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
• Low GitHub adoption signal
• The skill references an external audit script (audit-claim-positioning.py) that is not included in the skill directory, but it is part of the repository. This is acceptable but should be documented clearly.
• High-risk permission hints: Shell or command execution
• The skill's step 0 is advisory and allows export even if sources are unresolved, which could lead to incomplete exports if the user ignores the warning. This is a minor usability concern.

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
• Low GitHub adoption signal
• The skill references an external audit script (audit-claim-positioning.py) that is not included in the skill directory, but it is part of the repository. This is acceptable but should be documented clearly.
• High-risk permission hints: Shell or command execution
• The skill's step 0 is advisory and allows export even if sources are unresolved, which could lead to incomplete exports if the user ignores the warning. This is a minor usability concern.

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
• Low GitHub adoption signal
• The skill references an external audit script (audit-claim-positioning.py) that is not included in the skill directory, but it is part of the repository. This is acceptable but should be documented clearly.
• High-risk permission hints: Shell or command execution
• The skill's step 0 is advisory and allows export even if sources are unresolved, which could lead to incomplete exports if the user ignores the warning. This is a minor usability concern.

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
• Low GitHub adoption signal
• The skill references an external audit script (audit-claim-positioning.py) that is not included in the skill directory, but it is part of the repository. This is acceptable but should be documented clearly.
• High-risk permission hints: Shell or command execution
• The skill's step 0 is advisory and allows export even if sources are unresolved, which could lead to incomplete exports if the user ignores the warning. This is a minor usability concern.