{"id":50586,"plugin_id":"plugin_asdk_app_6ac19b6690cc8191a624a003f3e732bc","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T13:43:40.982Z","digest":"d659e5801e859877413529a87cc01717f465a5e0234e5b44ca68e5150ea545cb","against":null,"payload":{"description":"Use when the user asks to convert and score a published Bankstatemently benchmark statement. Do not use for ordinary user-statement conversion, spending analysis, or reconciliation.","included_files":[],"name":"benchmark-accuracy","skill_md_contents":"---\nname: benchmark-accuracy\ndescription: Use when the user asks to convert and score a published Bankstatemently benchmark statement. Do not use for ordinary user-statement conversion, spending analysis, or reconciliation.\n---\n\n# Benchmark\n\n**Input:** a benchmark statement id, PDF URL, or free-text benchmark request.\n**Output:** extraction accuracy, integrity score, overall score, and major failure categories, citing the benchmark statement id and converted document content_hash.\n\nTreat the input as a benchmark statement id, PDF URL, or free-text benchmark request.\n\nFollow this sequence:\n\n1. Read the benchmark catalog resource and choose the named published statement.\n2. Convert the benchmark PDF with `convert_statement`.\n3. Fetch the converted data with `get_statement` using original data mode.\n4. Pass the benchmark statement id and original parsed transactions to `evaluate_benchmark`.\n5. Present extraction accuracy, integrity score, overall score, and any major failure categories. Cite the benchmark statement id and converted document content_hash.\n\n**Example prompt:** Convert and score the published bsb-004 benchmark statement.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}