From e4e097fce13d72bc8fc83c9e1ab5bfd9bb1aae27 Mon Sep 17 00:00:00 2001 From: pyt Date: Sat, 23 May 2026 02:39:21 +0900 Subject: [PATCH] fix(sagemaker-ai): quote model-evaluation skill description to fix YAML parse error The model-evaluation SKILL.md description is an unquoted YAML plain scalar that contains a colon-space sequence ("two evaluation types: LLM-as-Judge"). The YAML parser reads that colon as a mapping indicator and rejects the frontmatter with "mapping values are not allowed here". When this happens the skill loads with empty metadata (name, description, and version are silently dropped), so the skill no longer triggers and "claude plugin validate" reports an error. Wrapping the description in single quotes makes it a valid quoted scalar while preserving the text verbatim, including the inner double quotes and the colon. This is the same class of fix as #10. --- plugins/sagemaker-ai/skills/model-evaluation/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/plugins/sagemaker-ai/skills/model-evaluation/SKILL.md b/plugins/sagemaker-ai/skills/model-evaluation/SKILL.md index f9de3866..ec05ab72 100644 --- a/plugins/sagemaker-ai/skills/model-evaluation/SKILL.md +++ b/plugins/sagemaker-ai/skills/model-evaluation/SKILL.md @@ -1,6 +1,6 @@ --- name: model-evaluation -description: Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "test model performance", "how did my model perform", "compare models", or other similar requests. +description: 'Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "test model performance", "how did my model perform", "compare models", or other similar requests.' metadata: version: "2.0.0" ---