学术文献检索与质量验证。覆盖 Semantic Scholar / CrossRef / arXiv / OpenAlex 四源,内置 Tier 0 反幻觉校验(DOI 反查 + Levenshtein ≥ 0.70) 和 venue quality 过滤(CCF + JCR 影响因子,arXiv 引用阈值)。任何需要 查文献、验证引用真实性、评估期刊/会议质量、生成…

No licenceAuto-check: notesResearch & Science

Install Citation Search

skills CLI
$ npx skills add larbare12/paperfactory-from-idea-to-manuscript --skill citation-search -a claude-code

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

GitHub CLI
$ gh skill install larbare12/paperfactory-from-idea-to-manuscript citation-search --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/larbare12/paperfactory-from-idea-to-manuscript.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/citation-search .claude/skills/citation-search && 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
citation-search
GitHub stars
116
Token cost
~1.9k tokens
SKILL.md length
422 words
Files
23 (incl. scripts)
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

学术文献检索与质量验证。覆盖 Semantic Scholar / CrossRef / arXiv / OpenAlex 四源,内置 Tier 0 反幻觉校验(DOI 反查 + Levenshtein ≥ 0.70) 和 venue quality 过滤(CCF + JCR 影响因子,arXiv 引用阈值)。任何需要 查文献、验证引用真实性、评估期刊/会议质量、生成…

  • Tasks that involve Academic paper search
  • SKILL.md covers 何时调用本 skill, 五种检索 mode 速查, 配套脚本 and 必读规范(进入本 skill 前/中), plus 4 more sections
  • Runs Shell scripts from its folder; calls bash and pip; reaches semanticscholar.org; needs S2_API_KEY
  • Tasks that involve Citation management

What it does

Citation Search is an agent skill from larbare12/paperfactory-from-idea-to-manuscript. 学术文献检索与质量验证。覆盖 Semantic Scholar / CrossRef / arXiv / OpenAlex 四源,内置 Tier 0 反幻觉校验(DOI 反查 + Levenshtein ≥ 0.70) 和 venue quality 过滤(CCF + JCR 影响因子,arXiv 引用阈值)。任何需要 查文献、验证引用真实性、评估期刊/会议质量、生成 BibTeX、或建立证据池 的场景都应调用本 skill,而不是让 Claude 凭记忆产出引用。M0-M9 模块在 执行文献检索时统一委托给本 skill,不重复实现。

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 26 other files, including scripts (for example `config/README.md`, `config/api.json` and `reference/anti-hallucination-protocol.md`).

It sits in Research & Science, covering Academic paper search and Citation management. It works with arXiv, Semantic Scholar and LaTeX. The repository describes itself as: 能够实现:人提供idea,agent自动帮你生成论文.

When your agent uses it

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

Example prompts

  • “/citation-search”

Requirements

  • Python 3
  • A Bash shell
  • A credential in S2_API_KEY
  • Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Grep, Glob

What it can do on your machine

Read from SKILL.md and the folder at commit 869103c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Edit
    • Grep
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 7 files in scripts/ (Shell, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • 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:

    • semanticscholar.org

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • S2_API_KEY

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

Context cost

Citation Search loads about 1.9k tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 422 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:182
    S2 网络失败 | `verdict=S2_UNAVAILABLE` | 检查 `.env` 凭据 / 网络代理 |
  • NoteMentions a .env fileSKILL.md:185
    | verify_config.sh 报警 | `cp .env.example .env` 并填入 |
  • NoteMentions a .env fileSKILL.md:214
    - `S2_API_KEY` = 从 `<project>/.env` 或 `<skill>/.env` 加载
  • NoteMentions a .env fileSKILL.md:221
    # 1. 在项目根或 skill 根创建 .env
  • NoteMentions a .env fileSKILL.md:222
    cp .env.example .env
  • NoteMentions a .env fileSKILL.md:225
    # 填入 .env: S2_API_KEY=Bearer xxxxx
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Edit, Grep, Glob

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 422 words (~1,872 tokens).

name
citation-search
allowed-tools
Bash, Read, Write, Edit, Grep, Glob

Read the full SKILL.md on GitHub

Files

SKILL.md and 22 other files (scripts) in skills/citation-search of larbare12/paperfactory-from-idea-to-manuscript.

  • SKILL.md
  • config/README.md
  • config/api.json
  • data/ccf_2026.jsonl
  • data/ccf_2026.sqlite
  • data/impact_factor.sqlite3
  • reference/anti-hallucination-protocol.md
  • reference/literature-research-protocol.md
  • reference/manifest-schema.md
  • reference/venue-quality-protocol.md
  • scripts/author_info.sh
  • scripts/check_material_gaps.sh
  • scripts/collect_papers.sh
  • scripts/doi2bibtex.sh
  • scripts/find_evidence.sh
  • scripts/init.sh
  • scripts/load_config.sh
  • … and 6 more

Open the folder on GitHubat commit 869103c

Compare with similar skills

Citation Search 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.

Citation Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Citation Search this skilllarbare12/paperfactory-from-idea-to-manuscript116—~1.9kAutomated safety check: NotesNone
Literature Review AgentAr9av/PaperOrchestra6791 repos~5.2kAutomated safety check: PassCustom licence
Nature Academic Searchjing1312/nature-figure-skill171—~1.3kAutomated safety check: NotesMIT
Literature ReviewNorman-bury/research-writing-skill3.4k—~2.2kAutomated safety check: NotesMIT
Literature Searchlingzhi227/agent-research-skills390—~805Automated safety check: PassNone
Ai4scholar ResearchDrchronx/ai-agent-research-starter-kit139—~1.4kAutomated safety check: PassCustom licence

Similar skills

  • Literature Review Agent

    Ar9av/PaperOrchestra

    Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from Ar9av/PaperOrchestra.

    679 GitHub starsUsed in 1 repo~5.2k tokens
    Research & ScienceAuto-check passed
  • Nature Academic Search

    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)…

    171 GitHub stars~1.3k tokensUpdated 1 mo ago
    Research & ScienceAuto-check: notes
  • Literature Review

    Norman-bury/research-writing-skill

    A skill your agent uses when writing literature review sections - guides searching, organizing, and synthesizing academic sources

    3.4k GitHub stars~2.2k tokensUpdated 4 mo ago
    Research & ScienceAuto-check: notes
  • Literature Search

    lingzhi227/agent-research-skills

    Search academic literature using Semantic Scholar, arXiv, and OpenAlex APIs.

    390 GitHub stars~805 tokensUpdated 7 mo ago
    Research & ScienceAuto-check passed
  • Ai4scholar Research

    Drchronx/ai-agent-research-starter-kit

    Use AI4Scholar for real scholarly literature tasks through MCP or the OpenClaw plugin: paper search, Google Scholar/Semantic Scholar/PubMed/arXiv/bioRxiv/medRxiv queries, PDF download and reading…

    139 GitHub stars~1.4k tokensUpdated 4 mo ago
    Research & ScienceAuto-check passed
  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes

More from larbare12/paperfactory-from-idea-to-manuscript

All 9 skills in this repo
  • M0 Dashboard

    larbare12/paperfactory-from-idea-to-manuscript

    M0 项目仪表盘——流程外的常驻横切模块,不属于线性步骤。任何时点 扫描 relate-work/ + draft/ 输出三态报表:已完成 / 待回填(NEEDS-EVIDENCE / TODO / 未读论文)/ 阻塞。M1-M7 任何阶段都可以调用 M0 看状态。/paper- assistant:init 命令首次扫描就是它。M0 只读不写,不动 manifest 也不动 draft。

    116 GitHub stars~809 tokensUpdated 4 mo ago
    Auto-check: notes
  • M1 Topic

    larbare12/paperfactory-from-idea-to-manuscript

    M1 选题诊断——数据驱动的研究 idea 可行性 / 创新性 / 领域契合度评估. An agent skill from larbare12/paperfactory-from-idea-to-manuscript.

    116 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check: notes
  • M2 Literature

    larbare12/paperfactory-from-idea-to-manuscript

    M2 文献管理(IMRAD 中的 Related Work + References)。消费 M1 沉淀的 search-.jsonl,做精读、引用网络分析、bibkey 整理、四类标签(基础/方法/ baseline/相关)、引用密度审计、BibTeX 格式规范化,产出 manifest.jsonl + ref-.md 笔记卡 + 引用校验报告,供 M3 baseline / M5 论证链…

    116 GitHub stars~1.8k tokensUpdated 4 mo ago
    Auto-check: notes
  • M3 Experiment

    larbare12/paperfactory-from-idea-to-manuscript

    M3 实验设计——方案检查、指标选择、对比方法、消融、显著性、误差分析. An agent skill from larbare12/paperfactory-from-idea-to-manuscript.

    116 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check: notes
  • M4 Structure

    larbare12/paperfactory-from-idea-to-manuscript

    M4 结构规划——生成 IMRAD 大纲、章节边界、篇幅分配、写作顺序。只管 骨架,不管论证逻辑(论证主线归 m5-argument)。消费 M3 实验结果概要 和 M1 选题定位,产出 outline 写入 passport,供 M5/M6 按章节展开。

    116 GitHub stars~952 tokensUpdated 4 mo ago
    Auto-check: notes
  • M6 Writing

    larbare12/paperfactory-from-idea-to-manuscript

    M6 写作辅助——按 M5 论证骨架展开正文,按 M4 章节边界控制内容. An agent skill from larbare12/paperfactory-from-idea-to-manuscript.

    116 GitHub stars~2.3k tokensUpdated 4 mo ago
    Auto-check: notes

Questions about Citation Search

What does Citation Search do?

学术文献检索与质量验证。覆盖 Semantic Scholar / CrossRef / arXiv / OpenAlex 四源,内置 Tier 0 反幻觉校验(DOI 反查 + Levenshtein ≥ 0.70) 和 venue quality 过滤(CCF + JCR 影响因子,arXiv 引用阈值)。任何需要 查文献、验证引用真实性、评估期刊/会议质量、生成…. Citation Search is an agent skill from larbare12/paperfactory-from-idea-to-manuscript.

When should I use Citation Search?

Citation Search fits situations like: tasks that involve Academic paper search; tasks that involve Citation management.

How do I install Citation Search in Claude Code?

Run `npx skills add larbare12/paperfactory-from-idea-to-manuscript --skill citation-search -a claude-code`. Or copy the skill folder (skills/citation-search in larbare12/paperfactory-from-idea-to-manuscript) into .claude/skills/citation-search in your project. Claude Code loads it when a task matches its description.

How do I install Citation Search in Codex?

Run `npx skills add larbare12/paperfactory-from-idea-to-manuscript --skill citation-search -a codex`. Or copy the skill folder (skills/citation-search in larbare12/paperfactory-from-idea-to-manuscript) into .agents/skills/citation-search in your project. Codex loads it when a task matches its description.

Can I use Citation Search 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 larbare12/paperfactory-from-idea-to-manuscript --skill citation-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/citation-search, .gemini/skills/citation-search, .github/skills/citation-search and .opencode/skills/citation-search in your project.

What does Citation Search need to run?

Going by SKILL.md and its folder, Citation Search needs a shell for the scripts in its folder, the command-line tools its instructions call (bash and pip) and credentials named S2_API_KEY. Our summary lists: Python 3; A Bash shell; A credential in S2_API_KEY. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit, Grep, Glob.

Does Citation Search access the network?

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

Is Citation Search safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. 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 Citation Search use?

No licence was found for Citation Search or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Citation Search use?

About 1.9k tokens (SKILL.md is roughly 7.5k 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 Citation Search?

Skills that share tags, products or a category with Citation Search: Literature Review Agent (Ar9av/PaperOrchestra, 679 stars), Nature Academic Search (jing1312/nature-figure-skill, 171 stars), Literature Review (Norman-bury/research-writing-skill, 3.4k stars) and Literature Search (lingzhi227/agent-research-skills, 390 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Citation Search?

larbare12 (a GitHub user) maintains it in larbare12/paperfactory-from-idea-to-manuscript, which has 116 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on May 19, 2026.

Source: larbare12/paperfactory-from-idea-to-manuscript on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.