Dotty Av Test
BrettKinny/dotty-stackchan
Run local black-box voice tests against the physical Dotty robot by playing a TTS prompt through the workstation speakers while the C920 records video and room audio.
arkcli +deploy：普通创建推理接入点（Endpoint）的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里；但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外，必须改走 arkcli-infer-endpoint，不能由本 skill…
Install Arkcli Deploy
$ npx skills add volcengine/ark-cli --skill arkcli-deploy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install volcengine/ark-cli arkcli-deploy --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/arkcli-deploy .claude/skills/arkcli-deploy && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "arkcli-deploy" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-deploy into .claude/skills/arkcli-deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-deploy", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-deployType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add volcengine/ark-cli --skill arkcli-deploy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install volcengine/ark-cli arkcli-deploy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/arkcli-deploy .agents/skills/arkcli-deploy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "arkcli-deploy" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-deploy into .agents/skills/arkcli-deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-deploy", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add volcengine/ark-cli --skill arkcli-deploy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install volcengine/ark-cli arkcli-deploy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/arkcli-deploy .cursor/skills/arkcli-deploy && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "arkcli-deploy" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-deploy into .cursor/skills/arkcli-deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-deploy", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/volcengine/ark-cli.git --path skills/arkcli-deploy--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add volcengine/ark-cli --skill arkcli-deploy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install volcengine/ark-cli arkcli-deploy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/arkcli-deploy .gemini/skills/arkcli-deploy && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "arkcli-deploy" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-deploy into .gemini/skills/arkcli-deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-deploy", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install volcengine/ark-cli arkcli-deployInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add volcengine/ark-cli --skill arkcli-deploy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/arkcli-deploy .github/skills/arkcli-deploy && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "arkcli-deploy" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-deploy into .github/skills/arkcli-deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-deploy", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add volcengine/ark-cli --skill arkcli-deploy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install volcengine/ark-cli arkcli-deploy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/arkcli-deploy .opencode/skills/arkcli-deploy && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "arkcli-deploy" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-deploy into .opencode/skills/arkcli-deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-deploy", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
arkcli-deploy- GitHub stars
- 140
- Token cost
- ~2.6k tokens
- SKILL.md length
- 661 words
- Files
- 3 (incl. references)
- Skills in repo
- 25
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
arkcli +deploy：普通创建推理接入点（Endpoint）的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里；但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外，必须改走 arkcli-infer-endpoint，不能由本 skill…
- Works in 6 steps: 完全没给模型：执行一次有界查询，例如 arkcli models search… → 只给品牌、系列或家族名（例如 “Doubao”“Seed 2”）：执行一次… → 从同一次返回的 items 中读取… → …
- Tasks that involve Speech recognition and synthesis
- SKILL.md covers 创建意图中的模型澄清, 示例代码：+deploy 创建后自动渲染 + 独立命令…, 子命令穷举（只有这一个） and 反幻觉清单, plus 5 more sections
- Calls jq; reaches console.volcengine.com
What it does
Arkcli Deploy is an agent skill from volcengine/ark-cli. arkcli +deploy：普通创建推理接入点（Endpoint）的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里；但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外，必须改走 arkcli-infer-endpoint，不能由本 skill 截获。只有不命中该例外的普通创建，才在模型尚未选择、只给品牌/家族名，或当前轮只查询候选时进入本 skill 完成模型澄清；候选要用实时 search 返回的 name 与 primaryversion 组合成可直接传给 --model 的完整 ID。对已有 Endpoint 做获取/列表/启停/更新等全生命周期管理也走 arkcli-infer-endpoint；本 skill 只负责带产品护栏的一键创建。创建成功后会自动把多语言调用示例渲染到 ./ark-examples/<ep-id/。反触发：TTS/ASR/语音模型不能 +deploy，只能转 models search 说明广场可搜但 arkcli 不支持 Endpoint 创建。
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/arkcli-deploy.md` and `references/evals.md`).
It sits in Media & Creative, covering Speech recognition and synthesis and Text to speech and voice. The repository describes itself as: The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deployed endpoint in a single command, no API… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Speech recognition and synthesis
- Tasks that involve Text to speech and voice
Example prompts
- “/arkcli-deploy”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- 完全没给模型：执行一次有界查询，例如 arkcli models search --size 10 --format json。若用户已说明用途或模态，把对应的 keyword / --modality 加进同一次查询。
- 只给品牌、系列或家族名（例如 “Doubao”“Seed 2”）：执行一次 arkcli models search --size 10 --format json；家族名不是可直接传给 --model 的完整 ID。
- 从同一次返回的 items 中读取 name、primary_version、lifecycle_status 和模态等已有字段。优先保留 lifecycle_status=Published 且名称不含 internal / test 的候选；状态缺失或非…
- 0 个可用候选：说明本轮没有查到，并请用户补充用途、模态或关键词；不要猜一个继续。
- 1 个可用候选：复述本轮返回的完整 ID，请用户确认；若用户已要求本轮只查询，则停在这里。
- 多个可用候选：列出精简候选及完整 ID，请用户明确选择；若候选仍过多，按用户用途缩小范围，不能擅自选第一项。
What it can do on your machine
Read from SKILL.md and the folder at commit fb5b7be. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
console.volcengine.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Arkcli Deploy loads about 2.6k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 134 tokens; SKILL.md has 661 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from volcengine/ark-cli at commit fb5b7be, republished under its Apache-2.0 licence (© volcengine). 661 words, ~2,618 tokens.
Download SKILL.mdSave it as
.claude/skills/arkcli-deploy/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- arkcli-deploy
- description
- arkcli +deploy：普通创建推理接入点（Endpoint）的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里；**但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外，必须改走 `arkcli-infer-endpoint`，不能由本 skill 截获**。只有不命中该例外的普通创建，才在模型尚未选择、只给品牌/家族名，或当前轮只查询候选时进入本 skill 完成模型澄清；候选要用实时 search 返回的 `name` 与 `primary_version` 组合成可直接传给 `--model` 的完整 ID。对**已有** Endpoint 做获取/列表/启停/更新等全生命周期管理也走 arkcli-infer-endpoint；本 skill 只负责带产品护栏的一键创建。创建成功后会自动把多语言调用示例渲染到 ./ark-examples/<ep-id>/。反触发：TTS/ASR/语音模型不能 +deploy，只能转 models search 说明广场可搜但 arkcli 不支持 Endpoint 创建。
- version
- 1.4.9
- metadata.cliHelp
- arkcli +deploy --help
arkcli +deploy
CRITICAL — 路由例外必须先于任何命令：用户明确要求脚本化 / CI / 无护栏 / 原始 raw CRUD 创建 Endpoint 时，立即读取 ../arkcli-infer-endpoint/SKILL.md 并由它接管；在完成交接前禁止认证检查、模型查询或其他命令。
前置： 先用 Read 读 ../arkcli-shared/SKILL.md 获取共享认证/配置/写操作守卫规则。
创建意图中的模型澄清
只要用户的最终目标仍是“创建 / 新建 / 部署 Endpoint”，即使尚未给出完整模型 ID，也必须留在 arkcli-deploy 工作流；arkcli-models 此时只是临时调用的只读候选查询能力，不能把创建任务改路由成纯模型发现。
候选必须来自本轮 ArkCLI 的实时结构化输出，禁止从模型记忆、示例或旧版本号补全。
查询预算是当前用户回合恰好一次 Bash 调用。 在执行前一次性确定 keyword、过滤条件和 --size。models search 的 keyword 是单个 catalog 子串，不要把多个概念拼成带空格的短语：先选最能缩小范围的一个 ASCII token，其余条件放到同一次调用的 flags 或 jq 本地过滤。例如“豆包代码模型”用 keyword code，再在同一管道按 name 的 doubao|seed 过滤；“生图”用 seedream。不确定稳定 token 时宁可省略 keyword 并使用已有结构化 filter，禁止把未翻译的中文短语直接提交后再换词重试。若担心输出过长，把字段投影直接放进同一条管道，例如
arkcli models search "<keyword>" --size 0 --format json | jq -c '{items: [(.items // [])[] | {name, primary_version, lifecycle_status, input_modalities, output_modalities}]}'。
这次调用无论成功、空结果、截断还是失败，都不得换关键词、调大分页、重跑同一命令或为了重新格式化再调用一次 ArkCLI；只能使用已捕获的 stdout，信息不足就如实停止。
- 完全没给模型：执行一次有界查询，例如
arkcli models search --size 10 --format json。若用户已说明用途或模态，把对应的 keyword /--modality加进同一次查询。 - 只给品牌、系列或家族名（例如 “Doubao”“Seed 2”）：执行一次
arkcli models search <keyword> --size 10 --format json；家族名不是可直接传给--model的完整 ID。 - 从同一次返回的
items中读取name、primary_version、lifecycle_status和模态等已有字段。优先保留lifecycle_status=Published且名称不含internal/test的候选；状态缺失或非 Published 时只能如实标为未核实，不能称为“可部署”。完整模型 ID 按模型查询契约确定：primary_version非空时使用返回值精确拼成<name>-<primary_version>，为空时才使用<name>；这是结构化字段组合，不是从名称或日期规律猜版本。不要自行给name拼pro、lite或任何未返回的版本后缀。 - 0 个可用候选：说明本轮没有查到，并请用户补充用途、模态或关键词；不要猜一个继续。
- 1 个可用候选：复述本轮返回的完整 ID，请用户确认；若用户已要求本轮只查询，则停在这里。
- 多个可用候选：列出精简候选及完整 ID，请用户明确选择；若候选仍过多，按用户用途缩小范围，不能擅自选第一项。
澄清阶段的收敛边界：本回合第一次 search 返回后，禁止再次执行 models search，也不要对候选循环执行 models get、价格查询或其他详情调用。只有用户选定单个候选后又明确要求比较某个缺失属性，才在后续回合追加一次针对性查询。模型尚未唯一确定前，禁止执行 +deploy、infer endpoint create 或 Raw API 创建。
Endpoint 名称不应阻塞上述只读候选查询；模型选定后，再收集名称并确认最终创建参数。
新增 flag --set-default <modality>: 部署成功后自动把新 endpoint 设为 active profile 该 modality (text / image / video) 的默认资源。仅在真实部署成功且用户明确传 modality 时生效；失败仅 stderr warn，不阻断部署主流程。详见 ../arkcli-shared/references/profile-defaults.md。
写操作 + 计费：+deploy 创建在线推理 Endpoint 是真实写操作，会产生计费资源。该工作流依赖在线探测，不支持 --dry-run；执行前必须与用户显式确认最终参数。
模型开通是独立计费写动作，非交互环境一律不自动开通：若目标基础模型尚未开通，+deploy 会触发"开通模型"（账号级计费写）。在 agent / CI / 管道这类非 TTY 环境，开通被硬拒——--yes 也不放行（--yes 只在真人交互终端里用于跳过 [y/N]）。命中时 CLI 返回 model_activation_required + console 链接，你必须结束本轮、把"开通（计费）"这件事连同链接交还给真人，由真人在交互终端确认或在网页 console 开通。严禁自己补 --yes / echo Y / 设 ARKCLI_ALLOW_HEADLESS_ACTIVATION 替用户开通——你打印一句"请确认"然后同一轮自己加 --yes 跑掉，等于没问。ARKCLI_ALLOW_HEADLESS_ACTIVATION=1 只留给真·无人值守自动化（CI 流水线），不是 agent 该设的。
实名前置（开通类硬闸门）：+deploy 会触发开通模型，第一步先 arkcli auth status 读 volc_sso.identity.verified——false 即停并把实名页 https://console.volcengine.com/user/authentication/detail/ 贴给用户、暂停等待（详见 ../arkcli-auth/references/realname-gate.md）。不要先试 +deploy、撞到 model-id 无效 / 模型未开通报错再回头查实名——那些报错会把你带偏。
语音模型硬边界：TTS / ASR / 配音 / 朗读 / 播客 / 音色设计 / 实时语音交互，或模型名命中 doubao-seed-tts-*、doubao-seed-asr-*、seedasr-* 时，不要执行 +deploy。这些模型在 arkcli 当前只支持 models search 做广场发现；不能创建 Endpoint，也不能通过开通模型绕过。
示例代码：+deploy 创建后自动渲染 + 独立命令 +code-example
两条路径都可用，都走 OpenTOP OpenGetSampleCode：
+deploy创建成功后自动渲染：把该接入点的多语言调用示例写到./ark-examples/<ep-id>/（用 ep-id 当作可直接调用的 model id，示例直接调你刚建的接入点），并在 stderr 打一行落盘摘要。best-effort —— 取不到示例只软提示，不影响 Endpoint 创建/启动。- 独立命令
arkcli +code-example：按基础模型名/版本单独生成示例，转../arkcli-code-example/SKILL.md；注意它按 model-version 提供，部分版本后端无 group 会返回 not found，缺失时再降级到ark-examples/静态示例或方舟控制台示例代码页。
子命令穷举（只有这一个）
| 调用 | 说明 |
|---|---|
arkcli +deploy --name <ep-name> --model <model-id> [...] | 创建 Endpoint；执行即真实创建 |
⚠️ 没有
arkcli deploy .../arkcli endpoint create/arkcli +deploy create等子命令。整个能力就是一个+deploy命令加 flag。
反幻觉清单
- 交付前读取 返回值与验收边界：区分新建/复用、创建/推理验证、示例生成成功/软失败。以真实 stdout、stderr 和文件为证，不因示例或默认设置失败重复创建计费资源。
--name、--model必填- 模型版本、价格与额度只能引用本轮只读命令返回的结构化结果；不得编造模型版本或价格。查询失败或未登录时，明确标为“尚未核实”，不要用“典型价格”或猜测值代替
- 查询失败后不得补全依赖字段：认证、模型、价格或资源查询任一失败时，保留对应字段为“尚未核实”，并明确指出失败来源；不得继续断言具体金额、空闲计费策略、精确模型版本或“没有现存 Endpoint”
- 检查已有 Endpoint 时使用
arkcli resources list --format json后按返回字段筛选；不得添加未记录的--filter或其他resources list --help中不存在的 flag - JSON 类 flag（
--rate-limit/--moderation/--intelligent-router/--tags等）字段名一律 PascalCase：Rpm、Tpm、Strategy、Mode，不是rpm/tpm - 独立
+code-example的 flag 是--model（基础模型名/带版本 id）+--language，不是--endpoint-id：arkcli +code-example --model <id> --language python（细节见../arkcli-code-example/SKILL.md） +deploy创建成功后会自动把示例渲染到./ark-examples/<ep-id>/（按 ep-id）；想按基础模型名另出一份则跑+code-example- 模型未开通时
+deploy的开通在非 TTY 下被硬拒、--yes也不放行；禁止自己补--yes/echo Y/ 设ARKCLI_ALLOW_HEADLESS_ACTIVATION，必须把开通（计费）交还真人在终端 / console 处理 - 语音模型（TTS / ASR / 播客 / 音色 / 实时语音交互）广场可搜不等于可部署；命中这类模型时停在
arkcli models search <keyword>，不要给+deploy命令
Show full SKILL.md (284 more words)Show less
创建意图中的模型澄清
只要用户的最终目标仍是“创建 / 新建 / 部署 Endpoint”，即使尚未给出完整模型 ID，也必须留在 arkcli-deploy 工作流；arkcli-models 此时只是临时调用的只读候选查询能力，不能把创建任务改路由成纯模型发现。
候选必须来自本轮 ArkCLI 的实时结构化输出，禁止从模型记忆、示例或旧版本号补全。
先确定用户硬条件与关键词，初次用 models search "<keyword>" --size 10 --format json；无关键词就省略。关键词用真实名称/家族的子串，能力和模态用真实 flags，不把多个自然语言概念拼成模型名。已有完整本轮结果就复用。
- 完全没给模型：按用途/输出模态查询；没有用途时展示实时代表供选择，不从记忆列型号。
- 只有品牌/家族：用该家族关键词召回；空结果先按 search 的规范化与恢复链 校正一次，不把品牌当精确 ID。
- 候选字段：读取真实
display_name/name/primary_version/lifecycle_status/input_modalities/output_modalities/create_time/update_time。新接入优先 Published，排除名称明确标 internal/test 以及 Shutdown/Retiring 的推荐项；未知状态不等于可部署。版本非空才拼name-version，不猜日期；自定义模型保留cm-...身份。 - 排序与覆盖：默认严格按真实
create_time倒序，最新创建/发布的候选在前；只有用户明确要求“最近更新”才按update_time倒序。禁止因历史偏好或上文提过某旧型号就把它置顶；可在问题正文提醒，但不得改顺序或自造“推荐/主力/旗舰”标签。不能用名称、ID 内时间或 search 默认相关性冒充创建时间；时间缺失/不可解析时标明未知，不伪造排序。无偏好时展示 5–8 个代表，兼顾实际存在的文本、多模态、图像、视频；有硬任务条件就只列匹配者，不为凑数混入其他任务。label 使用原始展示名，description 附完整 ID、模态和状态。 - 0/1/N：0 个如实说明并补问一个关键条件；1 个复述真实 ID；N 个使用宿主提供的结构化选择能力，用户选定前停止，不替选第一项。只要求查询/命令时不创建。
- 恢复不等于无限重试：stderr 与 stdout 分离并检查退出码。先读取工具已保存的完整 JSON；确无完整捕获可把同一只读查询重取到文件，不能从截断预览生成选项。成功为空允许规范化关键词或放宽一个非硬性偏好并说明；鉴权/权限失败不当成空，不换身份。仍不完整/无匹配则报告边界与待补条件，不重复盲查。
- 回到创建流程：选定精确目标后才读取所需详情/真实请求字段。明确版本或模态不支持时停止；不能用 activate 修复错误版本。用户选模型不等于批准创建，最终按共享授权流程执行；
+deploy不支持--dry-run，不要发明预览 flag。
精简字段模板见 search reference。以下为对已保存完整候选的本地排序，不新增 API 请求：
jq '[.items[]
| select(.lifecycle_status == "Published")
| select((.name | test("internal|test"; "i")) | not)
| {display_name,name,primary_version,lifecycle_status,input_modalities,output_modalities,create_time}]
| sort_by(.create_time // "") | reverse' "$candidate_file"先检查顶层 items 为数组及关键字段是否齐全，缺时间只能标“时间未知”。该投影不是账号可部署性验证，不逐候选循环 get/价格接口；只补齐完成当前任务所需的证据。
路由判断
- 用户要创建 / 部署 Endpoint，但模型缺失或只有品牌 / 家族名 → 仍路由到本
arkcli-deployskill，按上节执行一次实时只读查询并让用户选择；不要直接创建 - 用户已有模型 ID + 想正式部署 → 复述
model/name/region；确认后执行arkcli +deploy --name <ep> --model <id> - 用户要部署 / 接入语音模型，或模型名看起来是
*-tts-*/*-asr-*/seedasr-*→ 转arkcli-models说明"只支持广场检索，不支持 Endpoint 创建" - 用户传入自定义模型 ID（
cm-xxxxx）时，真实创建前会先查是否已有引用该自定义模型且状态为Running的 Endpoint；若有则直接复用并输出已有endpoint-id，不会再创建第二个计费资源。该在线复用决策也是+deploy无法提供可靠离线 Client Preview 的原因之一 - 用户语气紧急要求"立刻创建" → 不要跳过确认，复述
model/name/region - 已通过
arkcli infer endpoint create拿到Id→ 不要再+deploy创建第二个，转arkcli-infer-endpoint；要调用示例转arkcli-code-example（按模型名生成）
反触发（路由到别处，附完整命令避免下游幻觉）
| 用户意图 | 路由到 | 完整示范命令 |
|---|---|---|
| 只想试模型效果 / 一次性生成 | arkcli-chat / arkcli-gen | arkcli +chat --model <id> '...' 或 arkcli +gen --model <id> '...' |
| 要某模型的调用示例 | arkcli-code-example | arkcli +code-example --model <model-id> --language python（按模型名/版本生成；缺失版本降级到静态示例或控制台示例页） |
| 只想发现 / 对比模型，尚无创建 Endpoint 意图 | arkcli-models | arkcli models search <keyword> 或 arkcli models list |
| 语音模型部署 / TTS 接入点 / ASR Endpoint | arkcli-models | arkcli models search <keyword>（只做广场发现；当前不支持 Endpoint 创建） |
| 401 / 鉴权失败 | arkcli-auth | arkcli auth status，必要时 arkcli auth login |
| profile / region / project 不符预期 | arkcli-config | 身份摘要用 arkcli auth whoami --format json；默认资源用 arkcli resources list --format json。显式 Profile 管理才使用可能同步 Key 的 profile show/list |
| 脚本化 / CI / 需要精细控制每个参数、跳过护栏 | arkcli-infer-endpoint | arkcli infer endpoint create --model <id> --name <ep> |
典型链路
- 从模型选择到正式接入：
arkcli auth status→arkcli models search/get→ 复述并确认最终模型、名称、计费影响 →arkcli +deploy ...（自定义模型若已有 Running Endpoint 会复用） - 从试用切换到正式接入：
arkcli +chat/arkcli +gen验证效果 → 复述最终参数并确认 → 真实创建 - 创建后做调用集成：
+deploy已把示例自动写到./ark-examples/<ep-id>/，直接用即可；想按基础模型名另出一份跑arkcli +code-example --model <model-id> --language <lang>（部分版本无示例时降级到ark-examples/静态示例或控制台示例页）
详细 flag、JSON 字段示例、错误码见 references/arkcli-deploy.md。
参考
- arkcli-chat -- 快速对话试用，不创建 Endpoint
- arkcli-gen -- 图片/视频一步生成
- arkcli-models -- 部署前确认模型 ID
- arkcli-code-example -- 已有 endpoint 时生成调用代码
- arkcli-shared -- 认证与全局参数
© volcengine, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/arkcli-deploy of volcengine/ark-cli.
- SKILL.md
- references/arkcli-deploy.md
- references/evals.md
Open the folder on GitHubat commit fb5b7be
Compare with similar skills
Arkcli Deploy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Arkcli Deploy this skillvolcengine/ark-cli | 140 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Dotty Av TestBrettKinny/dotty-stackchan | 113 | — | ~866 | Automated safety check: Notes | MIT | |
| Stepfun Asrdaymade/claude-code-skills | 1.4k | — | ~3k | Automated safety check: Pass | MIT | |
| Stepfun Ttsdaymade/claude-code-skills | 1.4k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Groq Core Workflow Bjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Voice AI Ttssundial-org/awesome-openclaw-skills | 663 | — | ~2.3k | Automated safety check: Notes | None |
Similar skills
Stepfun Asr
daymade/claude-code-skills
Transcribes Chinese/English audio with StepFun's stepaudio-3-asr-max via its SSE endpoint (not /v1/audio/transcriptions) — one call handles long-form audio with no chunking.
Stepfun Tts
daymade/claude-code-skills
Generates Chinese/Japanese speech with StepFun's Contextual TTS — default stepaudio-2.5-tts, stepaudio-3-tts for whisper/inline-() prosody.
Groq Core Workflow B
jeremylongshore/tons-of-skills-marketplace
A skill your agent uses when you need Groq's non-chat endpoints — transcribing or translating audio with Whisper, understanding images with Llama 4 vision, generating speech (TTS), or benchmarking…
Voice AI Tts
sundial-org/awesome-openclaw-skills
High-quality voice synthesis with 9 personas, 11 languages, streaming, and voice cloning using Voice.ai API.
Video Reference
zenstory-ai/video-recap-skills
按需把一部成片拆成可复用的制作参考：测镜头节奏与响度，标注段落与音轨分工，把原片事实与可迁移方法分开， 导出不含原片人名台词的 productionreference.json 供下次制作参考。不在默认生产路径上。
More from volcengine/ark-cli
All 25 skills in this repoArkcli API Explorer
volcengine/ark-cli
Inspect or invoke locally registered ArkCLI actions when product commands cannot cover a task.
Arkcli Code Example
volcengine/ark-cli
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…
Arkcli Config
volcengine/ark-cli
arkcli 本地配置管理。处理 profile 配置归因、update.mode 的 automatic/disabled 策略、config reset 与历史 yaml 排障；profile 类操作优先使用 arkcli profile <subcmd。
Arkcli Custommodel
volcengine/ark-cli
arkcli 自定义模型仓库管理：从 TOS 导入自定义模型、查询/筛选自定义模型、查看详情、改名、删除、查询可用量化模式、量化已就绪的模型。任何提到自定义模型 ID（cm-）的管理、部署准备，或要求用 cm- 直接对话/推理/试效果的边界判断，都必须使用本 skill。注意：查询火山公共基础模型（doubao 等 foundation models）走 arkcli-models；本…
Arkcli Docs
volcengine/ark-cli
检索、读取与总结方舟官方文档。用户给出 ark.volcengine.com 文档 URL 或 /docs/ 路径、要求读链接、官方说明、API 契约或必填字段，询问 CC Switch 等第三方客户端的方舟图形配置流程，以及官方网页读取失败时使用。不用于业务调用、资源操作、CLI 帮助或通用知识。
Arkcli Doctor
volcengine/ark-cli
arkcli doctor 统一入口，覆盖 CLI 健康、account、error、infer-endpoint、model、metrics、report 与 Ark 图片/视频来源特征验证。用户给 1-20 个媒体 URL 并问是否由 Ark/Seedance/Seedream 生成时，走 doctor +verify-origin：整批只披露并确认一次费用，确认前不发…
Related
Categories
Questions about Arkcli Deploy
What does Arkcli Deploy do?
arkcli +deploy：普通创建推理接入点（Endpoint）的统一首选入口。用户说『创建/新建/create 一个 endpoint/接入点』或『部署/上线/deploy 某模型』时优先走这里；但脚本化 / CI / 无护栏 / 原始 raw CRUD 创建是唯一例外，必须改走 arkcli-infer-endpoint，不能由本 skill…. Arkcli Deploy is an agent skill from volcengine/ark-cli.
When should I use Arkcli Deploy?
Arkcli Deploy fits situations like: tasks that involve Speech recognition and synthesis; tasks that involve Text to speech and voice.
How do I install Arkcli Deploy in Claude Code?
Run `npx skills add volcengine/ark-cli --skill arkcli-deploy -a claude-code`. Or copy the skill folder (skills/arkcli-deploy in volcengine/ark-cli) into .claude/skills/arkcli-deploy in your project. Claude Code loads it when a task matches its description.
How do I install Arkcli Deploy in Codex?
Run `npx skills add volcengine/ark-cli --skill arkcli-deploy -a codex`. Or copy the skill folder (skills/arkcli-deploy in volcengine/ark-cli) into .agents/skills/arkcli-deploy in your project. Codex loads it when a task matches its description.
Can I use Arkcli Deploy in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add volcengine/ark-cli --skill arkcli-deploy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/arkcli-deploy, .gemini/skills/arkcli-deploy, .github/skills/arkcli-deploy and .opencode/skills/arkcli-deploy in your project.
What does Arkcli Deploy need to run?
Going by SKILL.md and its folder, Arkcli Deploy needs the command-line tools its instructions call (jq).
Does Arkcli Deploy access the network?
SKILL.md names 1 domain. In commands or code: console.volcengine.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Arkcli Deploy safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Arkcli Deploy use?
Arkcli Deploy is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Arkcli Deploy use?
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.
What are the alternatives to Arkcli Deploy?
Skills that share tags, products or a category with Arkcli Deploy: Dotty Av Test (BrettKinny/dotty-stackchan, 113 stars), Stepfun Asr (daymade/claude-code-skills, 1.4k stars), Stepfun Tts (daymade/claude-code-skills, 1.4k stars) and Groq Core Workflow B (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Arkcli Deploy?
volcengine (a GitHub organization) maintains it in volcengine/ark-cli, which has 140 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on September 29, 2026.
Source: volcengine/ark-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.