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 concrete output format (HTML, Markdown, PDF, PPTX, etc.) or how the agent should produce the deck.
• No OpenAgentSkill engagement data yet
• No setup, usage workflow, or example mapping from user content to slide pages is provided.
• Missing explicit limitations and safe operating boundaries, such as supported content length, font dependencies, or fallback behavior.

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 concrete output format (HTML, Markdown, PDF, PPTX, etc.) or how the agent should produce the deck.
• No OpenAgentSkill engagement data yet
• No setup, usage workflow, or example mapping from user content to slide pages is provided.
• Missing explicit limitations and safe operating boundaries, such as supported content length, font dependencies, or fallback behavior.

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 concrete output format (HTML, Markdown, PDF, PPTX, etc.) or how the agent should produce the deck.
• No OpenAgentSkill engagement data yet
• No setup, usage workflow, or example mapping from user content to slide pages is provided.
• Missing explicit limitations and safe operating boundaries, such as supported content length, font dependencies, or fallback behavior.

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 concrete output format (HTML, Markdown, PDF, PPTX, etc.) or how the agent should produce the deck.
• No OpenAgentSkill engagement data yet
• No setup, usage workflow, or example mapping from user content to slide pages is provided.
• Missing explicit limitations and safe operating boundaries, such as supported content length, font dependencies, or fallback behavior.