yam-simulation-transfer 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
• SKILL.md is very brief and does not itself contain the workflow, inputs, outputs, setup, limitations, or safe operating boundaries; it relies entirely on reference files.
• No OpenAgentSkill engagement data yet
• The reference files are partially excerpted and not fully self-contained; some sections are cut off (e.g., bowl-libero-transfer.md, can-libero-transfer.md).
• No explicit safety or operational boundaries are stated in SKILL.md, though the references mention cautious probing and scene stability.