OpenAgentSkill
GitHub200+

Pre-install eval

can 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.

FailedHigh riskBLOCK Policy
66
Eval report
71
Trust
77
Audit
49
Agent safety

do not auto install

Task fit: Task fit is weak; compare alternatives before selecting.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

58

fail

Task fit is weak; compare alternatives before selecting.

  • Evaluate can before installing it in an agent workflow
  • automation
  • RAG and knowledge workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add zhinkgit/embeddedskills --skill can

Install command safety

92

pass

standard package or runtime install path

  • npx skills add zhinkgit/embeddedskills --skill can

Trust score

71

warn

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

  • Manual review
  • 625 GitHub stars
  • MIT

Audit score

77

warn

Needs review

  • The SKILL.md description in the frontmatter is very long and includes trigger conditions, which is acceptable but could be more concise.

Agent safety gate

49

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 in the frontmatter is very long and includes trigger conditions, which is acceptable but could be more concise.
  • High-risk permission hints: Shell or command execution
  • The skill automatically writes to project config files after successful execution, which might be unexpected for some users but is documented.
  • Quality score needs review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

88

1mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.