OpenAgentSkill
GitHub200+

Pre-install eval

four-color-cards 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
73
Eval report
70
Trust
77
Audit
61
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 four-color-cards before installing it in an agent workflow
  • automation
  • Browser automation workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add anbeime/skill --skill four-color-cards

Install command safety

92

pass

standard package or runtime install path

  • npx skills add anbeime/skill --skill four-color-cards

Trust score

70

warn

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

  • Manual review
  • 6.2K GitHub stars
  • Unknown

Audit score

77

warn

Needs review

  • License is unclear

Agent safety gate

61

warn

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

  • Require human approval before installing into a real workspace.
  • License is unclear

License clarity

42

warn

Unknown

  • Unknown

Permission surface

86

pass

network or browser access

  • Network access: medium
  • Filesystem 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
  • License is unknown; no license file or license information is provided in the repository or SKILL.md.
  • License is unclear
  • SKILL.md lacks explicit setup instructions (e.g., how to install dependencies, configure environment, or run outside the original project context).
  • The script depends on `core.runtime.AgentSession` which may not be available or portable without the full project structure.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

warn

70

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.