OpenAgentSkill
GitHub200+

Pre-install eval

idea-refine 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
79
Eval report
75
Trust
84
Audit
56
Agent safety

manual review

Test manually in an isolated workspace and compare against safer alternatives.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

94

pass

Task wording matches this skill metadata.

  • Evaluate idea-refine before installing it in an agent workflow
  • coding-agents
  • Coding agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add addyosmani/agent-skills --skill idea-refine

Install command safety

92

pass

standard package or runtime install path

  • npx skills add addyosmani/agent-skills --skill idea-refine

Trust score

75

warn

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

  • Strong shortlist
  • 91K GitHub stars
  • MIT

Audit score

84

pass

Safe to try

  • The skill relies on the AskUserQuestion tool without specifying a fallback if that tool is unavailable in the agent runtime.

Agent safety gate

56

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

76

warn

shell or command execution

  • 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 relies on the AskUserQuestion tool without specifying a fallback if that tool is unavailable in the agent runtime.
  • High-risk permission hints: Shell or command execution
  • The script only creates the docs/ideas directory and does not validate or handle path traversal if an idea name is later used as a filename.
  • SKILL.md does not include an explicit limitations section, though the interactive nature is reasonably clear.

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.