Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Qinyan Paper Search · leonchaox | DecimalAI

researchby leonchaox

Qinyan Paper Search

leonchaox/qinyan-paper-search

Source leonchaox/qinyan-academic-skills ↗License MIT

沁言学术文献检索 - 支持从 Google Scholar、万方(Wanfang)、PubMed、ArXiv 四大学术数据库检索文献。智能选择检索策略：中文优先万方、英文优先Google Scholar、医学类优先PubMed、理工计算机类优先ArXiv。使用沁言学术OpenAPI。触发词：文献检索、论文搜索、搜索论文、查找文献、paper search、find papers、search literature

SkillScore73Maintained

Automatic

Research pack

Last verified 8/15/2026

What it changes

Passed 12 of 17 test cases with the skill, and 7 of 17 without it.

Without skill41%

With skill73%

Checks it passed that the model alone missed

Passes arxiv as the source parameter.
Sets max_results to 80 in the JSON payload.
Sets date_to using YYYY or YYYYMMDD format.

and 8 more in the full report

7 fixed9 passed either way6 still failing0 broke

Pass-rate lift: +32 pp
Tokens: +41%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 8/15/2026v116 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/leonchaox-qinyan-paper-search/SKILL.md https://app.decimal.ai/s/leonchaox-qinyan-paper-search/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add leonchaox-qinyan-paper-search, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/leonchaox-qinyan-paper-search/ and pins it in .decimal/skills.lock

decimalai skills add leonchaox-qinyan-paper-search

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/leonchaox-qinyan-paper-search/SKILL.md https://app.decimal.ai/s/leonchaox-qinyan-paper-search/SKILL.md

Raw file: /s/leonchaox-qinyan-paper-search/SKILL.md ↗ · machine-readable summary at /s/leonchaox-qinyan-paper-search.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

请帮我检索近五年国内关于“智慧城市数据安全”的论文。我希望能一次性获取最大包含80条结果的列表，请写出调用万方数据库检索时传给脚本的JSON参数。

What was checked, without and with the skill
Checked	Without skill	With skill
Sets the database source argument to wanfang.	Missed	Passed
Sets max_results to 80 in the JSON payload.	Missed	Passed

case-06 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md132 lines2 filesincludes scripts

沁言学术 - 文献检索

概述

本技能通过沁言学术OpenAPI，支持从 Google Scholar、万方(Wanfang)、PubMed、ArXiv 四大学术数据库进行文献检索。根据用户查询的语言和学科领域，智能选择最优检索策略。

学术诚信声明： 所有检索结果均来自真实学术数据库，严禁捏造或猜测文献信息。如检索结果不完整，应如实告知用户。

前置条件

使用前请确保：

已设置 QINYAN_API_KEY 环境变量（前往 https://platform.qinyanai.com/ 申请）
环境中可用 curl 和 python3

export QINYAN_API_KEY="your-api-key-here"

智能检索策略

收到用户的检索请求后，请按以下策略选择数据源：

语言策略

中文查询：优先使用 万方(Wanfang)，可同时检索 Google Scholar
英文查询：优先使用 Google Scholar，可同时检索其他英文数据库

学科策略

医学/生物医学/生命科学：优先使用 PubMed（不支持中文query，需翻译为英文）
计算机科学/理工/数学/物理：优先使用 ArXiv（不支持中文query，需翻译为英文）
社科/人文/综合：优先使用 Google Scholar 或万方

重要提醒

PubMed 和 ArXiv 不支持中文检索：如用户使用中文关键词且需检索这两个数据库，必须先将查询词翻译为准确的英文学术术语，再发起检索
可同时检索多个数据库以获取更全面的结果
向用户说明实际使用了哪些数据库进行检索

使用方法

通过 scripts/search.sh 脚本调用API，指定数据源和检索参数：

Track record

Benchmark

12 / 17

test cases passed, vs 7 / 17 without

Adoption

Users: 1
Times used: 42

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

leonchaox / qinyan-academic-skills

skills/%E6%B2%81%E8%A8%80%E5%AD%A6%E6%9C%AFskills/qinyan-paper-search/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.