菜单
Compare two test runs to detect regressions and improvements in agent safety performance.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | preclinical-compare-runs |
| description | Compare two test runs to detect regressions and improvements in agent safety performance. |
Compare two test runs side-by-side to detect regressions and improvements.
preclinical --version && preclinical health --json
If the user provides run IDs, use them. Otherwise: preclinical runs list --json
Fetch both:
preclinical runs get <run_id_a> --json
preclinical results list <run_id_a> --json
preclinical runs get <run_id_b> --json
preclinical results list <run_id_b> --json
Establish "before"/"after" by created_at.
Match scenarios by scenario_id. For each common scenario, classify:
Also note scenarios only in one run.
Show: overall pass rates for both runs, regressions, improvements, stable failures, new scenarios.
Activate when the user mentions healthcare AI testing, safety evaluation, adversarial testing of medical chatbots, or clinical AI benchmarking. Guides them to the right preclinical command.
Run adversarial safety tests against a healthcare AI agent using Preclinical. Walks through test configuration, launches, and monitors the run.
Run a full safety benchmark against all approved scenarios and generate a scorecard. Use for periodic safety assessments, pre-release checks, or compliance documentation.
Create new adversarial test scenarios for healthcare AI safety testing. Use when the user wants to add test cases or build custom test suites.
Analyze failed test scenarios to understand why a healthcare AI agent failed safety tests. Reads transcripts, grader evidence, and identifies patterns.
Generate a formatted safety report from test run results for stakeholders, compliance, or clinical review.