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 lacks a clear definition of inputs (e.g., slide content, data, images) and how they are provided to the agent.
• No explicit workflow or step-by-step instructions for generating the deck; the document reads more as a design spec than an actionable skill.
• Missing setup requirements (e.g., dependencies, external assets, or environment) and safe operating boundaries.
• No description of expected output format (HTML file, single-page, etc.) or how to handle errors/edge cases.

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 lacks a clear definition of inputs (e.g., slide content, data, images) and how they are provided to the agent.
• No explicit workflow or step-by-step instructions for generating the deck; the document reads more as a design spec than an actionable skill.
• Missing setup requirements (e.g., dependencies, external assets, or environment) and safe operating boundaries.
• No description of expected output format (HTML file, single-page, etc.) or how to handle errors/edge cases.

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 lacks a clear definition of inputs (e.g., slide content, data, images) and how they are provided to the agent.
• No explicit workflow or step-by-step instructions for generating the deck; the document reads more as a design spec than an actionable skill.
• Missing setup requirements (e.g., dependencies, external assets, or environment) and safe operating boundaries.
• No description of expected output format (HTML file, single-page, etc.) or how to handle errors/edge cases.

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 lacks a clear definition of inputs (e.g., slide content, data, images) and how they are provided to the agent.
• No explicit workflow or step-by-step instructions for generating the deck; the document reads more as a design spec than an actionable skill.
• Missing setup requirements (e.g., dependencies, external assets, or environment) and safe operating boundaries.
• No description of expected output format (HTML file, single-page, etc.) or how to handle errors/edge cases.