scholaraio: Skill for Claude Code

.claude/skills/citation-check/SKILL.md

citation-check is a skill for Claude Code from ZimoLiao/scholaraio. It costs 34 tokens per session (833 once invoked), scanned A, original, MIT.

A citation checker that compares references in written text with papers stored in a local research library.

In plain words
What is it for?
Use it to check citations in a file, pasted text, or a selected workspace, then inspect paper details and whether the text accurately describes the source.
Why use it?
It helps find made-up references, incorrect author or year details, unclear matches, and citations that are missing from the library before publication.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ZimoLiao/scholaraio's own configuration. It tells Claude Code how to work on scholaraio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scholaraio configures →

Part of the scholaraio plugin — 44 skills, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to ZimoLiao/scholaraio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ZimoLiao/scholaraio/main/.claude/skills/citation-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ZimoLiao/scholaraio

Made for: Claude Code.

Or install scholaraio, the plugin that ships this one along with the rest of its 44 skills, 1 hook.

Wrote 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.

agentmods badge for citation-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/zimoliao/scholaraio/citation-check/github.svg)](https://agentmods.dev/skills/zimoliao/scholaraio/citation-check)
Your own site
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/citation-check"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/citation-check/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.

agentmods 80×15 button for citation-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/citation-check"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/citation-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 833 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00833
Opus 5.5 $0.00014 $0.00333
Sonnet 5.5 $0.00007 $0.00167
Haiku 4.5 $0.00003 $0.00083

Measured 2mo ago against content hash 9494777873ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

citation-check 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 2mo 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.

.claude/skills/citation-check/SKILL.md · 78 lines

What it actually says

引用验证

检查文本中的引用是否真实、准确,防止 AI 幻觉引用和元数据错误。

重要背景:AI 生成的学术文本中约 40% 的引用可能是幻觉(编造的论文、张冠李戴、元数据拼凑)。即使是人类写的文本也常有年份/期刊名错误。本 skill 的目标是在投稿前消灭所有引用问题。

CLI 命令(首选方法)

# 检查文件中的引用
scholaraio citation-check <file>

# 在工作区范围内验证
scholaraio citation-check <file> --ws <workspace-name>

# 从 stdin 读取
cat draft.md | scholaraio citation-check

CLI 自动提取 author-year 格式的引用(Author (Year)、(Author, Year)、Author & Author (Year)、Author et al. (Year) 等),在本地知识库中搜索匹配,输出每条引用的验证状态:

状态 含义
VERIFIED 本地库有唯一匹配,作者+年份一致
AMBIGUOUS 本地库有多条匹配,需人工确认
NOT_IN_LIBRARY 本地库中无此论文

对于 AMBIGUOUS 和 NOT_IN_LIBRARY 的结果,可进一步执行手动深度验证(见下文)。

前提

用户提供待检查的文本(粘贴、文件路径、或指定 workspace 中的草稿文件)。 如有 workspace,优先在工作区范围内验证。

手动深度验证

CLI 完成初步筛查后,对问题引用执行更细致的检查:

Layer 1 — 本地库匹配

scholaraio search-author "<Author>" --limit 5
scholaraio usearch "<关键词 from title>" --limit 5

在本地库中找到匹配论文后,核对:作者名、年份、标题、期刊是否一致。

Layer 2 — DOI/元数据核验

如果本地库有匹配,读取 meta.json 中的 DOI 和详细元数据交叉比对。 如果本地库无匹配,提醒用户——该引用不在工作区/知识库中。

Layer 3 — 内容一致性

对于关键引用(支撑核心论点的),加载 L2-L3 检查:

scholaraio show <paper-id> --layer 3

验证:文本中对该论文的描述是否与论文实际内容一致?是否存在过度解读或断章取义?

常见问题模式

  • AI 幻觉引用:作者名和年份拼凑出一篇不存在的论文——标记 SUSPICIOUS
  • 张冠李戴:引用了真实论文但描述的是另一篇的内容——标记 CONTENT MISMATCH
  • 元数据错误:年份差一年、期刊名拼错、一作搞错——标记 METADATA MISMATCH 并给出正确值
  • 过度引用:一个论点堆了 5+ 引用但大部分并不直接相关——建议精简

示例

用户说:"帮我检查这段文字里的引用是否正确" → 先运行 scholaraio citation-check <file>,再对问题引用逐条深入验证

用户说:"检查 workspace/my-paper/introduction.md 里的引用" → 运行 scholaraio citation-check workspace/my-paper/introduction.md --ws my-paper

Changes

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.

  1. 2mo ago First seen · 78 lines · 34 tokens per session scan A 9494777873ee

Subscribe to this mod's changes

citation-check is a skill published in the GitHub repository ZimoLiao/scholaraio (584 stars, last pushed 10d ago), licensed MIT. It adds 34 tokens to every session and 833 once invoked, about $0.0001 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.

Related

citation-check compared with skills from other repositories

citation-check next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
citation-checkZimoLiao/scholaraioSkill58410d agoMITA34Claude Code
thoughtdagchenxiachan/thoughtdagSkill7425d agoMITB39Claude Code, Codex
autosearch:channel-selection0xmariowu/AutosearchSkill547d agoMITA87Claude Code
autosearch:context-retention-policy0xmariowu/AutosearchSkill547d agoMITA89Claude Code
autosearch:delegate-subtask0xmariowu/AutosearchSkill547d agoMITA71Claude Code
autosearch:experience-compact0xmariowu/AutosearchSkill547d agoMITA69Claude Code
autosearch:graph-search-plan0xmariowu/AutosearchSkill547d agoMITA72Claude Code