{"slug":"docxology-infrastructure-benchmark","source_name":"docxology/infrastructure-benchmark","name":"Docxology/Infrastructure Benchmark","description":"Deterministic benchmark harnesses for public template exemplars. Use when scoring generated project outputs against benchmark manifests, refreshing the default template smoke manifest, checking publication-readiness rubrics, or adding bounded no-network readiness checks for public template outputs.","version":1,"lift":{"pass_rate_delta_pts":56.52,"pass_rate_pct":91.3,"total_cases":23,"passed_cases":21,"tokens_delta_pct":-46,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-04T00:06:40.187513+00:00"},"skill_score":0.913,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":56.52,"with_pass_pct":91.3,"without_pass_pct":34.8,"tokens_delta_pct":-46,"turns_delta_pct":0,"total_cases":23,"cases_aggregated":21,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-04T00:06:40.187513+00:00","run_id":"27703b5d-46b7-4fa7-a155-bc6df68e65de","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"Apache-2.0","install_count":0,"manifest_hash":"cc46612a456c9e057e9b3a240d3f8bca0df92cebd16fad39d5afa17a44d947c3","raw_url":"https://app.decimal.ai/s/docxology-infrastructure-benchmark/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/docxology-infrastructure-benchmark"}