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.md does not define an explicit input/output contract or step-by-step workflow, so an agent must infer how to collect user requirements, structure the map, and present the output.
• Financial research output is not financial advice; require human review before any live investment decision
• The metadata.author field is used as promotional content for Markdown Viewer instead of identifying the skill author, and the parsed metadata does not include a top-level author field.

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.md does not define an explicit input/output contract or step-by-step workflow, so an agent must infer how to collect user requirements, structure the map, and present the output.
• Financial research output is not financial advice; require human review before any live investment decision
• The metadata.author field is used as promotional content for Markdown Viewer instead of identifying the skill author, and the parsed metadata does not include a top-level author field.

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.md does not define an explicit input/output contract or step-by-step workflow, so an agent must infer how to collect user requirements, structure the map, and present the output.
• Financial research output is not financial advice; require human review before any live investment decision
• The metadata.author field is used as promotional content for Markdown Viewer instead of identifying the skill author, and the parsed metadata does not include a top-level author field.

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.md does not define an explicit input/output contract or step-by-step workflow, so an agent must infer how to collect user requirements, structure the map, and present the output.
• Financial research output is not financial advice; require human review before any live investment decision
• The metadata.author field is used as promotional content for Markdown Viewer instead of identifying the skill author, and the parsed metadata does not include a top-level author field.