OpenAgentSkill
GitHub200+

Pre-install eval

craft-garnish 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
67
Eval report
69
Trust
74
Audit
54
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

84

pass

Task wording matches this skill metadata.

  • Evaluate craft-garnish before installing it in an agent workflow
  • design-creative
  • Design and creative workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add michtio/craftcms-claude-skills --skill craft-garnish

Install command safety

92

pass

standard package or runtime install path

  • npx skills add michtio/craftcms-claude-skills --skill craft-garnish

Trust score

69

warn

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

  • Manual review
  • 78 GitHub stars
  • MIT

Audit score

74

warn

Needs review

  • The description trigger list is extremely long and may cause the skill to be loaded in borderline cases; organizing triggers into clear categories in the description could reduce over-triggering and improve scannability.

Agent safety gate

54

warn

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The description trigger list is extremely long and may cause the skill to be loaded in borderline cases; organizing triggers into clear categories in the description could reduce over-triggering and improve scannability.

License clarity

86

pass

MIT

  • MIT

Permission surface

72

warn

filesystem or document access, network or browser access

  • Browser automation: medium
  • 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 description trigger list is extremely long and may cause the skill to be loaded in borderline cases; organizing triggers into clear categories in the description could reduce over-triggering and improve scannability.
  • The SKILL.md excerpt ends with an incomplete 'Task examples:' section. If the actual file is truncated, the missing examples should be completed to preserve the skill's practical guidance.
  • Quality score needs review
  • GitHub adoption: 78 GitHub stars

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.