html 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 external CDNs (Google Fonts, MathJax, highlight.js) which may not be available in offline environments, but this is typical for web-based output and not a security risk.
• Audit risk risky exceeds max_risk=medium
• Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
• The render-pdf.sh script is macOS-specific and requires Chrome/Chromium in standard locations; it may fail on other platforms, but this is clearly documented.