Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《国际经贸探索》(International Economics and Trade Research — 广东外语外贸大学主办的月刊, CN 44-1302/F) or deciding whether a Chinese trade/open-economy/business manuscript fits this venue. Encodes the journal's fit, 顺序编码制 house style, 粤港澳/开放经济 落点, official re-check, and desk-reject heuristics.
.claude/skills/brycewang-stanford-international-economics-and-trade-research/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 58% | 0% |
《国际经贸探索》由广东外语外贸大学主办（CN 44-1302/F，ISSN 1002-0594，月刊），国际贸易、开放经济与商务实践特色鲜明，对粤港澳大湾区开放、跨境电商、企业国际化等区域/实务落点更包容。相对《国际贸易问题》《世界经济》等顶刊，本刊更欢迎结合广东开放前沿的实证与政策研究，但仍要求识别清楚、口径国际可比。
这个 skill 是定位 / 选刊 / 改写框架工具，不替代该刊最新官方投稿须知。正式投稿前必须重新核对官网、采编系统或编辑部发布的最新模板。
inquiry-into-economic-issues（《经济问题探索》） / international-economic-review-cn（《国际经济评论》） / issues-in-agricultural-economy（《农业经济问题》） / journal-of-agrotechnical-economics（《农业技术经济》）。若这些刊物的读者对象更贴近，不要因为名称、地区或变量相似而强行投本刊。../../resources/source-basis.md 和 ../../resources/official-source-map.md，从其中的官方来源锚点或同一主办/出版体系入口开始核验，并在回答中说明核验日期。顶级国际经济理论转 journal-of-world-economy；国际金融转 studies-of-international-finance。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《国际经贸探索》 【选题标签】<最贴近的 2-3 个主题> 【方法证据】<当前方法是否够本刊标准> 【最大风险】<最可能导致退稿的一点> 【需核验官方要求】<投稿系统/匿名/摘要/图表/数据等> 【改投建议】<若不匹配，给出更合适期刊>
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 27,930 | 17,887 | -36% | 1 | 1 | 0% | 3,144 | 3,938 | +25% | 0 | 0 | — |
case-07 | fail→pass | 24,976 | 22,131 | -11% | 1 | 1 | 0% | 2,786 | 3,851 | +38% | 0 | 0 | — |
case-01 | fail→fail | 26,251 | 22,580 | -14% | 1 | 1 | 0% | 3,245 | 3,747 | +15% | 0 | 0 | — |
case-02 | fail→fail | 35,662 | 25,625 | -28% | 1 | 1 | 0% | 3,512 | 4,274 | +22% | 0 | 0 | — |
case-03 | fail→fail | 34,797 | 21,222 | -39% | 1 | 1 | 0% | 3,348 | 3,898 | +16% | 0 | 0 | — |
case-04 | fail→pass | 25,640 | 20,941 | -18% | 1 | 1 | 0% | 2,979 | 3,866 | +30% | 0 | 0 | — |
case-05 | fail→pass | 25,177 | 19,143 | -24% | 1 | 1 | 0% | 2,902 | 3,391 | +17% | 0 | 0 | — |
case-08 | pass→pass | 23,695 | 16,770 | -29% | 1 | 1 | 0% | 2,361 | 3,215 | +36% | 0 | 0 | — |
case-09 | fail→pass | 17,858 | 18,954 | +6% | 1 | 1 | 0% | 2,265 | 3,583 | +58% | 0 | 0 | — |
case-10 | fail→pass | 35,672 | 27,038 | -24% | 1 | 1 | 0% | 3,874 | 4,601 | +19% | 0 | 0 | — |
case-11 | fail→pass | 30,598 | 25,867 | -15% | 1 | 1 | 0% | 3,227 | 4,549 | +41% | 0 | 0 | — |
case-12 | fail→pass | 25,030 | 25,543 | +2% | 1 | 1 | 0% | 2,531 | 4,011 | +58% | 0 | 0 | — |
case-13 | fail→pass | 21,579 | 14,570 | -32% | 1 | 1 | 0% | 2,404 | 3,408 | +42% | 0 | 0 | — |
case-14 | fail→pass | 35,633 | 20,516 | -42% | 1 | 1 | 0% | 3,838 | 4,470 | +16% | 0 | 0 | — |
case-15 | fail→pass | 24,252 | 22,078 | -9% | 1 | 1 | 0% | 2,964 | 3,946 | +33% | 0 | 0 | — |
case-16 | fail→pass | 30,439 | 21,968 | -28% | 1 | 1 | 0% | 3,299 | 4,082 | +24% | 0 | 0 | — |
case-17 | fail→fail | 28,649 | 14,854 | -48% | 1 | 1 | 0% | 3,456 | 3,001 | -13% | 0 | 0 | — |
case-18 | fail→pass | 24,356 | 24,468 | +0% | 1 | 1 | 0% | 2,573 | 4,452 | +73% | 0 | 0 | — |
case-19 | pass→pass | 32,853 | 27,388 | -17% | 1 | 1 | 0% | 3,494 | 4,932 | +41% | 0 | 0 | — |
case-20 | pass→fail | 25,000 | 28,254 | +13% | 1 | 1 | 0% | 3,586 | 4,978 | +39% | 0 | 0 | — |
case-21 | pass→pass | 25,346 | 24,805 | -2% | 1 | 1 | 0% | 2,919 | 4,787 | +64% | 0 | 0 | — |
case-22 | fail→pass | 21,363 | 18,915 | -11% | 1 | 1 | 0% | 2,660 | 3,460 | +30% | 0 | 0 | — |
case-23 | fail→fail | 20,901 | 25,562 | +22% | 1 | 1 | 0% | 2,503 | 3,990 | +59% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +57 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.