OpenAgentSkill
GitHub200+

Pre-install eval

dbs-content-system 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
74
Eval report
74
Trust
80
Audit
60
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 dbs-content-system before installing it in an agent workflow
  • security
  • RAG and knowledge workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add Pluviobyte/rnskill --skill dbs-content-system

Install command safety

92

pass

standard package or runtime install path

  • npx skills add Pluviobyte/rnskill --skill dbs-content-system

Trust score

74

warn

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

  • Strong shortlist
  • 1.4K GitHub stars
  • NOASSERTION

Audit score

80

warn

Needs review

  • Repository license is NOASSERTION and no explicit license file or notice is visible in SKILL.md, so reuse terms are unclear.

Agent safety gate

60

warn

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

  • Require human approval before installing into a real workspace.
  • Repository license is NOASSERTION and no explicit license file or notice is visible in SKILL.md, so reuse terms are unclear.

License clarity

86

pass

NOASSERTION

  • NOASSERTION

Permission surface

88

pass

database access

  • Network access: medium
  • Filesystem access: medium
  • Database 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
  • Repository license is NOASSERTION and no explicit license file or notice is visible in SKILL.md, so reuse terms are unclear.
  • Quickstart references `dontbesilent2025/dbskill` while the submitted repository is `Pluviobyte/rnskill`, creating installation and attribution inconsistency.
  • SKILL.md claims it must be fully executable from a single SKILL.md, but the workflow depends on scripts and templates that are not visible in the submitted excerpt; packaging should be verified.
  • No explicit prompt-injection guard is stated for reading local content files; content should be treated as untrusted data, not as instructions.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.