OpenAgentSkill
GitHub200+

Pre-install eval

owners-vision 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
68
Trust
75
Audit
59
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

94

pass

Task wording matches this skill metadata.

  • Evaluate owners-vision before installing it in an agent workflow
  • developer-tools
  • developer-tools workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add AmmarAlBalkhi/owners-vision --skill owners-vision

Install command safety

92

pass

standard package or runtime install path

  • npx skills add AmmarAlBalkhi/owners-vision --skill owners-vision

Trust score

68

warn

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

  • Manual review
  • 0 GitHub stars
  • MIT

Audit score

75

warn

Needs review

  • The skill depends on project-specific governing rules that must define the vision file, lock, and accepted digest; if those rules are missing or ambiguous, the skill correctly pauses, but SKILL.md could provide a clearer concrete example of such governing rules.

Agent safety gate

59

warn

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

  • Require human approval before installing into a real workspace.
  • The skill depends on project-specific governing rules that must define the vision file, lock, and accepted digest; if those rules are missing or ambiguous, the skill correctly pauses, but SKILL.md could provide a clearer concrete example of such governing rules.

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 depends on project-specific governing rules that must define the vision file, lock, and accepted digest; if those rules are missing or ambiguous, the skill correctly pauses, but SKILL.md could provide a clearer concrete example of such governing rules.
  • The independent reviewer/oracle launch mechanism is not fully specified; SKILL.md describes what it must not do, but not how the agent should instantiate a fresh reviewer in practice.
  • The integrity script accepts only a single-line lock record; other valid lock file formats would be rejected. This limitation is documented only in README, not in SKILL.md.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

94

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

6d since push

Alternatives available

pass

82

Alternative skills are available for comparison.