菜单
Regenerate the arthur_genai_client package from the GenAI Engine OpenAPI spec. Use when the GenAI Engine API has changed, or when python/src/arthur_genai_client/ is missing after a fresh clone.
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
Arthur onboarding sub-skill — Step 4: Analyze the target repository (language, framework, existing instrumentation). Writes detection results to .arthur-engine.env.
Arthur onboarding sub-skill — Step 8: Configure an LLM provider for continuous evals (OpenAI, Anthropic, Gemini, Bedrock, or Vertex AI). Reads/writes .arthur-engine.env.
Arthur onboarding sub-skill — Step 9: Recommend and configure continuous LLM evals for the Arthur task. Reads credentials and eval provider from .arthur-engine.env.
Arthur onboarding sub-skill — Step 5: Instrument the target repository with Arthur tracing (Python SDK, Mastra TS, or OpenInference). Reads detection results from .arthur-engine.env.
Arthur onboarding sub-skill — Step 2: Ensure Arthur GenAI Engine is available (local install or remote). Reads/writes .arthur-engine.env.
Onboard an agentic application to Arthur GenAI Engine. Guides through engine connection, task setup, code instrumentation, trace verification, and eval configuration. Invoke from any agentic application repository.
| name | generate-client |
| description | Regenerate the arthur_genai_client package from the GenAI Engine OpenAPI spec. Use when the GenAI Engine API has changed, or when python/src/arthur_genai_client/ is missing after a fresh clone. |
| allowed-tools | Bash, Read |
The arthur_genai_client package under python/src/ is auto-generated and gitignored.
It must be present before running tests, linting (mypy), or using prompt management features.
node --version # needs Node.js (any recent LTS)
java -version # needs Java 11+
If either is missing, tell the user to install them and stop.
From the arthur-observability-sdk/ directory:
./scripts/generate_openapi_client.sh generate python
./scripts/generate_openapi_client.sh install python
generate python will:
openapi-generator-cli via npm if neededgenai-engine/staging.openapi.jsonpython/src/arthur_genai_client/install python runs uv sync to register the generated package in the venv.
python -c "from arthur_genai_client.models.agentic_prompt import AgenticPrompt; print('OK')"
If that prints OK, the client is ready. If it errors, re-run step 2.
python/src/arthur_genai_client/ — changes will be lost on the next regeneration.genai-engine/staging.openapi.json. If that file is missing, update it from the running GenAI Engine: curl http://localhost:3030/openapi.json > ../genai-engine/staging.openapi.json