Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《中国行政管理》(Chinese Public Administration — 国务院办公厅主管、中国行政管理学会主办, 不收版面费/审稿费) or deciding whether a Chinese public-administration/governance manuscript fits this journal. 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-chinese-public-administration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 29% | 0% |
《中国行政管理》由国务院办公厅主管、中国行政管理学会主办，是行政管理与政府治理领域的权威综合性学术月刊。覆盖行政改革、政府职能、政策执行、治理现代化、数字政府、基层治理、法治政府与公共服务等。本刊兼具学术性与决策影响力，设综合性与学术性等不同板块——既要研究问题清楚、机制与证据扎实，也强调对中国治理实践的解释力，而非地方工作总结或纯政策宣传。
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。
chinese-journal-of-management（《管理学报》） / chinese-journal-of-management-science（《中国管理科学》） / chinese-review-of-financial-studies（《金融评论》） / comparative-economic-and-social-systems（《经济社会体制比较》）。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。更强实证、方法更厚的学术公共管理转 journal-of-public-management（《公共管理学报》）；理论评论与案例比较转 china-public-administration-review（《公共管理评论》）；治理实践与基层治理转 governance-studies（《治理研究》）。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《中国行政管理》 【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/板块字数/查重/不收费/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-01 | fail→pass | 27,529 | 20,717 | -25% | 1 | 1 | 0% | 3,055 | 3,708 | +21% | 0 | 0 | — |
case-08 | pass→pass | 32,559 | 18,171 | -44% | 1 | 1 | 0% | 3,267 | 3,097 | -5% | 0 | 0 | — |
case-02 | fail→pass | 29,757 | 21,263 | -29% | 1 | 1 | 0% | 3,451 | 3,580 | +4% | 0 | 0 | — |
case-03 | fail→pass | 132,048 | 18,971 | -86% | 1 | 1 | 0% | 3,633 | 3,891 | +7% | 0 | 0 | — |
case-04 | fail→pass | 27,372 | 25,237 | -8% | 1 | 1 | 0% | 3,260 | 4,170 | +28% | 0 | 0 | — |
case-05 | pass→pass | 28,786 | 18,028 | -37% | 1 | 1 | 0% | 3,170 | 3,762 | +19% | 0 | 0 | — |
case-06 | fail→fail | 27,590 | 25,163 | -9% | 1 | 1 | 0% | 2,697 | 3,895 | +44% | 0 | 0 | — |
case-07 | pass→pass | 29,510 | 23,557 | -20% | 1 | 1 | 0% | 3,056 | 4,123 | +35% | 0 | 0 | — |
case-09 | fail→pass | 23,110 | 18,338 | -21% | 1 | 1 | 0% | 2,448 | 3,168 | +29% | 0 | 0 | — |
case-10 | fail→pass | 20,268 | 12,535 | -38% | 1 | 1 | 0% | 2,627 | 2,990 | +14% | 0 | 0 | — |
case-11 | fail→pass | 26,007 | 18,932 | -27% | 1 | 1 | 0% | 2,735 | 3,321 | +21% | 0 | 0 | — |
case-12 | fail→pass | 26,625 | 20,425 | -23% | 1 | 1 | 0% | 2,541 | 3,684 | +45% | 0 | 0 | — |
case-13 | fail→pass | 25,253 | 24,155 | -4% | 1 | 1 | 0% | 2,962 | 4,003 | +35% | 0 | 0 | — |
case-14 | fail→pass | 33,216 | 19,694 | -41% | 1 | 1 | 0% | 3,335 | 3,808 | +14% | 0 | 0 | — |
case-15 | fail→pass | 23,954 | 19,488 | -19% | 1 | 1 | 0% | 2,353 | 3,287 | +40% | 0 | 0 | — |
case-16 | pass→pass | 14,017 | 10,210 | -27% | 1 | 1 | 0% | 1,204 | 2,106 | +75% | 0 | 0 | — |
case-17 | fail→pass | 26,413 | 18,142 | -31% | 1 | 1 | 0% | 2,564 | 3,608 | +41% | 0 | 0 | — |
case-18 | pass→pass | 27,535 | 25,029 | -9% | 1 | 1 | 0% | 2,959 | 4,191 | +42% | 0 | 0 | — |
case-19 | pass→pass | 19,683 | 23,566 | +20% | 1 | 1 | 0% | 2,311 | 3,783 | +64% | 0 | 0 | — |
case-20 | pass→pass | 31,221 | 27,267 | -13% | 1 | 1 | 0% | 4,027 | 5,332 | +32% | 0 | 0 | — |
case-21 | fail→pass | 13,180 | 11,382 | -14% | 1 | 1 | 0% | 1,404 | 2,598 | +85% | 0 | 0 | — |
case-22 | pass→pass | 28,181 | 20,224 | -28% | 1 | 1 | 0% | 4,962 | 5,030 | +1% | 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 +59 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.