Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《经济问题》(Economic Problems — 山西省社会科学院主管主办的综合性经济理论学术月刊, 1979 年创刊) or deciding whether a Chinese econ/management manuscript fits this venue. Encodes the journal's fit, framing, fee-free policy and review timeline, house style, official-submission re-check, and desk-reject heuristics.
.claude/skills/brycewang-stanford-economic-problems/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 31% | 0% |
《经济问题》由山西省社会科学院主管主办，是综合性经济理论学术月刊，1979 年创刊。覆盖经济学各分支的应用与政策研究——区域经济、财政金融、产业发展、企业经营、能源资源与高质量发展——重学术研究成果，明确不收决策咨询、报告或新闻报导类稿件。相对国内顶刊（《经济研究》《管理世界》），它对选题的区域/政策落点更包容，但仍要求问题清楚、证据扎实、体例规范。
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。
economic-aspects（《经济纵横》） / economic-perspectives（《经济学动态》） / economic-research（《经济研究》） / economic-review-cn（《经济评论》）。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，从官方来源锚点开始核验，并在回答中说明核验日期。理论贡献更强、识别更干净 → economic-research（《经济研究》）/ china-economic-quarterly（《经济学（季刊）》）；纯理论或经济思想史 → economist-cn（《经济学家》）。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《经济问题》 【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/查重/参考文献等> 【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-11 | fail→pass | 27,157 | 20,948 | -23% | 1 | 1 | 0% | 2,612 | 3,422 | +31% | 0 | 0 | — |
case-09 | fail→pass | 22,792 | 24,814 | +9% | 1 | 1 | 0% | 3,102 | 3,711 | +20% | 0 | 0 | — |
case-10 | pass→pass | 13,727 | 6,656 | -52% | 1 | 1 | 0% | 1,223 | 2,333 | +91% | 0 | 0 | — |
case-01 | fail→fail | 25,318 | 18,240 | -28% | 1 | 1 | 0% | 2,810 | 3,186 | +13% | 0 | 0 | — |
case-02 | fail→pass | 26,659 | 19,853 | -26% | 1 | 1 | 0% | 3,835 | 3,296 | -14% | 0 | 0 | — |
case-03 | fail→pass | 27,739 | 17,540 | -37% | 1 | 1 | 0% | 2,722 | 3,344 | +23% | 0 | 0 | — |
case-04 | pass→pass | 14,732 | 12,178 | -17% | 1 | 1 | 0% | 2,185 | 2,966 | +36% | 0 | 0 | — |
case-05 | pass→pass | 24,989 | 22,964 | -8% | 1 | 1 | 0% | 2,400 | 4,085 | +70% | 0 | 0 | — |
case-06 | fail→pass | 23,685 | 22,348 | -6% | 1 | 1 | 0% | 2,743 | 3,597 | +31% | 0 | 0 | — |
case-07 | pass→pass | 31,221 | 25,750 | -18% | 1 | 1 | 0% | 3,222 | 3,704 | +15% | 0 | 0 | — |
case-08 | pass→pass | 26,094 | 15,227 | -42% | 1 | 1 | 0% | 2,867 | 2,696 | -6% | 0 | 0 | — |
case-12 | pass→pass | 24,784 | 18,895 | -24% | 1 | 1 | 0% | 2,450 | 3,449 | +41% | 0 | 0 | — |
case-13 | fail→pass | 24,987 | 23,351 | -7% | 1 | 1 | 0% | 2,867 | 3,961 | +38% | 0 | 0 | — |
case-14 | fail→pass | 24,274 | 19,201 | -21% | 1 | 1 | 0% | 3,256 | 3,148 | -3% | 0 | 0 | — |
case-15 | fail→fail | 24,825 | 25,191 | +1% | 1 | 1 | 0% | 2,802 | 4,096 | +46% | 0 | 0 | — |
case-16 | fail→fail | 18,515 | 17,605 | -5% | 1 | 1 | 0% | 2,028 | 2,916 | +44% | 0 | 0 | — |
case-17 | pass→pass | 28,068 | 28,078 | +0% | 1 | 1 | 0% | 2,903 | 4,110 | +42% | 0 | 0 | — |
case-18 | fail→fail | 32,552 | 27,372 | -16% | 1 | 1 | 0% | 3,131 | 4,328 | +38% | 0 | 0 | — |
case-19 | fail→pass | 18,151 | 13,549 | -25% | 1 | 1 | 0% | 1,935 | 2,460 | +27% | 0 | 0 | — |
case-20 | pass→pass | 16,831 | 18,849 | +12% | 1 | 1 | 0% | 2,304 | 3,734 | +62% | 0 | 0 | — |
case-21 | pass→pass | 23,422 | 20,389 | -13% | 1 | 1 | 0% | 2,175 | 3,669 | +69% | 0 | 0 | — |
case-22 | pass→pass | 30,082 | 28,602 | -5% | 1 | 1 | 0% | 3,173 | 4,503 | +42% | 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 +36 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.