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 does not include an explicit step-by-step workflow or output schema, so an agent may produce unstructured review results.
• Permission surface may require sandboxing
• SKILL.md references 'security-and-hardening' and 'performance-optimization' but does not specify whether they are required dependencies or how to invoke them.
• The skill does not state safe operating boundaries, such as treating code under review as untrusted input and avoiding execution of the change during review.

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 does not include an explicit step-by-step workflow or output schema, so an agent may produce unstructured review results.
• Permission surface may require sandboxing
• SKILL.md references 'security-and-hardening' and 'performance-optimization' but does not specify whether they are required dependencies or how to invoke them.
• The skill does not state safe operating boundaries, such as treating code under review as untrusted input and avoiding execution of the change during review.

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 does not include an explicit step-by-step workflow or output schema, so an agent may produce unstructured review results.
• Permission surface may require sandboxing
• SKILL.md references 'security-and-hardening' and 'performance-optimization' but does not specify whether they are required dependencies or how to invoke them.
• The skill does not state safe operating boundaries, such as treating code under review as untrusted input and avoiding execution of the change during review.

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 does not include an explicit step-by-step workflow or output schema, so an agent may produce unstructured review results.
• Permission surface may require sandboxing
• SKILL.md references 'security-and-hardening' and 'performance-optimization' but does not specify whether they are required dependencies or how to invoke them.
• The skill does not state safe operating boundaries, such as treating code under review as untrusted input and avoiding execution of the change during review.