OpenAgentSkill
GitHub200+

Pre-install eval

ai-360-product-spin 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
65
Trust
70
Audit
58
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 ai-360-product-spin before installing it in an agent workflow
  • automation
  • automation workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add wubin1836/ai-hive-agent-skills --skill ai-360-product-spin

Install command safety

92

pass

standard package or runtime install path

  • npx skills add wubin1836/ai-hive-agent-skills --skill ai-360-product-spin

Trust score

65

warn

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

  • Manual review
  • 4 GitHub stars
  • MIT

Audit score

70

warn

Needs review

  • SKILL.md lacks a Setup/Prerequisites section explaining how to connect to or enable the AI-HIVE MCP server, how authentication is handled, and what permission scope the agent should request.

Agent safety gate

58

warn

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

  • Require human approval before installing into a real workspace.
  • SKILL.md lacks a Setup/Prerequisites section explaining how to connect to or enable the AI-HIVE MCP server, how authentication is handled, and what permission scope the agent should request.

License clarity

86

pass

MIT

  • MIT

Permission surface

100

pass

no high-risk permission surface in public metadata

  • Network 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
  • SKILL.md lacks a Setup/Prerequisites section explaining how to connect to or enable the AI-HIVE MCP server, how authentication is handled, and what permission scope the agent should request.
  • The deliverables are named but not specified as concrete artifacts: no file formats, resolution, frame count, naming conventions, or output location are defined for the rotation sequence, looping video, or consistency report.
  • The YAML metadata has empty tags and frameworks, and the skill has no explicit Limitations/When-not-to-use section, making categorization and safe scope less clear.

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.