agent-ecosystem/skill-validator

Registry 信息

项目简介

一个基于Go的工具，根据Agent Skill规范验证Skill内容，并额外进行内容密度与质量检查，确保Skill提交符合高标准。

要点

• 根据Agent Skill规范验证Skill内容
• 执行内容密度分析
• 对Skill提交进行质量检查
• 使用Go构建，执行速度快
• 设计用于集成到CI/CD流水线

使用场景

• Skill开发者的提交前验证
• Skill发布工作流中的自动化质量门控
• 确保Skill生态系统贡献的一致性
• Skill仓库的CI/CD集成

README 摘要

# skill-validator [](https://github.com/agent-ecosystem/skill-validator/actions/workflows/ci.yml) [](https://opensource.org/licenses/MIT) A CLI tool that validates and scores [Agent Skill](https://agentskills.io) packages. Spec compliance is table stakes. `skill-validator` goes further: it checks that links actually resolve, flags files that shouldn't be in a skill directory, reports token counts so you can see how much of an agent's context window your skill will consume, analyzes content quality metrics, detects cross-language contamination, and offers LLM-as-judge scoring to evaluate skill quality across dimensions like clarity, actionability, and novelty. A spec-compliant skill that has broken links or a 60k-token reference file will technically pass the spec but perform poorly in practice. ## Table of Contents - [Install](#install) - [CLI](#install-cli) - [Homebrew](#homebrew) - [Using Go](#using-go) - [Pre-commit hook](#pre-commit-hook) - [As a library](#as-a-library) - [Command Usage](#command-usage) - [validate structure](#validate-structure) - [validate links](#validate-links) - [analyze content](#analyze-content) - [analyze contamination](#analyze-contamination) - [check](#check) - [score evaluate](#score-evaluate) - [score report](#score-report) - [Output Formats](#output-formats) - [JSON output](#json-output) - [Markdown output](#markdown-output) - [GitHub Actions annotations](#github-actions-annotations) - [CI Integration](#ci-integration) - [CI workflow example](#ci-workflow-example) - [Multi-skill directories](#multi-skill-directories) - [Examples](#exam

话题

暂无话题