acreadiness-assess 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 relies on `npx github:microsoft/agentrc` which downloads and executes code from a remote source; while the source is reputable, this introduces a supply chain risk that is not explicitly mitigated (e.g., version pinning or integrity checks).
• Indices de permissions à haut risque : exécution shell ou de commande
• The skill references a custom agent `@ai-readiness-reporter` without specifying how it is discovered or invoked; this dependency is not self-contained and may cause failures if the agent is unavailable.
• Production credentials, payments, or irreversible account changes without explicit human review