skills-manager Eval report.

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 relies on executing third-party code via `npx skills` and installing external skills, which inherently carries supply-chain risks. However, it mitigates this by requiring user confirmation and displaying security warnings before installation.
• High-risk permission hints: Shell or command execution
• The skill references other skills (`find-skills`, `skill-creator`) that may not be available in all environments, but it provides fallback instructions for when they are missing.
• Production credentials, payments, or irreversible account changes without explicit human review