ads Rapport d’évaluation.

Plan de validation

Ce que l’Agent doit faire ensuite

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.

Ne pas utiliser quand

Conditions exigeant une autre skill

• Équipes qui nécessitent un SLA soutenu par le fournisseur
• production agents without a repository review
• The SKILL.md description has a formatting issue: the first line ends with 'Google, Meta' and the next line starts a new sentence, causing a truncated description in the metadata. This could be cleaned up for clarity.
• Indices de permissions à haut risque : exécution shell ou de commande
• Financial research output is not financial advice; require human review before any live investment decision
• The skill relies on external references (benchmarks, bidding strategies, etc.) that are not fully included in the excerpt, but they are referenced as files in the repository. This is acceptable as long as they are present in the full submission.