human-writing 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 provided SKILL.md excerpt is cut off mid-sentence at the colon restriction; the full file should be included when packaging so the rule is not accidentally truncated.
• No OpenAgentSkill engagement data yet
• The rule set is very opinionated and extensive; without the full reference files, an agent might apply prose defaults to poetry, dialogue, or scripted formats, though the routing section tries to avoid this.
• Quality score needs review