Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when running the final pre-submission preflight for 《中国农村经济》 — format, word count, double-blind, references, anti-plagiarism, author info, and supplementary files. 本技能服务于《中国农村经济》(China Rural Economy, CRE)。
.claude/skills/brycewang-stanford-cre-submission/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 63% | 0% |
> 准确性提示：本刊的确切字数、参考文献条数、图表数量等限制会随年度调整。下方给出的是惯常规范与量级，投稿前请务必到《中国农村经济》官网"投稿须知"核对当年的具体数字。
【字数】正文 X / 摘要 X
【双盲合规】通过 / 待修改：[...]
【参考文献条数】中文 X / 英文 Y
【数据来源点名】是 / 否
【三农文献对话】到位 / 缺位
【查重率】X%
【附件齐全】是 / 否
【下一步】等待外审 / 收到 R&R → cre-rebuttaltemplates/manuscript_template.md — 标准稿件结构骨架（中英摘要、变量定义表、参考文献格式）templates/checklist.md — 投稿前 8 类自检清单（格式 / 作者信息 / 摘要 / 结构 / 内容 / 图表 / 文献 / 系统）../../resources/external_tools.md — 三农数据资源（CFPS / CHFS / CLDS / 农村固定观察点 / 农业农村部统计等）与统计软件包速查| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 34,202 | 35,013 | +2% | 1 | 1 | 0% | 4,409 | 5,210 | +18% | 0 | 0 | — |
case-02 | fail→pass | 28,954 | 22,855 | -21% | 1 | 1 | 0% | 3,621 | 4,213 | +16% | 0 | 0 | — |
case-03 | fail→pass | 33,256 | 29,391 | -12% | 1 | 1 | 0% | 4,356 | 4,917 | +13% | 0 | 0 | — |
case-04 | pass→pass | 14,682 | 19,056 | +30% | 1 | 1 | 0% | 1,794 | 3,437 | +92% | 0 | 0 | — |
case-05 | pass→pass | 15,073 | 20,497 | +36% | 1 | 1 | 0% | 1,955 | 3,525 | +80% | 0 | 0 | — |
case-06 | pass→pass | 19,857 | 16,738 | -16% | 1 | 1 | 0% | 2,144 | 3,048 | +42% | 0 | 0 | — |
case-07 | pass→pass | 22,616 | 18,406 | -19% | 1 | 1 | 0% | 2,669 | 4,144 | +55% | 0 | 0 | — |
case-08 | pass→pass | 13,313 | 12,463 | -6% | 1 | 1 | 0% | 1,955 | 3,005 | +54% | 0 | 0 | — |
case-09 | pass→pass | 19,268 | 19,358 | +0% | 1 | 1 | 0% | 2,566 | 3,498 | +36% | 0 | 0 | — |
case-10 | fail→pass | 20,622 | 24,207 | +17% | 1 | 1 | 0% | 2,497 | 3,952 | +58% | 0 | 0 | — |
case-11 | pass→pass | 19,384 | 11,219 | -42% | 1 | 1 | 0% | 1,905 | 2,902 | +52% | 0 | 0 | — |
case-12 | fail→pass | 17,321 | 17,523 | +1% | 1 | 1 | 0% | 2,519 | 4,095 | +63% | 0 | 0 | — |
case-13 | pass→pass | 17,924 | 18,374 | +3% | 1 | 1 | 0% | 2,159 | 3,767 | +74% | 0 | 0 | — |
case-14 | pass→pass | 20,232 | 21,256 | +5% | 1 | 1 | 0% | 2,190 | 3,741 | +71% | 0 | 0 | — |
case-15 | pass→pass | 25,961 | 20,246 | -22% | 1 | 1 | 0% | 2,899 | 4,013 | +38% | 0 | 0 | — |
case-16 | fail→fail | 24,712 | 23,173 | -6% | 1 | 1 | 0% | 2,499 | 3,730 | +49% | 0 | 0 | — |
case-17 | pass→pass | 9,844 | 8,995 | -9% | 1 | 1 | 0% | 665 | 1,828 | +175% | 0 | 0 | — |
case-18 | fail→pass | 25,278 | 21,873 | -13% | 1 | 1 | 0% | 2,709 | 4,405 | +63% | 0 | 0 | — |
case-19 | pass→pass | 13,290 | 18,299 | +38% | 1 | 1 | 0% | 2,020 | 3,374 | +67% | 0 | 0 | — |
case-20 | pass→pass | 25,452 | 25,791 | +1% | 1 | 1 | 0% | 2,736 | 4,482 | +64% | 0 | 0 | — |
case-21 | pass→pass | 14,676 | 13,666 | -7% | 1 | 1 | 0% | 1,954 | 3,304 | +69% | 0 | 0 | — |
case-22 | pass→pass | 25,921 | 39,734 | +53% | 1 | 1 | 0% | 3,172 | 5,612 | +77% | 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 +27 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.