行)
  1. 编号连续性:[1] 到 [N] 无跳跃、无重复
  2. 引用-列表一致性(仅模式 A):每个正文编号在 References 都有;References 无未引用孤儿
  3. 格式一致性:所有条目同一 style
  4. 原文完整性(仅模式 A):diff 比对确认未修改原文
  5. 预印本占比:若 include_preprint=False,复查 venue 不含 arxiv

模式 B 跳过第 2 项和第 4 项(不涉及原文与正文引用)。

交付时输出一份 SciPilot 引用报告:

  • 总计添加 N 篇
  • audit_report.json 的 PASS/FAIL 摘要
  • 各文献的验证状态、来源 API
  • 各章节引用分布
  • 任何 LIKELY_REAL 文献必须明确标注

错误处理

  • API 失败:自动重试 3 次(间隔 2s 指数退避);某 API 持续失败则用其他 API 补充
  • 数量不足:告知用户实际找到数量,询问是否放宽搜索或接受较少
  • 解析异常:请用户确认文件完整性

与 SciPilot Skills 家族协作

  • 引用插入后 → 推荐 scipilot-polish-skill 润色新增引用句
  • 全面审查 → 推荐 scipilot-review-skill
  • 图表配合 → 推荐 scipilot-figure-skill

依赖

pip install requests python-docx python-Levenshtein

所有 API 都是免费访问层级,无需 API key。

工作目录产物(必须保留至交付完成)

文件由谁生成用途
evidence_log.jsonlsearch_papers.py 每条结果落盘证明每篇候选都来自真实 API 响应
verification_log.jsonlverify_paper.py::batch_verify 每条验证落盘Stage 7 第 0 项的对账依据
final_papers.jsonLLM 在 Stage 4 用户确认后写出audit 的输入
audit_report.jsonaudit_no_hallucination.py 输出给用户的 Gate 8 凭证

这四个文件构成本 Skill 的"证据链"。LLM 没有写权限直接产生 evidence/verification 日志——必须通过运行对应的 Python 脚本来产生。这是把"不编造"从口号变成机器可检查契约的核心机制。

参考文件

  • references/citation-formats.md — 各引用格式完整规范与示例
  • references/api-reference.md — Semantic Scholar / OpenAlex / Crossref API 详细文档
  • references/workflow.md — 完整工作流程与边界情况处理
  • assets/format_templates/*.json — 各格式的 JSON 模板(可被自定义覆盖)

© franklee16, 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 19 other files (scripts, references, assets) in reference-citation/scipilot-cite-skill-main of franklee16/academic-research-skills.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • assets/format_templates/apa7.json
  • assets/format_templates/gb-t-7714.json
  • assets/format_templates/ieee.json
  • assets/format_templates/nature.json
  • assets/format_templates/vancouver.json
  • references/api-reference.md
  • references/citation-formats.md
  • references/workflow.md
  • requirements.txt
  • scripts/audit_no_hallucination.py
  • scripts/format_citation.py
  • scripts/insert_citations_docx.py
  • scripts/insert_citations_latex.py
  • … and 3 more

Open the folder on GitHubat commit 9a4b2db

Compare with similar skills

Scipilot Cite Skill 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.

Scipilot Cite Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scipilot Cite Skill this skillfranklee16/academic-research-skills223—~1.9kAutomated safety check: PassMIT
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~7.3kAutomated safety check: PassCustom licence
Latex To Word Workflowhajimi-kun/latex-to-word-workflow128—~2.3kAutomated safety check: PassMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Paper OrchestraAr9av/PaperOrchestra6771 repos~3.5kAutomated safety check: PassCustom licence
SearchMuuuun/luxas1.2k—~2.3kAutomated safety check: WarnMIT

Similar skills

  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.5k GitHub stars~7.3k tokensUpdated 4 days ago
    Documents & OfficeAuto-check passed
  • Latex To Word Workflow

    hajimi-kun/latex-to-word-workflow

    Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a…

    128 GitHub stars~2.3k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed
  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Paper Orchestra

    Ar9av/PaperOrchestra

    Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines…

    677 GitHub starsUsed in 1 repo~3.5k tokens
    Research & ScienceAuto-check passed
  • Search

    Muuuun/luxas

    Unified academic paper search, citation chains, paper download (arXiv LaTeX/PDF, Sci-Hub), figure extraction from papers, LaTeX source reading, BibTeX fetching, web search, and browser automation…

    1.2k GitHub stars~2.3k tokensUpdated 1 mo ago
    Research & ScienceAuto-check: warnings
  • Export

    ZimoLiao/scholaraio

    A skill your agent uses when the user needs BibTeX, RIS, Markdown reference lists, filtered citation exports, custom citation styles, or a Markdown-to-DOCX export for sharing.

    577 GitHub stars~1.6k tokensUpdated 14 days ago
    Research & ScienceAuto-check passed

More from franklee16/academic-research-skills

All 1,617 skills in this repo
  • Econometric Research Writing

    franklee16/academic-research-skills

    End-to-end econometric analysis and economics/management paper-writing workflow.

    223 GitHub stars~2.4k tokensUpdated 21 days ago
    Auto-check passed
  • Paper Revision

    franklee16/academic-research-skills

    Comprehensive workflow for handling journal Revise and Resubmit (R&R) decisions.

    223 GitHub stars~3.4k tokensUpdated 21 days ago
    Auto-check passed
  • Sci Ssci Polishing

    franklee16/academic-research-skills

    A skill your agent uses when researchers need Chinese academic prose translated into publication-oriented English or English manuscript paragraphs and complete sections polished for SCI, SSCI, or…

    223 GitHub starsUsed in 1 repo~1.5k tokens
    Auto-check passed
  • Research Defense Radar

    franklee16/academic-research-skills

    Assess and monitor an ongoing research project's competitor landscape, novelty risk, and method/data opportunities from a proposal, paper, research question, data or method notes, or a suspected…

    223 GitHub stars~4k tokensUpdated 21 days ago
    Auto-check passed
  • Academic Grant

    franklee16/academic-research-skills

    Generate or fill in academic grant application forms (project statement, education plan, pathway to impact, references) using draft research material.

    223 GitHub stars~2.8k tokensUpdated 21 days ago
    Auto-check: notes
  • Chinese Reference Formatter Skill

    franklee16/academic-research-skills

    A skill your agent uses when a user needs通用中文参考文献、GB/T 7714-style bibliography entries, Chinese academic reference formatting, or BibTeX completion from Chinese or English literature titles…

    223 GitHub stars~1.1k tokensUpdated 21 days ago
    Auto-check passed

Questions about Scipilot Cite Skill

What does Scipilot Cite Skill do?

SciPilot Skills 家族的文献检索与引用插入技能。支持两种输入模式—— 模式 A:读取用户的 Word(.docx) 或 LaTeX(.tex) 论文,在正文对应章节插入引用; 模式 B:接收用户给出的一段话/一个观点/一个论断,输出能支撑它的参考文献列表 (不修改文档)。两种模式都通过 Semantic Scholar、OpenAlex、Crossref 三源…. Scipilot Cite Skill is an agent skill from franklee16/academic-research-skills.

When should I use Scipilot Cite Skill?

Scipilot Cite Skill fits situations like: tasks that involve Academic paper search; tasks that involve LaTeX; tasks that involve Citation management.

How do I install Scipilot Cite Skill in Claude Code?

Run `npx skills add franklee16/academic-research-skills --skill scipilot-cite-skill -a claude-code`. Or copy the skill folder (reference-citation/scipilot-cite-skill-main in franklee16/academic-research-skills) into .claude/skills/scipilot-cite-skill in your project. Claude Code loads it when a task matches its description.

How do I install Scipilot Cite Skill in Codex?

Run `npx skills add franklee16/academic-research-skills --skill scipilot-cite-skill -a codex`. Or copy the skill folder (reference-citation/scipilot-cite-skill-main in franklee16/academic-research-skills) into .agents/skills/scipilot-cite-skill in your project. Codex loads it when a task matches its description.

Can I use Scipilot Cite Skill 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 franklee16/academic-research-skills --skill scipilot-cite-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scipilot-cite-skill, .gemini/skills/scipilot-cite-skill, .github/skills/scipilot-cite-skill and .opencode/skills/scipilot-cite-skill in your project.

What does Scipilot Cite Skill need to run?

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

Does Scipilot Cite Skill access the network?

SKILL.md names 1 domain. In commands or code: doi.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Scipilot Cite Skill 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 Scipilot Cite Skill use?

Scipilot Cite Skill is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scipilot Cite Skill use?

About 1.9k tokens (SKILL.md is roughly 7.8k 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 6.1k tokens, read only when the agent opens those files.

What are the alternatives to Scipilot Cite Skill?

Skills that share tags, products or a category with Scipilot Cite Skill: Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Latex To Word Workflow (hajimi-kun/latex-to-word-workflow, 128 stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars) and Paper Orchestra (Ar9av/PaperOrchestra, 677 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scipilot Cite Skill?

franklee16 (a GitHub user) maintains it in franklee16/academic-research-skills, which has 223 GitHub stars. The repository holds 1,617 skills in this directory. The repository was last updated on September 18, 2026.

Source: franklee16/academic-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.