一项Claude代码技能，用于标准化Netresearch技能库的布局、分发渠道、打包和验证。

这项技能解决了什么

Netresearch保留了许多代理技能;如果没有共享的布局，打包和配置就是在不同仓库间漂移。这项技能定义了一个标准仓库形状、可重用的工作流程、分割许可和验证脚本，确保新旧技能通过市场、Composer、npm和发布保持一致并可发布。

它通过仓库级别的惯例扩展了Anthropic风格的单文件技能（不能替代Anthropic的技能创建器——见下文对比）。

为什么这是一项技能（Delta模型）

• 价值类别： 组织/项目专属知识（Netresearch仓库形状、分割许可、作曲者类型ai-agent-skill）和可执行脚本/验证器（validate-skill.sh、checkpoints.yaml）。
• 没有该技能： 模型会发明一个合理的通用仓库布局——单一 LICENSE，没有 plugin.json、composer.json，但没有 ai-agent-skill 类型——但会导致 validate-skill.sh 和 org CI 失败。
• 评估证据： validate_skill_repo_structure 和 readme_requirements 在“技能/技能-回放/评估/评估”中。

Skill Repository Structure Guide

A Claude Code skill for standardizing Netresearch skill repository layout, distribution channels, packaging, and validation.

What this skill solves

Netresearch maintains many agent skills; without a shared layout, packaging and CI drift across repositories. This skill defines one standard repo shape, reusable workflows, split licensing, and validation scripts so new and existing skills stay consistent and shippable via marketplace, Composer, npm, and releases.

It extends Anthropic-style single-file skills with repository-level conventions (not a replacement for Anthropic’s skill-creator — see comparison below).

Why this is a skill (model delta)

• Value categories: org/project-specific knowledge (Netresearch repo shape, split licensing, composer type ai-agent-skill) and executable scripts/validators (validate-skill.sh, checkpoints.yaml).
• Without the skill: the model invents a plausible generic repo layout — single LICENSE, no plugin.json, composer.json without the ai-agent-skill type — that fails validate-skill.sh and org CI.
• Eval evidence: validate_skill_repo_structure and readme_requirements in skills/skill-repo/evals/evals.json.

Compatibility

This is an Agent Skill following the open standard originally developed by Anthropic and released for cross-platform use. The repository is also packaged as an Agent Plugins 1.0.0 plugin: the root plugin.json plus skills/ layout is what any conformant client loads.

Supported platforms:

• Claude Code (Anthropic)
• Cursor
• GitHub Copilot
• Other skills-compatible AI agents

Skills are portable packages of procedural knowledge that work across any AI agent supporting the Agent Skills specification.

Use when

• Creating or bootstrapping a Netresearch-style skill repository
• Standardizing layout, composer.json, plugin.json / .claude-plugin/plugin.json, or release workflows
• Wiring reusable CI from netresearch/skill-repo-skill
• Fixing validation errors from validate-skill.sh or marketplace packaging
• Migrating to split licensing (LICENSE-MIT + LICENSE-CC-BY-SA-4.0)

Expected outputs

• A documented directory layout and templates for new repos
• Validation: structural checks for SKILL.md, licenses, composer.json, plugin.json
• Release discipline: tag-driven packaging aligned with plugin version
• References for installation paths, marketplace sync, and release safety

Context requirements

• Validation script: bash 4.3+ and python3 (3.11+) on PATH when running validate-skill.sh (JSON checks use Python, not jq)
• Target repos: GitHub-hosted Netresearch skill repos using split licensing and Composer type ai-agent-skill