Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when a 《中国农村经济》 manuscript is at the topic-selection stage and the 三农 scope fit, theoretical grounding, marginal-contribution sentences, or venue match are unsettled. Produces the contribution-sentence template and the 三农-fit checklist. 本技能服务于《中国农村经济》(China Rural Economy, CRE)。
.claude/skills/brycewang-stanford-cre-topic-selection/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 34% | 0% |
《中国农村经济》对选题的硬约束：
本刊关注的主流议题（用来判断"是否对口"）：
如果选题在上述清单里找不到落点，多半不对口本刊。
写完一句话摘要后，逐条自检：
少于 3 个 yes → 选题深度不够，回到三农理论文献再读两轮。
本文的边际贡献主要体现在以下四个方面：
第一，[理论维度]——本文将……纳入[农户行为 / 土地制度 / 农村金融等理论框架]，区别于[已有研究]……。
第二，[识别策略维度]——本文利用[农村政策 / 制度冲击]构造……，缓解了农户自选择（如入社 / 外出务工）带来的内生性问题。
第三，[机制维度]——本文揭示了农户层面的……机制，回答了已有文献"知其然不知其所以然"的问题。
第四，[政策意义维度]——本文为理解[乡村振兴 / 粮食安全 / 共同富裕等议题]提供了……微观证据。四条都齐才算合格。少于四条 → 选题深度不够。
| | 中国农村经济 | 中国农村观察 | 综合经济学期刊 | |----------|--------|--------|------------| | 学科 | 农业 / 农村经济（实证为主） | 三农（含质性 / 案例 / 政策观察） | 一般经济学 | | 三农场景 | 必备 | 必备 | 不要求 | | 因果识别 | 高门槛 | 较包容 | 高门槛 | | 案例 / 质性 | 较少 | 接受 | 较少 | | 政策含义 | 意义层（落到三农） | 意义层 / 观察 | 意义层 |
如果稿子脱离三农场景，不要投《中国农村经济》；偏质性 / 案例可考虑《中国农村观察》。
【三农场景契合】高 / 中 / 低（落在哪个议题）
【理论贡献评分】X / 4
【边际贡献四句】（草稿）
1. ...
2. ...
3. ...
4. ...
【期刊匹配建议】中国农村经济 / 中国农村观察 / 其他
【下一步】cre-literature-review| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 32,395 | 25,153 | -22% | 1 | 1 | 0% | 4,074 | 4,195 | +3% | 0 | 0 | — |
case-02 | fail→pass | 35,749 | 22,669 | -37% | 1 | 1 | 0% | 3,911 | 3,885 | -1% | 0 | 0 | — |
case-03 | fail→pass | 29,544 | 22,330 | -24% | 1 | 1 | 0% | 3,613 | 3,418 | -5% | 0 | 0 | — |
case-04 | pass→pass | 22,660 | 19,055 | -16% | 1 | 1 | 0% | 2,667 | 3,117 | +17% | 0 | 0 | — |
case-20 | pass→pass | 16,165 | 14,290 | -12% | 1 | 1 | 0% | 2,369 | 3,088 | +30% | 0 | 0 | — |
case-05 | pass→pass | 22,734 | 19,262 | -15% | 1 | 1 | 0% | 2,709 | 3,346 | +24% | 0 | 0 | — |
case-06 | pass→pass | 23,351 | 17,259 | -26% | 1 | 1 | 0% | 2,760 | 3,689 | +34% | 0 | 0 | — |
case-07 | pass→pass | 29,750 | 19,769 | -34% | 1 | 1 | 0% | 3,133 | 3,456 | +10% | 0 | 0 | — |
case-08 | fail→pass | 29,221 | 13,184 | -55% | 1 | 1 | 0% | 3,680 | 3,082 | -16% | 0 | 0 | — |
case-09 | fail→pass | 16,502 | 18,881 | +14% | 1 | 1 | 0% | 2,535 | 3,398 | +34% | 0 | 0 | — |
case-10 | pass→pass | 28,720 | 18,897 | -34% | 1 | 1 | 0% | 3,066 | 3,277 | +7% | 0 | 0 | — |
case-11 | pass→pass | 21,137 | 30,050 | +42% | 1 | 1 | 0% | 3,504 | 4,384 | +25% | 0 | 0 | — |
case-12 | pass→pass | 24,697 | 17,531 | -29% | 1 | 1 | 0% | 2,721 | 3,379 | +24% | 0 | 0 | — |
case-13 | pass→pass | 28,763 | 27,707 | -4% | 1 | 1 | 0% | 3,403 | 4,372 | +28% | 0 | 0 | — |
case-14 | fail→fail | 31,923 | 22,289 | -30% | 1 | 1 | 0% | 3,427 | 4,070 | +19% | 0 | 0 | — |
case-15 | fail→pass | 27,634 | 18,256 | -34% | 1 | 1 | 0% | 3,159 | 3,189 | +1% | 0 | 0 | — |
case-16 | pass→pass | 18,629 | 13,759 | -26% | 1 | 1 | 0% | 2,401 | 3,151 | +31% | 0 | 0 | — |
case-17 | pass→pass | 17,962 | 13,610 | -24% | 1 | 1 | 0% | 2,780 | 3,168 | +14% | 0 | 0 | — |
case-18 | pass→pass | 18,718 | 9,965 | -47% | 1 | 1 | 0% | 2,151 | 2,661 | +24% | 0 | 0 | — |
case-19 | fail→fail | 21,442 | 15,092 | -30% | 1 | 1 | 0% | 2,773 | 3,298 | +19% | 0 | 0 | — |
case-21 | fail→pass | 28,139 | 22,132 | -21% | 1 | 1 | 0% | 3,816 | 4,249 | +11% | 0 | 0 | — |
case-22 | fail→pass | 23,441 | 10,786 | -54% | 1 | 1 | 0% | 2,828 | 2,820 | -0% | 0 | 0 | — |
case-23 | pass→pass | 26,881 | 31,872 | +19% | 1 | 1 | 0% | 3,963 | 5,696 | +44% | 0 | 0 | — |
case-24 | pass→fail | 12,011 | 16,608 | +38% | 1 | 1 | 0% | 1,548 | 3,462 | +124% | 0 | 0 | — |
case-25 | pass→pass | 18,964 | 23,388 | +23% | 1 | 1 | 0% | 3,017 | 4,320 | +43% | 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. 25 cases were attempted. The headline lift of +28 percentage points is the difference between those two pass rates over the 25 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.