OpenAgentSkill
GitHub200+

Pre-install eval

red 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
68
Eval report
69
Trust
76
Audit
48
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 red before installing it in an agent workflow
  • automation
  • Local desktop workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add glebis/claude-skills --skill red

Install command safety

92

pass

standard package or runtime install path

  • npx skills add glebis/claude-skills --skill red

Trust score

69

warn

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

  • Manual review
  • 370 GitHub stars
  • MIT

Audit score

76

warn

Needs review

  • The SKILL.md description metadata parsing shows '>-' which is a YAML artifact, but the actual description is clear and complete.

Agent safety gate

48

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

MIT

  • MIT

Permission surface

62

warn

shell or command execution, filesystem or document access

  • Shell or command execution: high
  • 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
  • The SKILL.md description metadata parsing shows '>-' which is a YAML artifact, but the actual description is clear and complete.
  • High-risk permission hints: Shell or command execution
  • The script excerpt is truncated in the provided documentation, but the visible portion indicates a well-structured defensive tool with clear guardrails.
  • 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

1mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.