skill-validator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

The

skill-validator

is the primary quality control tool for this repository. It ensures that every AI Agent Skill is "machine-consumable" by validating it against the

agentskills.io

standard and the repository's

AGENTS.md

rules.

skill-validator

是本仓库的核心质量控制工具。它通过对照

agentskills.io

标准和仓库的

AGENTS.md

规则进行验证，确保每个AI Agent Skill都能被“机器消费”。

During Development: Run this skill every time you create or modify a skill.
CI/CD Integration: Automatically block Pull Requests that contain non-compliant skill definitions.
Repository Audits: Periodically scan the entire
```
agent-skills/
```
directory to ensure long-term compliance as specifications evolve.

Code Logic Validation: This tool does not "run" the skills or verify their internal logic; it only validates the "contract" (the YAML and Markdown).

Invalid YAML: If
```
skill.yaml
```
cannot be parsed, the validator will fail immediately with a syntax error.
Missing Required Fields: Any missing field defined in the
```
agentskills.io
```
specification will result in
```
is_valid: false
```
.
Empty Directories: Folders in
```
agent-skills/
```
that do not contain a
```
skill.yaml
```
will be flagged as invalid skills.

无效YAML：如果
```
skill.yaml
```
无法被解析，验证器会立即因语法错误而失败。
缺少必填字段：任何
```
agentskills.io
```
规范中定义的必填字段缺失，都会导致
```
is_valid: false
```
。
空目录：
```
agent-skills/
```
下不包含
```
skill.yaml
```
的文件夹会被标记为无效技能。

ReadOnly Access: The skill only requires read permissions for the target directory.
No External Calls: Validation is performed locally using the embedded schema rules.