OpenAgentSkill
GitHub200+

Pre-install eval

math-figure-generator 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
72
Eval report
72
Trust
79
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

84

pass

Task wording matches this skill metadata.

  • Evaluate math-figure-generator before installing it in an agent workflow
  • research
  • Research agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add zhnnky329/MathModeling-skills --skill math-figure-generator

Install command safety

92

pass

standard package or runtime install path

  • npx skills add zhnnky329/MathModeling-skills --skill math-figure-generator

Trust score

72

warn

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

  • Strong shortlist
  • 723 GitHub stars
  • MIT

Audit score

79

warn

Needs review

  • SKILL.md does not define the meaning of 'Type 3' and 'Type 1/2/4' claims, which may be unclear to users outside the original project context.

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.
  • SKILL.md does not define the meaning of 'Type 3' and 'Type 1/2/4' claims, which may be unclear to users outside the original project context.

License clarity

86

pass

MIT

  • MIT

Permission surface

100

pass

no high-risk permission surface in public metadata

  • 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
  • SKILL.md does not define the meaning of 'Type 3' and 'Type 1/2/4' claims, which may be unclear to users outside the original project context.
  • No explicit limitations or safe operating boundaries are described in SKILL.md, such as acceptable input formats or behavior when source data is missing or invalid.
  • The skill relies on external reference files for chart patterns and styling, but SKILL.md itself does not summarize fallback behavior if those references are unavailable.
  • Quality score needs review

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.