OpenAgentSkill
GitHub200+

Pre-install eval

figure-description 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
75
Eval report
75
Trust
82
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 figure-description before installing it in an agent workflow
  • automation
  • Coding agents workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill figure-description

Install command safety

92

pass

standard package or runtime install path

  • npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill figure-description

Trust score

75

warn

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

  • Strong shortlist
  • 16K GitHub stars
  • MIT

Audit score

82

pass

Safe to try

  • The skill uses WebSearch and WebFetch but does not specify when or why they should be used, which could lead to unnecessary external calls.

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.
  • High-risk permission hints: Shell or command execution

License clarity

86

pass

MIT

  • MIT

Permission surface

62

warn

shell or command execution, filesystem or document access

  • 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 uses WebSearch and WebFetch but does not specify when or why they should be used, which could lead to unnecessary external calls.
  • High-risk permission hints: Shell or command execution
  • The skill assumes a specific directory structure (patent/figures) without providing a fallback if the structure is different.
  • 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.