holo-card-studio 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
• Source inspection only; the Blender/image-generation workflow and generated output have not been executed or visually tested by OpenAgentSkill.
• Permission surface may require sandboxing
• The workflow downloads and runs Blender and installs the pinned Three.js package. Review the source and use a dedicated output project.
• build_card.py saves Blender user preferences; using an existing Blender installation can change its interface language/preferences.