Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《经济研究》(Economic Research Journal) or deciding whether a Chinese social-science/econ/management manuscript fits this journal. Applies the journal's fit, framing, method, house-style, official-submission-check, and desk-reject heuristics.
.claude/skills/brycewang-stanford-economic-research/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 39% | 0% |
中国经济学综合旗舰期刊，完整生命周期支持已在 Economic-Research-Journal-Skills 中实现。这里提供目标 pack 内的快速触发和改投判断。
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。
er-* 生命周期 skill；本 skill 只做选刊与快速定位economic-perspectives（《经济学动态》） / economic-problems（《经济问题》） / economic-review-cn（《经济评论》） / economic-science（《经济科学》）。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。Economic-Research-Journal-Skills/skills/er-workflow若需要逐步写作/投稿检查，使用 er-workflow；若实践政策更强，转 management-world。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《经济研究》 【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-24 | pass→pass | 24,523 | 16,629 | -32% | 1 | 1 | 0% | 2,425 | 2,724 | +12% | 0 | 0 | — |
case-01 | fail→fail | 24,244 | 61,028 | +152% | 1 | 1 | 0% | 3,390 | 4,111 | +21% | 0 | 0 | — |
case-02 | pass→pass | 44,116 | 28,202 | -36% | 1 | 1 | 0% | 4,918 | 4,958 | +1% | 0 | 0 | — |
case-03 | pass→pass | 27,047 | 30,654 | +13% | 1 | 1 | 0% | 3,951 | 4,578 | +16% | 0 | 0 | — |
case-04 | pass→pass | 18,879 | 22,468 | +19% | 1 | 1 | 0% | 2,905 | 3,779 | +30% | 0 | 0 | — |
case-05 | fail→fail | 28,590 | 24,509 | -14% | 1 | 1 | 0% | 3,329 | 3,490 | +5% | 0 | 0 | — |
case-06 | fail→pass | 21,904 | 20,295 | -7% | 1 | 1 | 0% | 3,378 | 3,411 | +1% | 0 | 0 | — |
case-07 | fail→fail | 30,901 | 25,020 | -19% | 1 | 1 | 0% | 3,736 | 3,576 | -4% | 0 | 0 | — |
case-08 | fail→fail | 26,571 | 18,816 | -29% | 1 | 1 | 0% | 2,824 | 3,067 | +9% | 0 | 0 | — |
case-09 | pass→pass | 28,628 | 18,086 | -37% | 1 | 1 | 0% | 2,941 | 3,007 | +2% | 0 | 0 | — |
case-10 | pass→pass | 27,942 | 23,915 | -14% | 1 | 1 | 0% | 3,326 | 3,870 | +16% | 0 | 0 | — |
case-11 | fail→pass | 24,724 | 17,611 | -29% | 1 | 1 | 0% | 2,682 | 2,935 | +9% | 0 | 0 | — |
case-12 | fail→pass | 23,641 | 27,668 | +17% | 1 | 1 | 0% | 3,459 | 4,317 | +25% | 0 | 0 | — |
case-13 | pass→pass | 30,346 | 20,016 | -34% | 1 | 1 | 0% | 2,690 | 3,281 | +22% | 0 | 0 | — |
case-14 | fail→fail | 23,676 | 25,727 | +9% | 1 | 1 | 0% | 3,667 | 4,297 | +17% | 0 | 0 | — |
case-15 | fail→pass | 27,795 | 16,095 | -42% | 1 | 1 | 0% | 3,239 | 3,200 | -1% | 0 | 0 | — |
case-16 | fail→pass | 25,928 | 37,449 | +44% | 1 | 1 | 0% | 3,127 | 4,337 | +39% | 0 | 0 | — |
case-17 | pass→pass | 28,249 | 30,919 | +9% | 1 | 1 | 0% | 3,026 | 4,296 | +42% | 0 | 0 | — |
case-18 | fail→pass | 26,940 | 22,578 | -16% | 1 | 1 | 0% | 2,652 | 3,622 | +37% | 0 | 0 | — |
case-19 | fail→pass | 29,579 | 21,437 | -28% | 1 | 1 | 0% | 3,577 | 3,541 | -1% | 0 | 0 | — |
case-20 | pass→pass | 26,319 | 20,640 | -22% | 1 | 1 | 0% | 2,760 | 3,555 | +29% | 0 | 0 | — |
case-21 | pass→pass | 27,723 | 12,608 | -55% | 1 | 1 | 0% | 3,193 | 2,998 | -6% | 0 | 0 | — |
case-22 | fail→pass | 28,335 | 26,073 | -8% | 1 | 1 | 0% | 3,829 | 4,179 | +9% | 0 | 0 | — |
case-23 | fail→pass | 25,832 | 16,023 | -38% | 1 | 1 | 0% | 2,801 | 3,000 | +7% | 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. 24 cases were attempted. The headline lift of +38 percentage points is the difference between those two pass rates over the 24 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.