OpenAgentSkill
GitHub200+

Pre-install eval

smart-search 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
75
Eval report
74
Trust
83
Audit
51
Agent safety

manual review

Test manually in an isolated workspace and compare against safer alternatives.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate smart-search before installing it in an agent workflow
  • research
  • Research agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add jackwener/OpenCLI --skill smart-search

Install command safety

92

pass

standard package or runtime install path

  • npx skills add jackwener/OpenCLI --skill smart-search

Trust score

74

warn

Good trust signals with a few areas worth checking before rollout.

  • Strong shortlist
  • 29K GitHub stars
  • Apache-2.0

Audit score

83

pass

Safe to try

  • SKILL.md 未明确说明 opencli 的安装或环境要求，但假设 Agent 已具备该工具。

Agent safety gate

51

warn

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • High-risk permission hints: Shell or command execution

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

62

warn

shell or command execution, network or browser access

  • Shell or command execution: high
  • Browser automation: medium
  • 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
  • SKILL.md 未明确说明 opencli 的安装或环境要求，但假设 Agent 已具备该工具。
  • High-risk permission hints: Shell or command execution
  • 技能依赖外部命令 opencli，若该命令本身存在安全漏洞，可能影响 Agent，但技能本身未引入额外风险。
  • Quality score needs review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

76

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.