volcengine

arkcli doctor 诊断入口：用于火山方舟 Ark 报错、资源状态、用量配额、性能指标、错误码解释与修复建议；覆盖 doctor、doctor error、doctor infer-endpoint、doctor model、doctor metrics。用户给 Ark 错误码或错误 JSON、ep-xxx 接入点、模型名，问为什么报错、怎么修、状态/健康、用量/配额、限流、错误率、P99、Cache 命中率、接入点慢/挂、模型是否可用时使用；用户说诊断、体检、健康检查、排查、自助修复、看指标/监控也使用。模型名加失败、慢、超时、限流、异常、健康、配额等体检语义时走 doctor model，不因 seedream/seedance/生成视频关键词误触发 arkcli-gen。内容审核、敏感内容、PolicyViolation 等拦截诊断也归 doctor。安装、登录、profile、认证配置问题归 arkcli-shared 或 arkcli-auth。

火山方舟 Ark 图片/视频生成入口：用户要生图、画图、生成图片/视频、图生图、图生视频、参考图/视频/音频生成，或明确使用 seedream/seedance 创作新内容时使用 arkcli +gen。+gen 按当前 profile 的可用资源与模型 supported_params 生成；图片同步返回，视频提交后返回 task_id/status，需用 --wait 或 arkcli gen get/list 轮询并下载结果。反触发：用户问失败原因、失败率、模型健康、持续慢/超时/限流、配额是否够、内容审核/敏感内容/PolicyViolation 拦截怎么解决时，走 arkcli-doctor 的 doctor model 或 doctor error，不走本 skill。单条视频 queued/还在跑通常是异步任务未完成，仍用 gen get/list 查结果；跨任务统计性失败或持续异常才转 doctor。

arkcli helper:把 Claude Code / Codex / OpenCode / OpenClaw / Trae 配到火山方舟 Plan。用户说给当前或某个 Agent 配 MCP、豆包搜索、联网搜索、dataPro、OpenViking 时,用 `arkcli helper mcp`(只注入 MCP,不改 model);要连 model/provider 一起配用 `helper configure`;查状态用 `helper list`;移除注入用 `helper reset`。MCP 仅 Agent Plan 支持:个人版 agent-plan 配豆包搜索、dataPro、OpenViking 数据面/控制面;团队版 agent-plan-team 只配豆包搜索 + dataPro。Codex 支持 profile/global 配置范围;Trae 仅注 MCP,支持 `--scope project`。`helper supabase` 不是 MCP,用于安装 byted-supabase-cli + skill 并注入火山登录态。反触发:安装 arkcli skills → arkcli-connect;登录/401/鉴权 → arkcli-auth;生图生视频 → arkcli-gen。

arkcli 推理接入点**管理**能力：对**已有** Endpoint 做获取、列表、启动、停止、删除、更新（生命周期管理 + 启停 + 销毁）。优先使用产品命令 `arkcli infer endpoint ...`，而不是直接调用 Raw API。**反触发（重要）：用户说『创建/新建/create/部署/deploy 一个 endpoint/接入点』这类新建接入点的意图，一律走 arkcli-deploy（`+deploy`），不要用本 skill 的 `infer endpoint create`**；本 skill 的 `create` 仅用于脚本化 / CI / 需要无护栏的可预测 raw CRUD 行为（不做复用检查、不渲染示例）、且明确要绕过 +deploy 工作流护栏的场景。TTS/ASR/语音模型连 raw create 也不要引导，只能转 models search 说明 arkcli 不支持 Endpoint 创建。

ARK 套餐管理(Agent Plan / Coding Plan,个人版 + 企业版):查询持有 / 购买 / 续费 / 模型清单 / 轮换 APIKey,**以及企业版席位的全部管理操作**:列出席位(`plans team seat-list`)、给员工分配席位(`plans team seat-assign`)、查谁绑了哪个 seat、轮换席位 APIKey(`plans team rotate-apikey`)。命中关键词:套餐 / 买 / 续费 / 列席位 / 看 seat 绑定 / 谁绑了哪个 seat / 给员工分席位 / 解绑 / 团队席位 admin 视图 / 轮换 APIKey。**用量类问题(还剩多少额度 / 用了几成 / 每个 seat 用了多少)走 [arkcli-usage](../arkcli-usage/SKILL.md)。**动词路由:**列 / 绑 / 分 / 轮换 / 解绑** → 这里;**用 / 消耗 / 多少** → arkcli-usage。另含 harness-status:只读查看本机 AI Agent(claude-code/codex/opencode/openclaw/trae)上 Agent Plan 内置 MCP(豆包搜索/dataPro/OpenViking)装没装、key 就没就绪;命中:我的 MCP 装好了吗 / 查 MCP 安装状态 / 看 agent 上的 MCP / harness 状态。

arkcli 认证管理：交互式登录、Volc SSO 登录、查看状态、退出登录、生成 ARK API Key (apikey)、以及云开发机/CI 用 `arkcli init-volc` 从 VOLC_INIT_* 环境变量无交互引导 platform profile。0.1.16 起 SSO 登录走 Gate 1+2 自动绑定 Profile 切面 (type/region/project/owner_trn)；AK/SK login 通道暂关。当用户需要初始化凭证、排查鉴权问题、切换认证方式、生成或重选 ARK API Key、或在已注入凭证的环境无交互引导时使用。反触发：用户问 TTS/ASR/语音模型能力、接入或调用时，不要引导 `auth apikey`，只转 models search 说明 arkcli 当前仅支持广场发现。

arkcli +code-example：为指定基础模型生成多语言（Python / Go / Java / Node / curl）调用示例代码并写入本地文件。数据源是火山方舟 OpenTOP OpenGetSampleCode。当用户需要拿某个基础模型的 SDK / curl 调用示例、保存为本地接入模板时使用。反触发：TTS/ASR/语音模型没有 arkcli 示例代码路径，不能靠补版本解决，只能转 models search 说明当前不支持。

arkcli +connect：将 arkcli 内嵌的 AI skills 安装到本机检测到的所有 AI Agent 中，支持安装、列出已支持 agent、卸载。当用户需要将 arkcli 能力同步到 Claude Code 等本地 agent 时使用。

Search, read, remember, or manage durable OpenViking memories and resources when prior context is relevant.

Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures important facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites check, plugin install through OpenClaw's plugin manager first, with ov-install only as a backup path, wizard-based configuration, slot activation, gateway restart, verification, plus multi-tenant root-key support, multi-instance, and uninstall. Trigger when the user says any of: "install OpenViking", "set up memory", "configure memory plugin", "add long-term memory", "connect to OpenViking server", "RAG", "semantic memory", "帮我装 OpenViking", "配置记忆插件", "安装记忆功能", "接入 OpenViking", "我有一台 OpenViking 服务器". The user does NOT need to know any CLI commands — the agent runs everything and only asks for a few values. This skill assumes the OpenViking server is already running. If the server is not ready, the skill tells the user to con

Load relevant OpenViking experience memories via case-linked experience candidates before solving a task.

Load when an agent needs to add, manage, browse, search, modify, or remove resources in OpenViking. Trigger on explicit user requests about resource management or context search, when the user mentions `ov add-resource`, `ov task watch`, `ov export`, `ov import`, `ov backup`, `ov restore`, `ov ls`, `ov tree`, `ov read`, `ov write`, `ov mkdir`, `ov rm`, `ov mv`, `ov find`, `ov search`, `ov grep`, `ov glob`, or when an agent needs to inspect, search, or organize the `viking://resources/` namespace.

Use OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an OpenClaw agent. For first-time plugin installation, use the install-openviking-memory skill instead.

Load when the user asks to add, import, compile, or ingest a research paper/PDF into OpenViking, especially when they mention ov-add-paper, ARA, claims, evidence, figures, tables, or paper-to-OV knowledge resources.

Load when an agent needs to manage, install, update, remove, or validate OpenViking skills via the `ov skills` CLI. Trigger on explicit user requests about skill management, when the user mentions `ov skills`, `install skill`, `update skill`, `delete skill`, `validate skill`, or when an agent needs to discover what skills are available on the OpenViking server.

Use when the user explicitly types `ov dream` or `ov recall <query>` and the request should be routed to the OpenViking sync/recall CLI instead of handled as normal chat.

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.

Conversational search runtime: send messages, keep sessions consistent, and verify retrieval behavior and responses.

Recommend runtime and scene management: run recommendation requests, manage recommend scenes, and verify the basic recommendation path.

Create and manage Volcengine cloud resources using the Volcengine CLI (`ve` command). Supports all Volcengine services including ECS, VPC, CLB, RDS, Redis, and more. Trigger this skill whenever the user asks to create, query, modify, or delete cloud resources on Volcengine, mentions the `ve` command, says "volcengine CLI", or describes infrastructure tasks such as "create an ECS instance", "set up a VPC", "list security groups", "allocate an EIP". Also trigger on Chinese prompts mentioning "火山引擎" or "火山" (e.g., "火山引擎上有哪些 ECS"、"查一下我火山的云服务器"、 "火山引擎创建一个 VPC"、"火山的 Redis 实例列一下"). Also trigger when the user encounters errors from `ve` commands and needs troubleshooting help.

Manage Volcengine AI Native BaaS for Supabase (AIDAP) database workspaces as a deployment database provider. Use when the user asks for Volcengine Supabase, AIDAP PostgreSQL, AIDAP database workspace setup, branch management, API keys, endpoint or database connection information, service activation, enterprise real-name verification, SQL execution, migrations, Edge Functions, Storage buckets, TypeScript type generation, or using AIDAP as the database for a Volcengine deployment. Prefer `ve aidap` for control-plane operations; use bundled scripts only for Supabase data-plane APIs missing from the current `ve` CLI.

Deploy a local project directory or Git repository to Volcengine as a running, reachable cloud service. USE WHEN: deploy to Volcengine, deploy to 火山引擎/火山, deploy this repo/project, publish current code, launch the app, run it in the cloud, expose it as a service, deploy to ECS/VKE/veFaaS, run on ECS, push to VKE, deploy as serverless/FaaS, or the user wants the agent to choose a Volcengine hosting target. If the user only asks which Volcengine deployment target to choose, use `volcengine-prepare` skill first. Not for creating a single standalone resource — use `volcengine-cli` skill for that.

Use Terraform/IaC for Volcengine resources only when the user explicitly chooses Terraform/IaC, already has a Terraform workflow/state, or confirms they need plan/diff/drift/destroy safety for VKE, managed databases/cache/storage, load balancers, domains/certificates, logging/monitoring, or team-managed infrastructure.

火山引擎官方文档检索与全文获取技能：对火山引擎官方文档站（www.volcengine.com/docs）做语义检索并抓取正文。Use when 用户咨询火山引擎产品的概念、用法、计费规则、部署步骤、最佳实践、服务条款/协议等可在官方文档中找到解释的问题，或用户直接给出火山引擎官方文档链接（www.volcengine.com/docs/...）需要取全文时。

Use when the user wants to deploy a local directory or GitHub repository to Volcengine and needs the project analyzed, the app shape understood, and a ranked recommendation across ECS, VKE, and veFaaS before choosing an execution path. Also trigger when the user asks "what deploy mode should I use", "is this repo ready for Volcengine", or "check my repo before deploying". This skill prepares the decision; `volcengine-deploy` skill performs the chosen deployment, and `volcengine-iac` skill is used only when the user chooses Terraform/IaC or the task already has an IaC workflow.

Use when the user asks to analyze, consult, setup, manage, configure, or design a Volcengine Landing Zone, including organization, accounts, finance, identity, cloudtrail, or network infrastructure.

Generate accurate Volcengine SDK examples by locating an API with the bundled local ranker, fetching its API Explorer swagger, and calling api/common/explorer/make-code with user-provided Params. Use when the user asks how to write Volcengine SDK code, generate SDK samples, or call a Volcengine API in Python, Go, Java, PHP, cURL, Node.js. Supports Chinese and English API names such as "角色扮演", "AssumeRole", or "STS AssumeRole". Also use for explicit SDK configuration questions about retry, timeout, AK/SK, STS, AssumeRole, temporary credentials, proxy, connection pooling, SSL, debug mode, request signing, response parsing, and error handling. If the user only needs API parameters, enum values, required fields, error codes, response schemas, pagination, or API comparisons, hand off to volcengine-api. If they need CLI-based operations, hand off to volcengine-cli.

音视频剪辑，涵盖音视频拼接、裁剪、合成等能力。包含能力：add-image-to-video, add-subtitle-to-video, adjust-audio-speed, adjust-video-speed, adjust-video-volume, apply-video-filter, concat-audio, concat-video, extract-audio, fade-audio, fade-video-audio, flip-video, image-to-video, mix-audio, mux-audio-video, trim-audio, trim-video。当用户需要使用 editing 域的 MediaKit CLI 能力时触发。

1. mediakit-cli: supports a variety of operations such as audio/video processing, editing, and images, with some capabilities covering both cloud and local modes; 2. mediakit-cli shared: environment checks, initialization config, command structure, authentication config, async task responses, and error handling.

视频处理，涵盖视频画质增强、视频理解、字幕擦除等能力。包含能力：analyze-video-highlights, analyze-video-storyline, asr-subtitles, enhance-video, enhance-video-generative, erase-video-subtitle, erase-video-subtitle-pro, generate-highlights-microdrama, generate-highlights-minigame, matte-greenscreen-video, matte-portrait-video, probe-video-metadata, segment-scenes, video-ocr。当用户需要使用 video 域的 MediaKit CLI 能力时触发。

音频处理，涵盖音频处理和增强、内容理解等能力。包含能力：separate-voice, probe-audio-metadata。当用户需要使用 audio 域的 MediaKit CLI 能力时触发。

图像处理，涵盖图像压缩、图像增强、AI处理等能力。包含能力：image-ocr, erase-image, remove-image-background, enhance-image, evaluate-image-quality。当用户需要使用 image 域的 MediaKit CLI 能力时触发。

Command-line interface for HiAgent Python SDK - Observe service (API Token, Trace Spans) via CLI

当用户想使用 HiAgent 观测(observe)能力（API Token、Trace Spans 查询）时，务必使用这个技能给出可直接执行的 cli-anything-hiagent observe 命令与排障步骤。尤其适用于用户提到 agent-harness、cli_anything、--json、workspace-id、custom-app-id、VOLC_ACCESSKEY/VOLC_SECRETKEY、observe token、observe trace，以及希望用命令行(cli-anything-hiagent / python -m cli_anything.hiagent_sdk)。trace-ai-process / trace-ai-history / alert-ai-process / RuleID / IsStream

Hibot Go SDK 端到端测试上传的最小可解析 Skill。 当用户要求执行 pulse check / 心跳检查 / 排障状态查询时，Agent 应当 调用本 skill 并返回结构化响应（包含字面量 PULSE_OK_E2E）。

Use tos-cli for ByteCloud TOS object storage work. Trigger this skill when a user asks an AI agent to inspect, configure, list, upload, download, sync, delete, presign, diagnose, or automate ByteCloud TOS resources with the tos-cli command-line tool.

Use ve-adrive-cli for Volcengine A-Drive file storage work. Trigger this skill when a user asks an AI agent to inspect, configure, list, upload, download, sync, delete, create folders, diagnose, or automate A-Drive resources with the ve-adrive-cli command-line tool.

Use ve-tos-cli for Volcengine TOS object storage work. Trigger this skill when a user asks an AI agent to inspect, configure, list, upload, download, sync, delete, presign, diagnose, or automate Volcengine TOS resources with the ve-tos-cli command-line tool.

Generates AI-authored code reading guides from a project or module. Invoke when user asks to read code, summarize architecture, and write a guide document.

Generates AI-authored code reading guides from a project or module. Invoke when user asks to read code, summarize architecture, and write a guide document.

How to answer weather questions. Use whenever the user asks about the weather in a city.

Manage OpenViking collections (OV libraries) from the command line with `ov-cp` — list / create / get / usage / get the data-plane API key / delete. Use when the user wants to provision or inspect an OpenViking library, fetch a library's data-plane API key, do the create→get-key cold-start, or otherwise drive the OpenViking control plane (topapi). Authenticates with an Ark AgentPlan ApiKey.

Hibot 端到端测试上传的最小可解析 Skill。 当用户要求执行 pulse check / 心跳检查 / 排障状态查询时，Agent 应当 调用本 skill 并返回结构化响应（包含字面量 PULSE_OK_E2E）。