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 does not explicitly define input/output artifacts or success criteria for each phase, so an agent may not know when the skill has been fully applied.
• The skill lacks a dedicated limitations section, such as when to stop abstracting or when the process is unnecessary.
• No concrete example or template is provided to illustrate the expected semantic-level output.
• Production credentials, payments, or irreversible account changes without explicit human 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
• SKILL.md does not explicitly define input/output artifacts or success criteria for each phase, so an agent may not know when the skill has been fully applied.
• The skill lacks a dedicated limitations section, such as when to stop abstracting or when the process is unnecessary.
• No concrete example or template is provided to illustrate the expected semantic-level output.
• Production credentials, payments, or irreversible account changes without explicit human 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
• SKILL.md does not explicitly define input/output artifacts or success criteria for each phase, so an agent may not know when the skill has been fully applied.
• The skill lacks a dedicated limitations section, such as when to stop abstracting or when the process is unnecessary.
• No concrete example or template is provided to illustrate the expected semantic-level output.
• Production credentials, payments, or irreversible account changes without explicit human 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
• SKILL.md does not explicitly define input/output artifacts or success criteria for each phase, so an agent may not know when the skill has been fully applied.
• The skill lacks a dedicated limitations section, such as when to stop abstracting or when the process is unnecessary.
• No concrete example or template is provided to illustrate the expected semantic-level output.
• Production credentials, payments, or irreversible account changes without explicit human review