{"id":21519,"plugin_id":"plugins_6aae54a259ac8191b56161d366fb6e51","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:16:58.570Z","digest":"69bb048d8b4307400404b46a222181a766bbe9fee87034d220f7fc7e6d970c61","against":null,"payload":{"description":"Frame, audit or improve an existing AI feature, RAG pipeline, OCR flow, agent tools, ML pipeline, evaluation, model serving or AI governance. Select the actual model/data/tool boundary.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":206},{"relative_path":"references/ai-evaluation-audit.md","size_in_bytes":2395},{"relative_path":"references/ai-evaluation-polish.md","size_in_bytes":1455},{"relative_path":"references/ai-feature-audit.md","size_in_bytes":3655},{"relative_path":"references/ai-feature-polish.md","size_in_bytes":1256},{"relative_path":"references/ai-ml-problem-framing.md","size_in_bytes":1616},{"relative_path":"references/ai-safety-governance-audit.md","size_in_bytes":1862},{"relative_path":"references/ai-safety-governance-polish.md","size_in_bytes":1272},{"relative_path":"references/llm-agent-tools-audit.md","size_in_bytes":2999},{"relative_path":"references/llm-agent-tools-polish.md","size_in_bytes":1256},{"relative_path":"references/ml-pipeline-audit.md","size_in_bytes":3252},{"relative_path":"references/ml-pipeline-polish.md","size_in_bytes":1237},{"relative_path":"references/model-serving-monitoring-audit.md","size_in_bytes":1853},{"relative_path":"references/model-serving-monitoring-polish.md","size_in_bytes":1247},{"relative_path":"references/ocr-document-ai-audit.md","size_in_bytes":3462},{"relative_path":"references/ocr-document-ai-polish.md","size_in_bytes":2533},{"relative_path":"references/rag-audit.md","size_in_bytes":3490},{"relative_path":"references/rag-polish.md","size_in_bytes":2541}],"name":"vibe-ai","skill_md_contents":"---\nname: vibe-ai\ndescription: \"Frame, audit or improve an existing AI feature, RAG pipeline, OCR flow, agent tools, ML pipeline, evaluation, model serving or AI governance. Select the actual model/data/tool boundary.\"\n---\n\n# AI, RAG & ML\n\nRead [the shared workflow](../../references/workflow.md) once per task, then the one recipe matching the requested operation and boundary. Do not load every recipe. The user's request controls scope and whether edits are allowed.\n\n## Recipes\n\n| Recipe | Operation |\n|---|---|\n| [AI Evaluation Audit](references/ai-evaluation-audit.md) | audit |\n| [AI Evaluation Polish](references/ai-evaluation-polish.md) | implement |\n| [AI Feature Audit](references/ai-feature-audit.md) | audit |\n| [AI Feature Polish](references/ai-feature-polish.md) | implement |\n| [AI ML Problem Framing](references/ai-ml-problem-framing.md) | plan |\n| [AI Safety & Governance Audit](references/ai-safety-governance-audit.md) | audit |\n| [AI Safety & Governance Polish](references/ai-safety-governance-polish.md) | implement |\n| [LLM Agent Tools Audit](references/llm-agent-tools-audit.md) | audit |\n| [LLM Agent Tools Polish](references/llm-agent-tools-polish.md) | implement |\n| [ML Pipeline Audit](references/ml-pipeline-audit.md) | audit |\n| [ML Pipeline Polish](references/ml-pipeline-polish.md) | implement |\n| [Model Serving & Monitoring Audit](references/model-serving-monitoring-audit.md) | audit |\n| [Model Serving & Monitoring Polish](references/model-serving-monitoring-polish.md) | implement |\n| [OCR Document AI Audit](references/ocr-document-ai-audit.md) | audit |\n| [OCR Document AI Polish](references/ocr-document-ai-polish.md) | implement |\n| [RAG Audit](references/rag-audit.md) | audit |\n| [RAG Polish](references/rag-polish.md) | implement |\n\nFor an explicit multi-stage request, follow the necessary stages without discarding requested work. For a single stage, deliver that result and stop. Use [the catalog](../../references/catalog.md) only if the requested boundary belongs elsewhere.\n\nUse [MCP](../vibe-mcp/SKILL.md) for protocol/transport conformance and [Harness](../vibe-harness/SKILL.md) for durable execution/checkpoint recovery. This skill owns model decisions, grounding and tool-selection quality.\n\nFor a verification-only request, apply the relevant audit recipe to the stated acceptance criteria and report the measured result and gaps. Verification alone does not authorize implementation; a separate check recipe is not required.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}