Menü
Shared SearchCLI setup: install, authenticate, run doctor, and verify the local environment.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| 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.vs ... command in this shared workflow, first consult vs-product-qa to verify the current command surface, required flags, payload fields, input format, and allowed values. Only after that check may you finalize parameters and run the command.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_clivs-product-qa; return to this workflow only after the grounded product answer is complete.Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay script. It must not mutate scenes, apps, dictionaries, datasets, recall core parameters, or online defaults.
Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and request-level candidate testing; do not modify search scenes, app config, dictionaries, recommend scenes, or primary recall parameters.
V2 item-level onboarding driven entirely by the V2 OpenAPI: GetPresignedImportUrlV2 → PUT upload → AddInferDatasetSchemaTaskV2 → GetInferDatasetSchemaResultV2 → CreateDatasetV2 → data write → CreateApplicationV2 → AttachDatasetToApplicationV2. Backend handles schema inference end-to-end and auto-picks the primary key from `BizAttr`; the agent persists the inferred artifact locally, confirms it once with the user, dry-runs, then drives create / write / attach using the same persisted artifact. Use this whenever the user wants the shortest path from a raw item file to a fully wired Viking AI Search dataset (and optional application).
Answer Viking AI Search product questions, CLI usage questions, API/auth questions, configuration questions, and troubleshooting questions by grounding every claim in either the installed `vs` CLI's own output or official Volcengine documentation. Never fabricate.
Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-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.