[Feature] Adding support for evaluating skills ( eval-driven approach)

[egasimov]

Problem

We would like to see having support of evaluating skills like skill-scanner in the Web UI.

Additional data:
https://agentskills.io/skill-creation/evaluating-skills

Proposed Solution

Add support for evaluating skills and execute or interpret its results while publishing/exploring the skills

Alternatives Considered

No response

Impact

No response

Contract Or SDK Impact

No response

[github-actions]

Issue Triage

• Route: triage/core
• Priority: priority/p1 (3.6/5)
• Effort: effort/l (5/5)
• Confidence: 4/5
• Risk: low
• Analysis Mode: rules-only

Why

• Touches core SkillHub workflows (publish, publishing, scanner).
• Open for 10 days; forced into an active lane before the 14-day closure SLA is missed.

Maintainer Brief

Summary: We would like to see having support of evaluating skills like skill-scanner in the Web UI. Additional data: https://agentskills.io/skill-creation/evaluating-skills
Why core:

• Likely spans multiple modules or a public compatibility surface.
  Reproduction or operator path:
• We would like to see having support of evaluating skills like skill-scanner in the Web UI.
• Additional data:
• https://agentskills.io/skill-creation/evaluating-skills
  Suspected areas:
• Security scanner pipeline and audit/reporting behavior
  Risks to watch:
• Check for regressions in adjacent user-facing workflow paths before merging.
  Validation checklist:
• Validate the primary reported workflow end-to-end after the fix.

Next Action

• Hand the issue to a core maintainer and use a local programming agent for reproduction, scoping, and validation.

---

问题分流结果

• 路由: triage/core
• 优先级: priority/p1 (3.6/5)
• 修复投入: effort/l (5/5)
• 信息完整度: 4/5
• 风险: 低
• 分析模式: rules-only

原因

• 涉及 SkillHub 核心流程（publish, publishing, scanner）
• 已打开 10 天，为避免超过 14 天仍未闭环，强制进入 active lane

维护者交接摘要

概要: We would like to see having support of evaluating skills like skill-scanner in the Web UI. Additional data: https://agentskills.io/skill-creation/evaluating-skills
为何进入 core:

• 大概率跨多个模块或公共兼容面
  复现路径或操作路径:
• We would like to see having support of evaluating skills like skill-scanner in the Web UI.
• Additional data:
• https://agentskills.io/skill-creation/evaluating-skills
  怀疑影响区域:
• 安全扫描流程与审计/报告行为
  重点风险:
• 合并前检查相邻用户路径是否出现回归
  验证清单:
• 修复后端到端验证主报告流程

下一步

• 交给 core maintainer，并结合本地编程Agent协助完成复现、收敛范围与验证闭环