OpenAgentSkill
GitHub200+

Pre-install eval

kb-article 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
78
Eval report
74
Trust
85
Audit
57
Agent safety

do not auto install

Permission surface: secrets or environment access, filesystem or document access

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate kb-article before installing it in an agent workflow
  • ai-knowledge
  • Customer support workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add anthropics/knowledge-work-plugins --skill kb-article

Install command safety

92

pass

standard package or runtime install path

  • npx skills add anthropics/knowledge-work-plugins --skill kb-article

Trust score

74

warn

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

  • Strong shortlist
  • 30K GitHub stars
  • Apache-2.0

Audit score

85

warn

Needs review

  • Permission surface may require sandboxing

Agent safety gate

57

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: Secrets or environment access

License clarity

86

pass

Apache-2.0

  • Apache-2.0

Permission surface

46

fail

secrets or environment access, filesystem or document access

  • Network access: medium
  • Filesystem access: medium
  • Secrets or environment access: high

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 uses unresolved `~~support platform`, `~~knowledge base`, and `~~project tracker` placeholders instead of concrete connector names, which may make the skill ambiguous outside its original repo.
  • High-risk permission hints: Secrets or environment access
  • Permission surface may require sandboxing
  • No explicit guidance for handling sensitive data (PII, internal notes, credentials) when reading tickets or internal systems; the skill should require redacting confidential information from any customer-facing draft.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

Pushed today

Alternatives available

pass

82

Alternative skills are available for comparison.