Agents
elevenlabs/skills
Build voice AI agents with ElevenLabs. An agent skill from elevenlabs/skills.
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 VOLCINIT 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…
$ npx skills add volcengine/ark-cli --skill arkcli-auth -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install volcengine/ark-cli arkcli-auth --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-auth .claude/skills/arkcli-auth && 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-auth" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-auth into .claude/skills/arkcli-auth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-auth", 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-authType 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-auth -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install volcengine/ark-cli arkcli-auth --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-auth .agents/skills/arkcli-auth && 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-auth" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-auth into .agents/skills/arkcli-auth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-auth", 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-auth -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install volcengine/ark-cli arkcli-auth --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-auth .cursor/skills/arkcli-auth && 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-auth" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-auth into .cursor/skills/arkcli-auth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-auth", 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-auth--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-auth -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install volcengine/ark-cli arkcli-auth --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-auth .gemini/skills/arkcli-auth && 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-auth" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-auth into .gemini/skills/arkcli-auth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-auth", 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-authInstalls 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-auth -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-auth .github/skills/arkcli-auth && 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-auth" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-auth into .github/skills/arkcli-auth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-auth", 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-auth -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-auth --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-auth .opencode/skills/arkcli-auth && 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-auth" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-auth into .opencode/skills/arkcli-auth/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-auth", 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.
arkcli-autharkcli 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 VOLCINIT 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…
Arkcli Auth is an agent skill from volcengine/ark-cli. 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 VOLCINIT 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/ownertrn);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。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `references/api-key-query.md`, `references/arkcli-auth-init-volc.md` and `references/arkcli-auth-login.md`).
It sits in Backend & APIs, covering Authentication, 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.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit fb5b7be. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Arkcli Auth loads about 2.5k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 896 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
)时,用 `arkcli auth whoami`,不要去 `~/.arkcli/.env` 里手动解 JWTikey` 只列举并选择**普通 API Key 池**,写入 identity/.env 兼容凭证;它不读取或修复 Agent Plan 专属 Key、也不读取团队席位 Key。当前是 Plan profile 时优先使用 `profilte` 创建、验证并保存一把**普通 API Key**到当前 identity/.env 兼容凭证;TTY 必须确认,非交互环境收到 `requires_confirmation` 后必须走共享 Skill 的宿主确认流程;只发一次 `CAutomated 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.
The full file from volcengine/ark-cli at commit fb5b7be, republished under its Apache-2.0 licence (© volcengine). 896 words, ~2,453 tokens.
.claude/skills/arkcli-auth/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.CRITICAL — 开始前 MUST 先用 Read 工具读取 ../arkcli-shared/SKILL.md,其中包含认证闸门、配置排查与共享安全规则
CRITICAL — 用户目标是其他业务命令时,必须先判断是不是被认证阻塞,再决定是否进入本 skill。
CRITICAL — auth 是身份/TTY 工作流,全域不注册 --dry-run;不要生成该 flag。
⚠️ 0.1.16 变化总览(必读):
is_default profile.OwnerTrn,4-case 分别走 BuildFirstProfile (新建) / GUIDE_SKIP (复用) / 提示切 default / 提示新建。详见 docs/runtime/volc-sso.md。auth login --access-key / --secret-key 已注释,promptui 也移除"AK/SK"选项;SSO(火山)+ arkcli auth login --no-browser(根命令 flag, 不是 volc-sso 子命令 flag)是唯一登录入口。active_profile.{name,type,region,project,owner_trn} 和 profiles_summary[...];顶层 auth_method/logged_in/volc_sso/ark_api_key 等老字段全部保留(向后兼容)。arkcli profile:config init/list/show/switch/delete 已 deprecated,详见 ../arkcli-config/SKILL.md。BuildFirstProfile 的 project 步骤改为经 IAM ListProjects 拉当前身份名下真实 active project 列表交互选(拉取失败/无权限回退兜底 default,不阻断登录)。登录后想换 project 不必重登:arkcli profile project [<name>](拉同一列表重选,把 platform profile 重派生到新 project,个人版 plan profile 保留),详见 ../arkcli-profile/SKILL.md。arkcli auth login 交互式浏览器 SSO 分支支持借用本机 volcengine-cli 登录态:检测到 ve >= 1.0.45 且已 ve login 时,直接接管 STS 落一份 arkcli identity (identity_store/<key>/metadata.json.source="ve", 不写 IDToken/refresh_token/ClientID; STS 由 volcengine-go-sdk 内部持 refresh_token 自动 refresh)。用户视角: 少一次浏览器授权; agent 视角: auth_method 变成 "sts" 而非 "sso", 但 logged_in=true。检测失败 / ve 未登录 → 自动降级 arkcli 原生 SSO OAuth 流。详见 references/arkcli-auth-login.md 的"volcengine-cli 登录态借用"节。arkcli<!-- AK/SK 通道在 0.1.16 暂关 (见上方说明); 恢复后取消下条注释 -->
<!-- - 使用 AK/SK 做非交互登录 -->
arkcli auth whoamiVOLC_INIT_* 凭证,无交互引导 —— 用 arkcli init-volc(不是 SSO)云开发机 / CI 等已经把火山凭证注入成 VOLC_INIT_* 环境变量的场景,用 arkcli init-volc 一条命令、零交互地落一个火山 platform profile 并设为 default,让后续 arkcli / OpenCode 调用开箱即用(数据面用 API Key,控制面用 STS)。
auth login 的区别:init-volc 不登录、不交互、不联网,纯消费环境变量;本地终端用户首次引导仍走 auth login(SSO)references/arkcli-auth-init-volc.mdarkcli auth statusarkcli auth whoami,不要去 ~/.arkcli/.env 里手动解 JWTarkcli auth login volc-sso(不要只是"提示用户去跑")。SSO 是 0.1.16 唯一可用登录通道,覆盖控制面 BFF + 数据面绝大多数能力timeout=600000(10 分钟)open 失败、端口被占用、超时等)→ 不原地重试,把 stderr 贴回给用户,请用户手动在终端跑对应租户的登录命令(火山:arkcli auth login volc-sso)--no-browser(AK/SK 通道 0.1.16 暂关,提到 AK/SK 时告知并引导走这里):agent 终端通常非 TTY,--no-browser 现为两段式,不再阻塞读 stdin(旧版在沙箱必报 读取授权码失败: EOF —— 进程在拿到授权码前就被 EOF 打断):arkcli auth login --no-browser。它打印授权 URL 并以 JSON 输出 {"stage":"authorize_pending","authorize_url":"...","next_command":"..."} 后立即退出(不傻等)。把 authorize_url 原样转发给用户,请他在任意设备浏览器完成 SSO,复制页面显示的 base64 授权码回来。arkcli auth login --no-browser --code <授权码> 完成登录(读 Phase 1 落盘的 PKCE/state 换 token)。--code 必须连 --no-browser(单独写会报 --code 仅在 --no-browser 模式下有效)。~/.arkcli/.sso-pending.json、Phase 2 读它接力,两条命令须共享同一 HOME / 同一持久化卷(同一容器 / 开发机);跨容器或跨 HOME 派发会让 Phase 2 报「没有待完成的…会话」。期间不要动 ~/.arkcli/。--no-browser / --code 都挂在 auth login 根命令上,不是 volc-sso 子命令;auth login volc-sso --no-browser 会报 unknown flag。会话过期(TTL 10min) / 没有待完成的会话 → 重跑 Phase 1(确保同一 HOME);base64 解码失败 / state 不匹配(CSRF) / token 交换瞬时失败 → pending 仍在盘,TTL 内纠正后直接重试 Phase 2(贴对当前 authorize_url 的码,必要时从同一 URL 重新授权拿新码),不必重跑 Phase 1。arkcli auth login --no-browser 仍是一条命令交互式(打印 URL 后当场粘贴),行为不变。arkcli auth loginarkcli auth logoutauth status 是默认入口;不要上来就 loginauth logout 是破坏性操作,必须由用户明确提出auth status 会对敏感字段做掩码,可直接用于排障,并会展示当前生效的 project_nameauth login 成功后会输出 auth_method;凭证存储位置是实现细节,不再回显路径arkcli auth login volc-sso)与 auth apikey 都会在选中 API Key 之后写入凭证存储;0.1.16 final clean-slate 模型: 整 arkcli 同一时间只 active 一个 identity, 新 SSO 跟旧 sub 不一致时清空所有 profile (含跨 tenant) 重建platform / coding-plan 个人版使用普通 API Key;agent-plan 个人版使用 Scene=RealAgentPlanPersonal 的专属 Key;agent-plan-team / coding-plan-team 使用 GetSeatInfo 返回的席位 Key。普通池里“有 Key”不能证明 Agent Plan/团队版 Key 可用。CreateApiKey,再最多读 3 次状态。Agent Plan 专属记录存在但非 Active 时会询问是否轮转;确认后也只轮转一次、最多读 3 次状态。非 TTY、用户拒绝或无专属记录时绝不写。Restricted),CLI 会保留已选 region/project、从本轮候选中移除该失败类型,并重新让用户选择其他消费场景。失败类型不会再次 silent backfill,避免重复获取或二次轮转;这属于 profile 级重选,绝不会拿普通/Coding Plan Key 冒充 Agent Plan 专属 Key。volcengine-cli >= 1.0.45 且已 ve login 时, arkcli auth login 会先尝试借用其登录态直接落 arkcli identity (省一次浏览器授权)。落盘差异见 references/arkcli-auth-login.md: 不落 token.json (IDToken/refresh_token/ClientID 由 ve SDK 管), 但落 sts.json + metadata.json.source="ve"; auth whoami 显示 auth_method="sts" 而非 "sso", 是合法登录态。检测失败 / ve 未登录 → 自动降级 arkcli 原生 SSO OAuth。arkcli auth apikey 只列举并选择普通 API Key 池,写入 identity/.env 兼容凭证;它不读取或修复 Agent Plan 专属 Key、也不读取团队席位 Key。当前是 Plan profile 时优先使用 profile keys refresh 或对应 Plan 的轮转/席位流程,不能把 auth apikey 的 saved=true 解读为 Plan Key 已恢复。它也不能让广场语音模型获得 +chat / +gen / +deploy / +code-example / usage / pricing 能力。arkcli auth apikey create 创建、验证并保存一把普通 API Key到当前 identity/.env 兼容凭证;TTY 必须确认,非交互环境收到 requires_confirmation 后必须走共享 Skill 的宿主确认流程;只发一次 CreateApiKey,随后最多做 3 次只读状态检查,成功输出不包含明文 Key。它同样不能创建或修复 Agent Plan 专属 Key、团队席位 Key;已有 Profile 要切换默认 Key 时仍用 profile keys refresh/use。arkcli api apikey.list --params '{"PageSize":100}' --page-all --format json,不要跑 auth apikey — 后者是交互式选择并写入凭证存储,会改变当前生效 keyauth status 输出里的 ark_api_key 字段,不需要再调远端查询 Key 列表、辨别掩码与明文、向下游注入凭证前,先读 API Key 查询与交付。保留“查元数据 → 定位真实 ID → 必要时授权导出”的业务流程;不要默认回显全部明文。
arkcli-models、arkcli-chat、arkcli-gen、arkcli-deploy、arkcli-usage 被鉴权错误阻塞时,先回到这里../arkcli-config/SKILL.md| 用户怎么说 | 走哪个命令/skill |
|---|---|
| "我是谁/我的身份/当前用户/哪个账号/我自己的 IAM 用户 ID" | arkcli auth whoami |
| "查同事 zhangsan 的 IAM 用户 ID/查别人的 IAM 用户 ID" | 转 arkcli-profile(查看当前 profile 并列出可用 API Key)+ 提示用户使用 arkcli iam 命令(如有) |
| "API Key 泄露/废弃旧 Key/换新 Key/rotate/轮换 API Key" | 转 arkcli-plans:plans personal rotate-apikey 或 plans team rotate-apikey |
| "命令突然报 key 失效/401/InvalidApiKey 但我没换过 key"(疑似后端轮换) | 转 arkcli-profile:先 arkcli profile keys refresh 同步后端 key 再重试(遇失败才触发的反应式自愈,非预防性);refresh 救不了再看 references/auth-modes.md |
| "看账号有哪些 Key/Key 列表/只查不切" | arkcli api apikey.list,按上述 reference 分页查看元数据,不改变当前 Key |
| "看当前 Profile 的 Key 库存" | 转 arkcli-profile:说明同步影响后用 profile keys list |
| "切换默认 Key/用另一个 Key" | 转 arkcli-profile:arkcli profile keys use <key> |
| "创建一把普通 API Key" | arkcli auth apikey create;非交互环境按 requires_confirmation 走宿主确认流程 |
| "AK/SK 登录/access key/secret key" | 告知通道暂关:当前版本 AK/SK 登录通道暂时关闭,请使用 SSO 登录,运行 arkcli auth login |
| 命令 | 说明 |
|---|---|
arkcli auth status | 查看当前认证状态(凭证健康度) |
arkcli auth whoami | 查看当前认证身份(用户名 / IAM 用户 ID / 账号 ID 等),脚本与 Skill 用 |
arkcli auth login | 交互式选择登录方式(火山 SSO 浏览器 / 火山 SSO 无浏览器) |
arkcli auth login volc-sso | 浏览器 SSO 登录 |
arkcli auth login --no-browser | 无浏览器 SSO(cross-device)。TTY:一条命令交互式粘贴;非 TTY(agent/沙箱):Phase 1,打印 URL + authorize_pending JSON 后退出 |
arkcli auth login --no-browser --code <授权码> | 无浏览器 SSO Phase 2:把 base64 授权码喂回完成登录(agent/沙箱两段式的第二步) |
<!-- AK/SK 通道 0.1.16 暂关; 恢复后取消下行注释 -->
<!-- \| `arkcli auth login --access-key <ak> --secret-key <sk>` \| 非交互 AK/SK 登录 \| -->
| arkcli auth apikey | 选择普通 API Key 并写入对应 identity store;不代表 Agent Plan 专属/团队席位 Key 可用 |
| arkcli auth apikey create | 创建、验证并保存一把普通 API Key 到当前身份;不输出明文 Key,不处理 Plan 专属/席位 Key |
| arkcli auth logout | 删除本地凭证 |
© 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
SKILL.md and 8 other files (references) in skills/arkcli-auth of volcengine/ark-cli.
Open the folder on GitHubat commit fb5b7be
Arkcli Auth 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 Auth this skillvolcengine/ark-cli | 140 | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | |
| Agentselevenlabs/skills | 481 | — | ~6.5k | Automated safety check: Pass | MIT | |
| Voice AI Developmentmajiayu000/claude-skill-registry | 666 | 3 repos | ~4.4k | Automated safety check: Pass | MIT | |
| Elevenlabs Agentsjezweb/claude-skills | 1.1k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Agentstadaspetra/loop | 296 | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Dotty Av TestBrettKinny/dotty-stackchan | 113 | — | ~866 | Automated safety check: Notes | MIT |
elevenlabs/skills
Build voice AI agents with ElevenLabs. An agent skill from elevenlabs/skills.
majiayu000/claude-skill-registry
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps.
jezweb/claude-skills
Build conversational AI voice agents on the ElevenLabs platform.
tadaspetra/loop
Build voice AI agents with ElevenLabs. An agent skill from tadaspetra/loop.
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.
amd/skills
Makes this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API.
volcengine/ark-cli
Inspect or invoke locally registered ArkCLI actions when product commands cannot cover a task.
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…
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。
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…
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…
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 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 VOLCINIT 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…. Arkcli Auth is an agent skill from volcengine/ark-cli.
Arkcli Auth fits situations like: tasks that involve Authentication; tasks that involve Speech recognition and synthesis; tasks that involve Text to speech and voice.
Run `npx skills add volcengine/ark-cli --skill arkcli-auth -a claude-code`. Or copy the skill folder (skills/arkcli-auth in volcengine/ark-cli) into .claude/skills/arkcli-auth in your project. Claude Code loads it when a task matches its description.
Run `npx skills add volcengine/ark-cli --skill arkcli-auth -a codex`. Or copy the skill folder (skills/arkcli-auth in volcengine/ark-cli) into .agents/skills/arkcli-auth in your project. Codex loads it when a task matches its description.
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-auth -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-auth, .gemini/skills/arkcli-auth, .github/skills/arkcli-auth and .opencode/skills/arkcli-auth in your project.
SKILL.md names no scripts, command-line tools or credentials: Arkcli Auth is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Arkcli Auth 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.
About 2.5k tokens (SKILL.md is roughly 9.8k 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 12k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Arkcli Auth: Agents (elevenlabs/skills, 481 stars), Voice AI Development (majiayu000/claude-skill-registry, 666 stars), Elevenlabs Agents (jezweb/claude-skills, 1.1k stars) and Agents (tadaspetra/loop, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.