
Onboard an agentic application to the Arthur SaaS Platform (platform.arthur.ai). Guides through authentication, workspace selection, engine deployment, model creation, code instrumentation, trace verification, and eval configuration.
--- name: arthur-onboard-platform-workspace description: Arthur onboarding sub-skill — Platform Step 3: Select or create a workspace in Arthur Platform. Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write --- # Arthur Onboard — Platform Step 3: Select or Create Workspace **Goal:** Establish `ARTHUR_PLATFORM_WORKSPACE_ID` and `ARTHUR_PLATFORM_WORKSPACE_NAME` in `.arthur-engine.env`. ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `AR
--- name: arthur-onboard-platform-access description: Arthur onboarding sub-skill — Platform Step 2: Authenticate to Arthur Platform using service account credentials (OAuth2 client credentials). Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write --- # Arthur Onboard — Platform Step 2: Authenticate to Arthur Platform **Goal:** Establish `ARTHUR_PLATFORM_CLIENT_ID` and `ARTHUR_PLATFORM_TOKEN` in `.arthur-engine.env`. ## Read State ```bash cat .arthur-engine.env 2>/dev/null || e
--- name: arthur-onboard-oss-engine description: Arthur onboarding sub-skill — Step 2: Ensure Arthur GenAI Engine is available (local install or remote). Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write, Edit, Task --- # Arthur Onboard — Step 2: Ensure Arthur GenAI Engine Is Available **Goal:** Establish `ARTHUR_ENGINE_URL` and `ARTHUR_API_KEY` in `.arthur-engine.env`. ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGIN
--- name: arthur-onboard-evals description: 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. allowed-tools: Bash, Read --- # Arthur Onboard — Step 9: Recommend & Configure Continuous Evals ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, `ARTHUR_TASK_ID`, `ARTHUR_EVAL_PROVIDER`, `ARTHUR_EVAL_MODE
--- name: arthur-onboard-task description: Arthur onboarding sub-skill — Step 3: Set up an Arthur Task (create or select). Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write, Edit --- # Arthur Onboard — Step 3: Set Up Arthur Task **Goal:** Establish `ARTHUR_TASK_ID` in `.arthur-engine.env`. ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, and `ARTHUR_TASK_ID` from the output. **State write hel
--- name: arthur-onboard-prompts description: Arthur onboarding sub-skill — Step 6: Extract prompts from the target repository and register them with Arthur Engine. Reads credentials from .arthur-engine.env. allowed-tools: Bash, Read, Task --- # Arthur Onboard — Step 6: Extract & Register Prompts ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, `ARTHUR_TASK_ID`. --- ## Extract Prompts via Sub-agent Delegate
--- name: arthur-onboard-analyze description: Arthur onboarding sub-skill — Step 4: Analyze the target repository (language, framework, existing instrumentation). Writes detection results to .arthur-engine.env. allowed-tools: Bash, Read --- # Arthur Onboard — Step 4: Analyze Repository **Goal:** Detect language, framework, and existing instrumentation. Write results to `.arthur-engine.env`. ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` --- ## Detect
--- name: arthur-onboard-platform-model description: Arthur onboarding sub-skill — Platform Step 5: Gate on application type, create an Agentic Model on Arthur Platform, and retrieve GenAI Engine task connection info. Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write --- # Arthur Onboard — Platform Step 5: Create Agentic Model **Goal:** Gate on application type; for Agentic applications, create a Project and Agentic Model on the platform, then retrieve GenAI Engine task connect
Arthur onboarding helper — Refresh Arthur Platform OAuth2 token using arthur_client. Reads CLIENT_ID/SECRET from .arthur-engine.env, writes ARTHUR_PLATFORM_TOKEN back to state.
--- name: arthur-onboard-verify description: Arthur onboarding sub-skill — Step 7: Verify that traces are flowing from the instrumented application to Arthur Engine. Reads credentials from .arthur-engine.env. allowed-tools: Bash, Read --- # Arthur Onboard — Step 7: Verify Instrumentation ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, `ARTHUR_TASK_ID`. --- ## Tell the User to Run Their Application Show the
--- name: arthur-onboard-eval-provider description: 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. allowed-tools: Bash, Read, Write --- # Arthur Onboard — Step 8: Configure Eval Model Provider ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL` and `ARTHUR_API_KEY`. --- ## Check Existing Providers ```bash cu
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: arthur-onboard-instrument description: 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. allowed-tools: Bash, Read, Write, Edit, Task --- # Arthur Onboard — Step 5: Instrument Code ## Read State ```bash cat .arthur-engine.env 2>/dev/null || echo "(no state file)" ``` Parse `ARTHUR_ENGINE_URL`, `ARTHUR_API_KEY`, `ARTHUR_TASK_ID`, `ARTHUR_DETECTED_LANGU
--- name: arthur-onboard-platform-engine description: Arthur onboarding sub-skill — Platform Step 4: Ensure an Arthur Engine (data plane) is registered and active in the selected workspace. Reads/writes .arthur-engine.env. allowed-tools: Bash, Read, Write, Task --- # Arthur Onboard — Platform Step 4: Ensure Arthur Engine Is Registered **Goal:** Establish `ARTHUR_PLATFORM_ENGINE_ID` and `ARTHUR_PLATFORM_ENGINE_URL` in `.arthur-engine.env`. > **Important:** Arthur GenAI Engines installed with `
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.
Set up the GenAI Engine development environment. Use when starting work on the project for the first time, or when environment needs to be reset. Handles uv, PostgreSQL, migrations, and environment variables.
Run the arthur-observability-sdk integration tests. These build the SDK wheel into a fresh venv and verify OTLP telemetry delivery end-to-end. Use when you want to confirm the installable wheel works correctly.
## Changes to review Read the git diff from the file path provided as the first argument: $0 ## Target docs - docs/getting-started.md — Arthur init, session/user/attributes helpers, instrumentation - docs/prompt-management.md — get_prompt, render_prompt, span attributes ## Update rules - Changes to arthur.py (session/user/attributes, instrument_* methods) → getting-started.md - Changes to _client.py or arthur.py prompt methods → prompt-management.md - Pure refactors with no behaviour change
Start the GenAI Engine backend server and frontend UI. Use when you need to launch the API server and the frontend locally.
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.
Start the GenAI Engine frontend UI dev server. Use when you need to launch the React app locally.
Run the arthur-observability-sdk unit tests. Use when you want to verify SDK logic without building a wheel or spinning up external services.