Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →leonchaox/qinyan-nature-writing
面向 Nature、Nature Communications 及同等级综合期刊的证据驱动论文写作技能。用于从已核验的结果、图表、实验记录或中英文草稿构建标题、摘要、引言、结果、方法、讨论、结论和首次投稿材料；也用于重组论文论证、建立 claim–evidence map、控制声称边界和开展投稿前完整性检查。触发场景包括 Nature 写作、论文起草、章节重写、scientific writing、manuscript drafting、abstract、introduction、results narrative、discussion、cover letter、投稿材料。
Passed 20 of 23 test cases with the skill, and 11 of 23 without it.
and 11 more in the full report
10 fixed10 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Here is a CSV file containing raw optical density readings across 4 treatment groups. Please run a two-way ANOVA test, calculate p-values, check normality assumptions, and produce the statistical report.
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to execute statistical calculations or notes statistical design verification is outside drafting scope. | Missed | Passed |
The instructions your model reads when the skill loads.
把论文视为一条可审计的论证链，而不是一组“像顶刊”的句子。先锁定事实和证据，再安排读者路径，最后写作。
qinyan-nature-polishing。qinyan-nature-review。qinyan-nature-statistics。qinyan-nature-figures。从用户材料中提取并明确标注：
Central claim：论文实际证明或支持的核心命题。Evidence set：支撑命题的图、表、实验、模型、数据集和统计结果。Boundary：证据不能支持的外推范围、机制解释或因果结论。Audience：跨领域读者为何应关心，以及专业读者需要看到什么。Terminology ledger：方法、数据集、指标、缩写、符号的唯一标准写法。Unresolved facts：仍需作者确认的事实；统一写为 AUTHOR_INPUT_NEEDED。如果核心命题、关键证据或边界缺失，先给出可继续工作的框架与缺口清单，不补造正文事实。
python scripts/manuscript_audit.py <file>，处理 blocker 与 warning。需要章节级结构时读取 references/section-blueprints.md。需要完整论证与证据映射方法时读取 references/argument-workflow.md。需要首次投稿材料时读取 references/submission-package.md。
test cases passed, vs 11 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.