minimal-run-and-audit 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 executes arbitrary commands via run_command.py without explicit safeguards against destructive or unsafe operations. While the skill is intended for reproduction runs, the agent must ensure the command is safe before execution.
• High-risk permission hints: Shell or command execution
• The tracked source changed or could not be synchronized. Review the current source before installing.
• The skill depends on shared scripts from other RigorPilot skills (ai-research-reproduction). This creates a deployment dependency that may not be obvious to users.