OpenAgentSkill
GitHub200+

Pre-install eval

corpus 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
64
Eval report
66
Trust
71
Audit
55
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 corpus before installing it in an agent workflow
  • security
  • Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add NathanAB/corpus-skill --skill corpus

Install command safety

92

pass

standard package or runtime install path

  • npx skills add NathanAB/corpus-skill --skill corpus

Trust score

66

warn

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

  • Manual review
  • 12 GitHub stars
  • MIT

Audit score

71

warn

Needs review

  • The SKILL.md references detailed workflows in references/ but those files are not included in the provided excerpt; however, they are part of the repository and presumably present.

Agent safety gate

55

warn

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

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The SKILL.md references detailed workflows in references/ but those files are not included in the provided excerpt; however, they are part of the repository and presumably present.

License clarity

86

pass

MIT

  • MIT

Permission surface

86

pass

filesystem or document 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
  • Low GitHub adoption signal
  • The SKILL.md references detailed workflows in references/ but those files are not included in the provided excerpt; however, they are part of the repository and presumably present.
  • No explicit security boundaries or permission requirements are stated in SKILL.md, though the skill itself appears safe.
  • 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.