Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《经济纵横》(Economic Review Journal — 吉林省社会科学院/社科联主办的综合性经济理论月刊, 1985 年创刊, 不收版面费/审稿费) or deciding whether a Chinese econ/policy manuscript fits this venue. Encodes the journal's fit, framing, fee-free policy, abstract/keyword house style, official-submission re-check, and desk-reject heuristics.
.claude/skills/brycewang-stanford-economic-aspects/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 49% | 0% |
《经济纵横》由吉林省社会科学院、吉林省社会科学界联合会主办，是综合性经济理论月刊，1985 年创刊（ISSN 1007-7685）。适合宏观经济形势、改革开放、产业政策、区域经济、共同富裕、数字经济与绿色转型的学术化分析。偏好观点鲜明、论证规范的中短篇，明确区别于政策宣传或经验汇报。
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。
e-government（《电子政务》） / east-china-economic-management（《华东经济管理》） / economic-perspectives（《经济学动态》） / economic-problems（《经济问题》）。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。严格实证转 economic-review-cn；制度比较转 comparative-economic-and-social-systems。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《经济纵横》 【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-22 | fail→pass | 26,105 | 15,697 | -40% | 1 | 1 | 0% | 2,701 | 3,117 | +15% | 0 | 0 | — |
case-01 | fail→pass | 30,200 | 20,324 | -33% | 1 | 1 | 0% | 3,454 | 3,789 | +10% | 0 | 0 | — |
case-02 | fail→pass | 26,612 | 15,589 | -41% | 1 | 1 | 0% | 2,970 | 3,059 | +3% | 0 | 0 | — |
case-03 | fail→pass | 30,121 | 15,858 | -47% | 1 | 1 | 0% | 3,231 | 3,161 | -2% | 0 | 0 | — |
case-04 | pass→pass | 24,161 | 25,419 | +5% | 1 | 1 | 0% | 2,897 | 4,480 | +55% | 0 | 0 | — |
case-05 | pass→pass | 28,779 | 27,525 | -4% | 1 | 1 | 0% | 2,871 | 4,329 | +51% | 0 | 0 | — |
case-06 | fail→fail | 14,638 | 10,444 | -29% | 1 | 1 | 0% | 1,513 | 2,000 | +32% | 0 | 0 | — |
case-07 | fail→pass | 17,653 | 17,295 | -2% | 1 | 1 | 0% | 1,989 | 2,959 | +49% | 0 | 0 | — |
case-08 | fail→pass | 24,506 | 24,320 | -1% | 1 | 1 | 0% | 3,058 | 3,909 | +28% | 0 | 0 | — |
case-09 | fail→pass | 30,862 | 22,249 | -28% | 1 | 1 | 0% | 3,125 | 3,794 | +21% | 0 | 0 | — |
case-10 | fail→pass | 24,426 | 19,156 | -22% | 1 | 1 | 0% | 2,773 | 3,118 | +12% | 0 | 0 | — |
case-11 | fail→pass | 25,730 | 18,576 | -28% | 1 | 1 | 0% | 2,388 | 3,116 | +30% | 0 | 0 | — |
case-12 | fail→pass | 21,092 | 19,968 | -5% | 1 | 1 | 0% | 2,769 | 4,063 | +47% | 0 | 0 | — |
case-13 | pass→pass | 26,156 | 18,226 | -30% | 1 | 1 | 0% | 2,468 | 3,310 | +34% | 0 | 0 | — |
case-14 | fail→pass | 26,531 | 20,289 | -24% | 1 | 1 | 0% | 3,125 | 3,377 | +8% | 0 | 0 | — |
case-15 | fail→pass | 24,014 | 23,021 | -4% | 1 | 1 | 0% | 2,282 | 3,764 | +65% | 0 | 0 | — |
case-16 | pass→pass | 25,980 | 15,982 | -38% | 1 | 1 | 0% | 2,547 | 3,207 | +26% | 0 | 0 | — |
case-17 | fail→pass | 31,694 | 26,511 | -16% | 1 | 1 | 0% | 3,204 | 3,987 | +24% | 0 | 0 | — |
case-18 | fail→pass | 25,203 | 16,748 | -34% | 1 | 1 | 0% | 2,368 | 3,603 | +52% | 0 | 0 | — |
case-19 | fail→pass | 27,354 | 17,134 | -37% | 1 | 1 | 0% | 2,762 | 3,398 | +23% | 0 | 0 | — |
case-20 | fail→fail | 27,464 | 27,975 | +2% | 1 | 1 | 0% | 2,837 | 4,249 | +50% | 0 | 0 | — |
case-21 | pass→pass | 29,061 | 26,407 | -9% | 1 | 1 | 0% | 2,895 | 4,340 | +50% | 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. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.