PulseAugur
实时 21:43:21
English(EN) Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No-Plugin Baseline, and a CI Gate for Skills

Anthropic 推出 Claude Code 插件评估工作流

Anthropic 推出了其 Claude Code 工具的新评估工作流,旨在帮助开发人员测试和衡量插件的有效性。该系统名为 `claude plugin eval`,将插件与实际提示进行运行并对输出进行评分,将其与未使用插件的基线进行比较。它专门解决了插件技能是否被触发、在编辑或模型更新后是否保持功能以及是否优于裸模型的问题。该工作流包括六种评分器类型,其中四种是免费的,两种需要调用 judge model,并提供了一个清晰的指标 (Δ) 来量化插件的贡献。 AI

影响 增强了 LLM 插件集成的开发人员工具,可能加快开发周期。

排序理由 这是现有产品的新功能/工作流,而不是核心模型发布或研究论文。

在 MarkTechPost 阅读 →

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

Anthropic 推出 Claude Code 插件评估工作流

本文如何被排名

Signal score
59 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是现有产品的新功能/工作流,而不是核心模型发布或研究论文。
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
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. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Anthropic 为 Claude 代码添加插件评估:6 种评分器类型、无插件基线和技能 CI 门禁

    <p>Anthropic has published a new plugin evals workflow for Claude Code. The claude plugin eval command runs a plugin against realistic prompts, grades what Claude produced, and compares the result with a run where the plugin is not loaded. It answers 3 questions plugin developers…