Skill Checker
Check only SKILL.md.
Use this skill when the user explicitly wants to check, audit, review, or optimize a SKILL.md file.
Accept either a SKILL.md path or a skill directory path. If the input is a directory, resolve SKILL.md inside it before running any checks.
Support absolute paths directly. Prefer absolute paths when auditing skills outside the current workspace.
Run the checker script (PowerShell):
CODEBLOCK0
Example with absolute paths:
CODEBLOCK1
Use the generated HTML report as the primary output. Summarize the overall result, the severe issue count, and the highest-priority fixes in the final response.
What to check
Validate the target SKILL.md against the Agent Skills specification:
- 1. Confirm YAML frontmatter exists and is parseable.
- Confirm required fields such as
name and description. - Validate optional specification fields when present.
- Check that
name matches the skill directory name when it can be inferred. - Review whether
description says what the skill does and when to use it. - Review whether the body contains enough actionable guidance to help another agent execute the skill.
Treat specification violations as severe issues.
Treat obvious semantic failures as severe issues too, including:
- - descriptions that are too short or too vague to support triggering
- bodies that are nearly empty or do not provide actionable guidance
Treat weaker organization or thin guidance as warnings.
Return a failing result when severe issues are 2 or more. Otherwise return a passing result.
Reporting
Always point the user to the generated HTML report path, especially when the target skill lives outside the current repo.
When summarizing results:
- 1. State whether the result is passing or failing.
- Mention the severe issue count and warning count.
- Call out the first fixes the user should make.
References
Read references/specification-checklist.md when you need the exact rules and severity mapping used by this skill.
技能检查器
仅检查 SKILL.md。
当用户明确要求检查、审计、审查或优化 SKILL.md 文件时使用此技能。
接受 SKILL.md 路径或技能目录路径。如果输入是目录，则在运行任何检查前解析其中的 SKILL.md。
直接支持绝对路径。审计当前工作区之外的技能时，优先使用绝对路径。
运行检查脚本（PowerShell）：
powershell
自动定位此技能目录（即使从其他文件夹运行也可用）
$SkillDir = Split-Path -Parent $MyInvocation.MyCommand.Path
Set-Location $SkillDir
运行
python .\scripts\check_skill.py <目标路径> [--out <报告路径>]
使用绝对路径的示例：
powershell
$SkillDir = Split-Path -Parent $MyInvocation.MyCommand.Path
Set-Location $SkillDir
python .\scripts\check_skill.py C:\path\to\skill\SKILL.md --out .\reports\skill-report.html
将生成的 HTML 报告作为主要输出。在最终回复中总结整体结果、严重问题数量以及最高优先级的修复项。
检查内容
根据代理技能规范验证目标 SKILL.md：
- 1. 确认 YAML 前置元数据存在且可解析。
- 确认必填字段如 name 和 description 存在。
- 验证可选规范字段（若存在）。
- 检查 name 是否与可推断的技能目录名称匹配。
- 审查 description 是否说明了技能的功能及使用时机。
- 审查正文是否包含足够的可操作指南，以帮助其他代理执行该技能。
将规范违规视为严重问题。
将明显的语义失败也视为严重问题，包括：
- - 描述过于简短或模糊，无法支持触发
- 正文几乎为空或未提供可操作指南
将组织较弱或指导不足视为警告。
当严重问题数量为 2 或更多时，返回失败结果。否则返回通过结果。
报告
始终向用户指明生成的 HTML 报告路径，尤其是当目标技能位于当前仓库之外时。
总结结果时：
- 1. 说明结果是通过还是失败。
- 提及严重问题数量和警告数量。
- 指出用户应优先修复的问题。
参考资料
当需要此技能使用的确切规则和严重程度映射时，请阅读 references/specification-checklist.md。
