{"id":21073,"plugin_id":"plugins_6aac006819508191a02506fb32a88714","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:16:47.651Z","digest":"a5627531708d78aa68d4241e91bb521edffb960f22f23d22665033dd26ba73ec","against":null,"payload":{"name":"approval-boundary-mapper","description":"Map which CIO actions can be advised, drafted, prepared for approval or must remain human-only. Use when the user needs approval boundary mapper for CIO decision support.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":140}],"skill_md_contents":"---\nname: approval-boundary-mapper\ndescription: Map which CIO actions can be advised, drafted, prepared for approval or must remain human-only. Use when the user needs approval boundary mapper for CIO decision support.\n---\n\n# Approval Boundary Mapper\n\n## Mission\n\nMake autonomy boundaries explicit before executive actions, approvals or escalations are prepared.\n\n## Inputs\n\nAccept action ledgers, decision packets, risk registers, approval notes, policy excerpts, governance models and meeting outcomes.\n\n## Workflow\n\n1. Identify each proposed action or decision.\n2. Classify the autonomy level from observe, advise, draft, ready for governed execution or human-only.\n3. Name required approver, decision forum and control evidence.\n4. Mark regulated, irreversible or high-risk domains as human approval required.\n5. Draft the boundary map without executing or approving anything externally.\n\n## Output Format\n\n- Executive Summary\n- Boundary Count\n- Approval Boundaries\n- Human-Only Domains\n- Required Approvals\n- Evidence Gates\n- Residual Risks\n- Next Controls\n\n## Guardrails\n\nDo not approve, execute or route actions. Prepare a boundary map for accountable human review.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}