{"id":19197,"plugin_id":"plugins_6a9464ad86dc8191bd1a478b38296c88","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:15:22.670Z","digest":"c487b62bf14390365f2e9c8323ba3719c3603256c79a5d63770a92f7adb8f70c","against":null,"payload":{"name":"analyst-review","description":"Use when preparing or reviewing a reproducible security evidence package.","included_files":[],"skill_md_contents":"---\nname: analyst-review\ndescription: Use when preparing or reviewing a reproducible security evidence package.\n---\n\nPurpose: hand a bounded investigation to a human analyst with facts, inferences, alternatives, and explicit response boundaries.\n\nPrerequisites: an existing case and reproducible evidence references.\n\nInputs: case ID, evidence package, analyst decision, and evidence IDs.\n\nWorkflow: retrieve evidence package → assess quality and confidence → record analyst review → choose a bounded next step or closure recommendation.\n\nAllowed tools: case evidence package, quality, confidence, review, closure-readiness, and outcome-agent brief tools.\n\nSecurity constraints: no automated response, case closure, or verdict; human review remains required.\n\nOutput: review-ready package, recorded decision, evidence gaps, and next safe action.\n\nFailure modes: missing evidence, inconsistent hypotheses, insufficient reviewer authority, or unresolved response proposal.\n\nTests: evidence package, review, confidence, closure-readiness, and autonomy-boundary tests.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}