OpenAgentSkill
GitHub200+

Pre-install eval

hr-assistant Eval report.

A machine-readable install decision for agents: task fit, Trust Score, Audit Score, install safety, permission surface, and a concrete validation plan before this skill touches a workspace.

Needs reviewMedium riskREVIEW Policy
65
Eval report
63
Trust
71
Audit
59
Agent safety

manual review

Require human approval before installing into a real workspace.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate hr-assistant before installing it in an agent workflow
  • automation
  • Browser automation workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add zj-unicom-ai/UniEmployee --skill hr-assistant

Install command safety

92

pass

standard package or runtime install path

  • npx skills add zj-unicom-ai/UniEmployee --skill hr-assistant

Trust score

63

warn

Potentially useful, but at least one trust signal needs human inspection.

  • Manual review
  • 21 GitHub stars
  • MIT

Audit score

71

warn

Needs review

  • SKILL.md 未明确列出所需的工具（如 kb_search、customer_profile、create_ticket、bocha_search）的详细输入输出格式，可能导致实现时歧义。

Agent safety gate

59

warn

Usable candidate, but the agent should surface permission and audit notes before installation.

  • Require human approval before installing into a real workspace.
  • SKILL.md 未明确列出所需的工具（如 kb_search、customer_profile、create_ticket、bocha_search）的详细输入输出格式，可能导致实现时歧义。

License clarity

86

pass

MIT

  • MIT

Permission surface

100

pass

no high-risk permission surface in public metadata

  • Network access: medium

Validation plan

What the agent should do next

  1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
  2. 2Install in an isolated workspace or sandbox with no production secrets available.
  3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
  4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
  5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when

Conditions that require another skill

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Low GitHub adoption signal
  • SKILL.md 未明确列出所需的工具（如 kb_search、customer_profile、create_ticket、bocha_search）的详细输入输出格式，可能导致实现时歧义。
  • 缺少对知识库内容范围、更新机制和权限控制的说明，可能影响安全边界。
  • 未说明技能在无法访问外部工具时的降级策略或错误处理。

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

60

Public metadata needs stronger README/SKILL.md context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.