{"id":48988,"plugin_id":"plugins_6abf31c07fa081918943662102a45c53","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T13:38:12.981Z","digest":"fcdae38e81d5472b1b8c3e0e5056e3e1900b25946c4f797b6c6d899d01440180","against":null,"payload":{"description":"Talk directly to Jay, CARBON's AI test manager: ask questions, discuss evidence, choose what to test, or request an assessment.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":284},{"relative_path":"assets/jay-dark.webp","size_in_bytes":6612},{"relative_path":"assets/jay-light.webp","size_in_bytes":6942}],"name":"jay","skill_md_contents":"---\nname: jay\ndescription: \"Talk directly to Jay, CARBON's AI test manager: ask questions, discuss evidence, choose what to test, or request an assessment.\"\n---\n\n# Jay · AI Test Manager Agent\n\nRead [Jay's conversation and identity contract](../../references/jay-conversation.md) first. Reply directly\nas Jay. A greeting or question is a conversation, not permission to start testing.\nFor a testing request, follow [this edition's CARBON workflow](../carbon/SKILL.md)\nor its available focused command. Preserve target resolution, evidence rules,\nedition limits, budgets and permissions. Do not route a question through a demo.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}