// Shared SearchCLI setup: install, authenticate, run doctor, and verify the local environment.
Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.
Search runtime and scene management: run queries, inspect scenes, debug app readiness, and diagnose recall or config issues.
Provide system alias mapping for Search CLI. Invoke this skill when user mentions "Search CLI", "search_cli", or tries to execute search_cli commands.
Binds a dataset to an application with reviewed field config inference. Invoke when using `vs app dataset bind` and searchable/filter/suggest fields must be inferred and confirmed first.
Conversational search runtime: send messages, keep sessions consistent, and verify retrieval behavior and responses.
General item-level onboarding: understand structured item data, generate schema and config plans, create datasets, and create or bind apps only when the user explicitly asks for app-level setup.
| name | vs-shared |
| description | Shared SearchCLI setup: install, authenticate, run doctor, and verify the local environment. |
| category | shared |
| applies_to | codex, agents, external-agent |
| requires_cli | >=0.1.0 |
| keywords | install cli, auth import-env, auth login, llm login, doctor, first-time setup, profile switch, shared basics |
| commands | auth import-env, auth login, auth status, auth use, auth list, llm login, llm import-env, llm status, llm logout, doctor, skill list, skill install, app status, app diagnose, search run, chat run |
Use this skill when an external agent is setting up SearchCLI for the first time, or when it needs to check authentication, profiles, and local readiness.
Node.js >= 20 is installedscripts/install.shauth import-env: import VIKING_AK / VIKING_SK from the current shell into the local secure storeauth login: capture AK/SK interactively in a real terminalauth status: inspect the active profile, credential source, and regionauth use: switch profilesauth list: list saved profilesllm login: capture OpenAI-compatible LLM base URL, model, and API key interactively; stores the API key in the local secure storellm import-env: import VIKING_LLM_BASE_URL / VIKING_LLM_API_KEY / VIKING_LLM_MODEL into config plus secure storellm status: inspect the active LLM provider, model, base URL, and secret source without revealing the API keyllm logout: delete the stored LLM API key for a profiledoctor: check local dependencies, auth, and configurationskill list: inspect the published Viking skillsskill install: install Viking skills from the local repository checkoutapp status / app diagnose: inspect app readiness before blaming runtime behaviorsearch run / chat run: run a minimal verification requestBuilt-in region checklist (for --region and auth profiles):
cn-beijingap-southeast-1auth statusVIKING_AK / VIKING_SK, prefer auth import-envauth loginVIKING_AK / VIKING_SK in the current shell and then run auth import-envdoctor to verify the local environmentnpx skills add "<repo-url>" -y -gskill install all or install named skills from the local checkoutapp status or search/chat run for a minimal runtime checkSearch tuning query generation and LLM relevance judging need an OpenAI-compatible LLM API. Do not ask the user to paste an LLM API key into chat.
Use this priority order:
VIKING_LLM_BASE_URL, VIKING_LLM_API_KEY, and VIKING_LLM_MODEL, run vs llm import-env.vs llm login and wait for the user to enter the API key in that terminal.VIKING_LLM_BASE_URL, VIKING_LLM_API_KEY, and VIKING_LLM_MODEL in the current terminal, then run vs llm import-env.The first version supports only the openai-compatible protocol. Non-secret LLM metadata is written to ~/.viking/config.json; the API key is stored through the local secure credential store.
vs CLI surface (--help, command output, and observed runtime behavior), and explicit user-provided information.auth import-env and do not ask them to paste secrets into chatllm import-env or llm login; do not ask the user to paste LLM API keys into chatrequires_cli