statistical-reporting

仓库创建 2026年7月6日最近提交 21 天前SkillHot 收录 20 天前

▸ 精选理由

确保结论基于合适的统计设计与可重复测量。

这个 Skill 做什么

规范数值结果报告：重复次数、置信区间与配对比较等要素。

把要发表或汇报的数值结果变成靠谱的陈述：要求说明跑了多少次、给出不确定度区间（如 confidence intervals）、在比较方法时用配对比较并写清分母 N。避免把单次随机抽样当结论，强调中心值和分布、重复次数与配对设计的可见性。适合写论文、做结果比对或设计需要多少次运行时用。

▸ 展开 SKILL.md 英文原文

Use when a numeric result is about to be reported, compared, or put in a paper — enforcing replication counts, uncertainty intervals, paired comparisons on matched instances, and visible denominators. Also use when designing how many runs a claim needs. Trigger phrases: "is this difference real", "how many replications", "report with confidence intervals", "single run result", "compare method A vs B", "is N=3 enough".

研究检索统计报告重复次数不确定度通用

Stars

Forks

仓库内 Skill

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/huguryildiz/ALETHEIA/main/skills/extended/statistical-reporting/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/huguryildiz/ALETHEIA/main/skills/extended/statistical-reporting/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# statistical-reporting

**Never report a single run as a result.** A number from one draw of a stochastic system is
an anecdote; a claim is a distribution summarized honestly: center, spread, replication
count, and — for comparisons — a paired design with the pairing stated. This skill governs
how numbers become claims.

## When to use

- A numeric result is entering a build-log entry, a decision's evidence, or a paper draft.
- Designing a campaign: choosing the replication unit and count before launch.
- Comparing methods, configurations, or arms.
- Reviewing a draft for naked point estimates.

## When NOT to use

- Deterministic quantities (an exact count, a closed-form value, a proven bo

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有