Skill audit report
Use this for a concrete decision, design, or plan when the user asks to pressure-test its assumptions, alternatives, risks, trade-offs, or failure modes. A host may select it automatically only when both the concrete subject and the pressure-test signal are present. Otherwise wait for an explicit `/persona grill-me` request or use the more specific existing route.
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
FAIL30
20 GitHub stars
Stars/forks activity
FAIL32
20 stars, 0 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
24d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add jyt6640/persona-harness --skill grill-me
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS100
no high-risk permission surface in public metadata
Repository evidence
PASS86
https://github.com/jyt6640/persona-harness/tree/main/packages/shared-skills/skills/grill-me
Review status
PASS88
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add jyt6640/persona-harness --skill grill-me
Repository
88
https://github.com/jyt6640/persona-harness/tree/main/packages/shared-skills/skills/grill-me
License
86
Apache-2.0
Maintenance
100
24d since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
86
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Install command safety
92
standard package or runtime install path
Permission surface
100
no high-risk permission surface in public metadata
Stars/forks activity
32
20 stars, 0 forks; issue activity unavailable in current metadata
Adoption
42
20 GitHub stars
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.