Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《电子政务》(E-Government — 中国科学院主管、中国科学院文献情报中心主办, 2004 年创刊) or deciding whether a Chinese digital-government/e-governance manuscript fits this journal. Encodes the journal's fit, framing, abstract/citation house style, multi-stage review, official-submission re-check, and desk-reject heuristics.
.claude/skills/brycewang-stanford-e-government/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 17% | 0% |
《电子政务》由中国科学院主管、中国科学院文献情报中心主办，2004 年创刊，是数字政府与电子政务领域的专业学术刊物。覆盖政务数据与数据治理、数字政府与政务服务数字化、智慧城市、基层治理数字化、平台监管、算法治理、数据要素、隐私安全与公共价值等。与一般公共管理刊相比，本刊更聚焦信息技术与政府治理的交叉，强调技术应用要落到治理机制与公共价值，而非纯技术或纯政策宣传。
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。
contemporary-economy-of-japan（《现代日本经济》） / contemporary-finance-and-economics（《当代财经》） / east-china-economic-management（《华东经济管理》） / economic-aspects（《经济纵横》）。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。公共管理理论与方法更厚的稿转 journal-of-public-management（《公共管理学报》）；信息系统/管理科学方法为核心的转 management-science-cn（《管理科学》）；行政管理与政策实务转 chinese-public-administration（《中国行政管理》）。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《电子政务》 【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/字数/摘要/GB7714参考文献/审稿等> 【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-01 | fail→pass | 31,277 | 22,118 | -29% | 1 | 1 | 0% | 3,739 | 3,762 | +1% | 0 | 0 | — |
case-02 | fail→pass | 36,327 | 20,747 | -43% | 1 | 1 | 0% | 3,865 | 3,630 | -6% | 0 | 0 | — |
case-03 | fail→pass | 28,827 | 20,085 | -30% | 1 | 1 | 0% | 3,312 | 3,610 | +9% | 0 | 0 | — |
case-04 | fail→fail | 29,412 | 23,712 | -19% | 1 | 1 | 0% | 3,181 | 4,056 | +28% | 0 | 0 | — |
case-05 | pass→pass | 27,700 | 23,400 | -16% | 1 | 1 | 0% | 2,721 | 3,806 | +40% | 0 | 0 | — |
case-06 | pass→pass | 30,010 | 35,091 | +17% | 1 | 1 | 0% | 3,239 | 3,916 | +21% | 0 | 0 | — |
case-07 | fail→pass | 27,273 | 12,128 | -56% | 1 | 1 | 0% | 2,908 | 3,632 | +25% | 0 | 0 | — |
case-08 | fail→pass | 26,222 | 16,823 | -36% | 1 | 1 | 0% | 2,933 | 3,426 | +17% | 0 | 0 | — |
case-09 | pass→pass | 28,592 | 17,315 | -39% | 1 | 1 | 0% | 2,904 | 3,404 | +17% | 0 | 0 | — |
case-10 | pass→pass | 31,699 | 20,321 | -36% | 1 | 1 | 0% | 2,420 | 3,472 | +43% | 0 | 0 | — |
case-11 | pass→pass | 27,141 | 14,891 | -45% | 1 | 1 | 0% | 3,146 | 3,915 | +24% | 0 | 0 | — |
case-12 | fail→pass | 30,715 | 21,984 | -28% | 1 | 1 | 0% | 3,253 | 4,307 | +32% | 0 | 0 | — |
case-13 | fail→pass | 25,804 | 18,946 | -27% | 1 | 1 | 0% | 2,894 | 3,960 | +37% | 0 | 0 | — |
case-14 | pass→pass | 28,456 | 18,981 | -33% | 1 | 1 | 0% | 3,087 | 3,267 | +6% | 0 | 0 | — |
case-15 | fail→pass | 29,504 | 20,775 | -30% | 1 | 1 | 0% | 3,327 | 3,658 | +10% | 0 | 0 | — |
case-16 | pass→pass | 20,638 | 20,046 | -3% | 1 | 1 | 0% | 2,597 | 3,966 | +53% | 0 | 0 | — |
case-17 | fail→pass | 31,606 | 25,001 | -21% | 1 | 1 | 0% | 3,587 | 4,134 | +15% | 0 | 0 | — |
case-18 | pass→pass | 19,585 | 15,062 | -23% | 1 | 1 | 0% | 3,026 | 2,909 | -4% | 0 | 0 | — |
case-19 | pass→pass | 27,584 | 16,584 | -40% | 1 | 1 | 0% | 2,850 | 3,492 | +23% | 0 | 0 | — |
case-20 | pass→fail | 22,174 | 27,663 | +25% | 1 | 1 | 0% | 2,579 | 4,764 | +85% | 0 | 0 | — |
case-21 | pass→pass | 19,619 | 17,079 | -13% | 1 | 1 | 0% | 2,443 | 3,786 | +55% | 0 | 0 | — |
case-22 | pass→pass | 20,851 | 25,845 | +24% | 1 | 1 | 0% | 2,354 | 4,832 | +105% | 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. 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.