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 define the meaning of 'Type 3' and 'Type 1/2/4' claims, which may be unclear to users outside the original project context.
• No OpenAgentSkill engagement data yet
• No explicit limitations or safe operating boundaries are described in SKILL.md, such as acceptable input formats or behavior when source data is missing or invalid.
• The skill relies on external reference files for chart patterns and styling, but SKILL.md itself does not summarize fallback behavior if those references are unavailable.

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 define the meaning of 'Type 3' and 'Type 1/2/4' claims, which may be unclear to users outside the original project context.
• No OpenAgentSkill engagement data yet
• No explicit limitations or safe operating boundaries are described in SKILL.md, such as acceptable input formats or behavior when source data is missing or invalid.
• The skill relies on external reference files for chart patterns and styling, but SKILL.md itself does not summarize fallback behavior if those references are unavailable.

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 define the meaning of 'Type 3' and 'Type 1/2/4' claims, which may be unclear to users outside the original project context.
• No OpenAgentSkill engagement data yet
• No explicit limitations or safe operating boundaries are described in SKILL.md, such as acceptable input formats or behavior when source data is missing or invalid.
• The skill relies on external reference files for chart patterns and styling, but SKILL.md itself does not summarize fallback behavior if those references are unavailable.

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 define the meaning of 'Type 3' and 'Type 1/2/4' claims, which may be unclear to users outside the original project context.
• No OpenAgentSkill engagement data yet
• No explicit limitations or safe operating boundaries are described in SKILL.md, such as acceptable input formats or behavior when source data is missing or invalid.
• The skill relies on external reference files for chart patterns and styling, but SKILL.md itself does not summarize fallback behavior if those references are unavailable.