Star0

Pre-install eval

OnWatch 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
81
Eval
82
Trust
87
Audit
67
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 OnWatch 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 onllm-dev/onWatch

Install command safety

92

pass

standard package or runtime install path

  • npx skills add onllm-dev/onWatch

Trust score

82

pass

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

  • Strong shortlist
  • 669 GitHub stars
  • GPL-3.0

Audit score

87

warn

Needs review

  • Permission surface may require sandboxing

Agent safety gate

67

warn

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

  • Require human approval before installing into a real workspace.
  • Permission surface may require sandboxing

License clarity

86

pass

GPL-3.0

  • GPL-3.0

Permission surface

60

warn

filesystem or document access, network or browser access

  • Network access: medium
  • Filesystem access: medium
  • Database 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
  • high-compliance environments without internal security review
  • No major risk signals from current metadata
  • Permission surface may require sandboxing
  • Quality score needs review
  • Permission surface needs review: filesystem or document access, network or browser access

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

90

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

4d since push

Alternatives available

pass

82

Alternative skills are available for comparison.