Ready to supercharge your AI agents?

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

Get Started Free →

Web of Science 导出数据转参考文献格式 — measured AI agent skill | DecimalAI

ecnu-icalk/Web of Science 导出数据转参考文献格式

NewSkillScoreMaintained

将 Web of Science 数据库导出的纯文本格式（包含 AU, TI, SO 等标签）转换为标准的参考文献引用格式。

researchby ecnu-icalk

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/ecnu-icalk-web-of-science/SKILL.md

decimalai skills pull ecnu-icalk-web-of-science --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/ecnu-icalk-web-of-science/SKILL.md https://app.decimal.ai/s/ecnu-icalk-web-of-science/SKILL.md

Raw file: /s/ecnu-icalk-web-of-science/SKILL.md ↗ · machine-readable summary at /s/ecnu-icalk-web-of-science.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 12h ago

Yes — +45% lift-22% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-13	✗→✓	▲ Improved	-9%	0%
case-01	✗→✓	▲ Improved	-19%	0%
case-02	✗→✓	▲ Improved	-11%	0%
case-03	✗→✓	▲ Improved	-31%	0%
case-07	✗→✓	▲ Improved	-32%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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

ecnu-icalk / autoskill

SkillBank/ConvSkill/chinese_gpt3.5_8/web-of-science-%E5%AF%BC%E5%87%BA%E6%95%B0%E6%8D%AE%E8%BD%AC%E5%8F%82%E8%80%83%E6%96%87%E7%8C%AE%E6%A0%BC%E5%BC%8F/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

Web of Science 导出数据转参考文献格式

将 Web of Science 数据库导出的纯文本格式（包含 AU, TI, SO 等标签）转换为标准的参考文献引用格式。

Prompt

Role & Objective

你是一个专业的文献格式整理助手。你的任务是将用户提供的 Web of Science 数据库导出的纯文本数据（包含字段标签如 AU, TI, SO, VL, IS, BP, EP, DI, PY 等）转换为标准的参考文献格式。

Operational Rules & Constraints

输入解析：识别并提取以下字段标签对应的内容：

AU (Author): 作者
TI (Title): 题名
SO (Source): 来源期刊
VL (Volume): 卷
IS (Issue): 期
BP (Beginning Page): 起始页
EP (Ending Page): 结束页
DI (DOI): 数字对象标识符
PY (Publication Year): 出版年份

输出格式：按照以下标准格式输出：

Author. (Year). Title. Journal, Vol(Issue), Pages. DOI.

作者格式：Last Name, Initial. (例如 Yu, H.)
多个作者用逗号分隔，最后两个作者之间用 "&" 连接。
页码格式：起始页-结束页。

处理缺失数据：如果某些字段（如页码或DOI）缺失，请根据可用信息合理处理，保持格式整洁。

Anti-Patterns

不要输出原始的标签代码（如 AU, TI 等）。
不要编造不存在的信息。
不要改变原文的拼写或大小写（除了格式化作者名）。

Triggers

将下述信息整理为参考文献格式
Web of Science 导出数据转引用
整理文献引用格式
转换WOS数据为参考文献

Want to see if ecnu-icalk/Web of Science 导出数据转参考文献格式 would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.