메뉴
Install and configure the Preclinical CLI for healthcare AI safety testing. Use when the user mentions preclinical, wants to test a healthcare AI agent, or when any other preclinical skill needs the CLI installed.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
Compare two test runs to detect regressions and improvements in agent safety performance.
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.
| name | preclinical-setup |
| description | Install and configure the Preclinical CLI for healthcare AI safety testing. Use when the user mentions preclinical, wants to test a healthcare AI agent, or when any other preclinical skill needs the CLI installed. |
Ensure the preclinical CLI is installed and can reach the server.
preclinical --version
If not found, install: pipx install preclinical (preferred) or pip install preclinical. If pip fails with "externally-managed-environment", install pipx first (brew install pipx on macOS, sudo apt install pipx on Linux).
preclinical health --json
If it fails, the CLI defaults to http://localhost:3000. Configure a different server via:
export PRECLINICAL_API_URL=https://server-url.com~/.preclinical/config.toml with api_url = "https://server-url.com"preclinical agents list --json
If no agents, the user needs to create one first (via CLI or UI at http://localhost:3000). Supported providers: openai, vapi, browser, livekit, pipecat, elevenlabs.