Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when targeting 《中国农村观察》(China Rural Survey — 中国社会科学院农村发展研究所主办的三农双月刊, CN11-3586/F, 双向匿名、零审稿/版面费, 需中英文摘要) or deciding whether a Chinese 三农 manuscript fits this venue. Encodes the journal's fit, framing, fee-free anonymous-review policy, abstract/keyword/citation house style, official-submission re-check, and desk-reject heuristics.
.claude/skills/brycewang-stanford-china-rural-survey/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 28% | 0% |
《中国农村观察》由中国社会科学院农村发展研究所主办，是三农领域的双月刊（CN 11-3586/F，ISSN 1006-4583）。主发表关于农业、农村和农民问题的学术论文，研究范围横跨农村经济、政治、社会、法律、文化、教育等多领域，强调原创性、思想性、前瞻性与方向性，以创新性为首要考量。它与同所主办的姊妹刊《中国农村经济》(china-rural-economy) 形成分工：本刊更偏制度调查、农村社会与多学科观察，《中国农村经济》更偏经济学实证与政策机制。
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。
china-public-administration-review（《公共管理评论》） / china-rural-economy（《中国农村经济》） / china-soft-science（《中国软科学》） / chinese-journal-of-management（《管理学报》）。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。更纯经济计量、政策机制实证转 china-rural-economy（《中国农村经济》）；农业技术效率转 journal-of-agrotechnical-economics（《农业技术经济》）；综合农业政策转 issues-in-agricultural-economy（《农业经济问题》）。
text【匹配度】高 / 中 / 低（一句话理由） 【目标期刊】《中国农村观察》 【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/中英文摘要/数据代码公开/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 | 25,644 | 20,660 | -19% | 1 | 1 | 0% | 3,066 | 3,973 | +30% | 0 | 0 | — |
case-02 | fail→pass | 23,119 | 18,228 | -21% | 1 | 1 | 0% | 2,868 | 3,589 | +25% | 0 | 0 | — |
case-03 | fail→pass | 34,226 | 20,506 | -40% | 1 | 1 | 0% | 3,822 | 3,957 | +4% | 0 | 0 | — |
case-04 | pass→pass | 35,974 | 41,891 | +16% | 1 | 1 | 0% | 4,307 | 6,447 | +50% | 0 | 0 | — |
case-05 | pass→fail | 24,660 | 30,205 | +22% | 1 | 1 | 0% | 2,368 | 5,557 | +135% | 0 | 0 | — |
case-06 | pass→fail | 27,947 | 32,124 | +15% | 1 | 1 | 0% | 3,366 | 5,102 | +52% | 0 | 0 | — |
case-07 | pass→pass | 29,313 | 28,484 | -3% | 1 | 1 | 0% | 3,311 | 4,487 | +36% | 0 | 0 | — |
case-08 | fail→pass | 26,353 | 20,742 | -21% | 1 | 1 | 0% | 2,911 | 3,567 | +23% | 0 | 0 | — |
case-09 | fail→pass | 29,542 | 19,559 | -34% | 1 | 1 | 0% | 3,012 | 3,866 | +28% | 0 | 0 | — |
case-10 | pass→pass | 26,898 | 16,466 | -39% | 1 | 1 | 0% | 2,995 | 3,336 | +11% | 0 | 0 | — |
case-11 | pass→pass | 14,091 | 17,494 | +24% | 1 | 1 | 0% | 2,036 | 3,351 | +65% | 0 | 0 | — |
case-12 | pass→pass | 23,325 | 15,366 | -34% | 1 | 1 | 0% | 2,553 | 3,291 | +29% | 0 | 0 | — |
case-13 | fail→pass | 25,125 | 16,249 | -35% | 1 | 1 | 0% | 3,072 | 3,512 | +14% | 0 | 0 | — |
case-14 | fail→pass | 24,650 | 14,627 | -41% | 1 | 1 | 0% | 2,701 | 3,922 | +45% | 0 | 0 | — |
case-15 | fail→pass | 23,307 | 24,998 | +7% | 1 | 1 | 0% | 2,189 | 4,264 | +95% | 0 | 0 | — |
case-16 | pass→pass | 17,642 | 12,540 | -29% | 1 | 1 | 0% | 1,579 | 3,234 | +105% | 0 | 0 | — |
case-22 | pass→pass | 21,929 | 11,274 | -49% | 1 | 1 | 0% | 2,282 | 2,619 | +15% | 0 | 0 | — |
case-17 | fail→pass | 29,793 | 14,913 | -50% | 1 | 1 | 0% | 3,266 | 3,140 | -4% | 0 | 0 | — |
case-18 | fail→pass | 24,240 | 19,978 | -18% | 1 | 1 | 0% | 2,347 | 3,522 | +50% | 0 | 0 | — |
case-19 | fail→pass | 23,106 | 19,037 | -18% | 1 | 1 | 0% | 2,688 | 3,557 | +32% | 0 | 0 | — |
case-20 | fail→pass | 21,502 | 18,313 | -15% | 1 | 1 | 0% | 2,287 | 3,809 | +67% | 0 | 0 | — |
case-21 | fail→pass | 24,838 | 11,113 | -55% | 1 | 1 | 0% | 2,848 | 3,297 | +16% | 0 | 0 | — |
case-23 | fail→pass | 26,208 | 15,668 | -40% | 1 | 1 | 0% | 2,916 | 4,051 | +39% | 0 | 0 | — |
case-24 | fail→pass | 35,228 | 23,489 | -33% | 1 | 1 | 0% | 3,824 | 4,566 | +19% | 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 +54 percentage points is the difference between those two pass rates over the 24 comparable cases. 2 cases got worse with the skill loaded, and they are 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.