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
• The SKILL.md excerpt is truncated, so the full workflow and core file contents were not reviewed, but the visible portions are clear and structured.
• The skill requires external Python dependencies (e.g., PDF libraries) which are not explicitly listed in SKILL.md, but the manifest and workflow imply they are available in the environment.
• Production credentials, payments, or irreversible account changes without explicit human review
• Sensitive private data before reviewing repository code, license, and permission surface

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
• The SKILL.md excerpt is truncated, so the full workflow and core file contents were not reviewed, but the visible portions are clear and structured.
• The skill requires external Python dependencies (e.g., PDF libraries) which are not explicitly listed in SKILL.md, but the manifest and workflow imply they are available in the environment.
• Production credentials, payments, or irreversible account changes without explicit human review
• Sensitive private data before reviewing repository code, license, and permission surface

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
• The SKILL.md excerpt is truncated, so the full workflow and core file contents were not reviewed, but the visible portions are clear and structured.
• The skill requires external Python dependencies (e.g., PDF libraries) which are not explicitly listed in SKILL.md, but the manifest and workflow imply they are available in the environment.
• Production credentials, payments, or irreversible account changes without explicit human review
• Sensitive private data before reviewing repository code, license, and permission surface

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
• The SKILL.md excerpt is truncated, so the full workflow and core file contents were not reviewed, but the visible portions are clear and structured.
• The skill requires external Python dependencies (e.g., PDF libraries) which are not explicitly listed in SKILL.md, but the manifest and workflow imply they are available in the environment.
• Production credentials, payments, or irreversible account changes without explicit human review
• Sensitive private data before reviewing repository code, license, and permission surface