PulseAugur
中
实时 05:34:55
English(EN) When a Claude Code skill's reference.md and scripts actually load (the 'executed, not loaded' script was read in 13 of 16 runs)

Claude Code 的脚本加载行为与文档不符

最近对 Claude Code 的一项分析显示,在 16 次运行中有 13 次成功将技能捆绑的脚本加载到上下文中,这与文档中建议的脚本在不加载的情况下执行的说法相悖。研究还发现,当在 SKILL.md 中引用时,诸如 reference.md 之类的参考文件,无论大小如何,都会被一致地加载到模型的上下文中。这与文档中关于额外文件在需要之前不产生任何成本且脚本被运行而非读取的行为相矛盾。 AI

影响 阐明了 Claude Code 捆绑文件的实际上下文加载行为,影响了开发人员构建其技能的方式。

排序理由 对产品内特定功能的行为进行分析。

在 dev.to — Claude Code tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Claude Code 的脚本加载行为与文档不符

本文如何被排名

Signal score
14 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
对产品内特定功能的行为进行分析。
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — Claude Code tag TIER_1 English(EN) · Rulestack ·

    当 Claude 代码技能的 reference.md 和脚本实际加载时(“已执行但未加载”的脚本在 16 次运行中有 13 次被读取)

    <blockquote> <p>13 of 16 Claude Code runs that executed a skill's bundled <code>scripts/check-entry.sh</code> also loaded its source into context, with <code>Read</code> or <code>cat</code>, although the skills docs label such a script "executed, not loaded". The rest held as doc…