replica-launch 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 assumes replica/fixes.md, replica/brand.md, and replica/brand.json already exist with a specific schema, but SKILL.md does not document that schema. An agent may need to guess fields.
• High-risk permission hints: Shell or command execution
• The workflow depends on replica-design's contrast check, but there is no fallback or verification if that skill is unavailable.
• No explicit legal/permission check is included for the 'clone' target; users are warned about store rejections but not about copyright/trademark risks beyond the original's name.