audit-reproducibility

仓库创建 2026年2月7日最近提交 1 个月前SkillHot 收录 20 天前
▸ 精选理由

在投稿或发布前快速发现与修正数值不一致问题。

▸ 风险提示

需要访问原始数据和分析代码,可能涉及敏感数据。

这个 Skill 做什么

核对论文数值声明与分析产出的一致性并给出通过/未通过结论。

把论文里写的数值(点估计、标准误、p 值、计数等)和实际的 R/Stata/Python 分析输出逐条比对,按预设容差给每条声明标注 PASS/FAIL。常在投稿前或要发布复现包前跑一遍,能快速定位不一致或可疑数值,节省人工反复核对的时间。特别会遵循 .claude/rules/replication-protocol.md 的容差规则,输出逐条可审计的结论和差异报告,方便修订和复现。

▸ 展开 SKILL.md 英文原文

Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.

研究检索可重复性审计数值核对通用
1.4k
Stars
2.8k
Forks
40
仓库内 Skill
+59
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/pedrohcgs/claude-code-my-workflow/main/.claude/skills/audit-reproducibility/SKILL.md
或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/pedrohcgs/claude-code-my-workflow/main/.claude/skills/audit-reproducibility/SKILL.md"
SKILL.MD 节选查看完整文件 ↗
# Audit Reproducibility

Compare numeric claims in a manuscript (point estimates, standard errors, p-values, counts) against the actual outputs produced by the analysis pipeline. Report PASS / FAIL per claim against the tolerance thresholds defined in [`.claude/rules/replication-protocol.md`](../../rules/replication-protocol.md).

**Core principle:** If the paper says `ATT = -1.632 (0.584)` and the code produces `-1.628 (0.591)`, we verify — **numerically** — that the difference is within the documented tolerance. No more "looks close enough" eyeballing.

## When to use

- **Before submission.** Catches the "I updated the analysis but forgot to update Table 2" bug.
- **Before releasing a rep
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有