PulseAugur
中
实时 04:10:41
English(EN) With 160 skills installed, Claude Code kept 20 descriptions, and the model found 0 of 3 skills that lost theirs

Claude Code的技能描述预算被揭示为上下文窗口的1%

最近对Claude Code 2.1.289和Opus 5.5模型的实验显示,该系统的技能描述预算是上下文窗口的1%,而不是文档中先前说明的2%。当超出此预算时,Claude Code会丢弃不常调用的技能的描述,从而影响模型自主选择它们的能力。实验发现,虽然技能名称得以保留,但模型未能调用仅列出名称的技能,这与其有描述的技能的成功率形成对比。 AI

影响 阐明了Claude Code技能调用的局限性,可能影响开发者的工作流程和模型的自主性。

排序理由 对特定产品行为和文档差异的分析。

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的技能描述预算被揭示为上下文窗口的1%

本文如何被排名

Signal score
33 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
对特定产品行为和文档差异的分析。
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, model release
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 ·

    安装了160项技能后,Claude Code保留了20项描述,模型未找到3项失去技能的技能

    <blockquote> <p>With Opus 5.5's 1M-token window, Claude Code 2.1.289 held the skill listing to 30,000 characters. Of 160 project skills with 1,000-character descriptions, 20 kept their descriptions (22 of 40, 21 of 80) and every name stayed, but the model invoked 0 of 3 target sk…