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.
ARK 用量查询:usage stats(Token / 请求数,5-30 分钟延迟)、usage plan / usage balance --type plan(套餐额度快照)、usage plan-details(仅 Agent Plan 按模型时间序列,套餐内/外拆分)、usage balance(余额:免费额度 / 媒资库 / 套餐)、usage seats…
Install Arkcli Usage
$ npx skills add volcengine/ark-cli --skill arkcli-usage -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install volcengine/ark-cli arkcli-usage --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-usage .claude/skills/arkcli-usage && 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-usage" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-usage into .claude/skills/arkcli-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-usage", 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-usageType 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-usage -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install volcengine/ark-cli arkcli-usage --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-usage .agents/skills/arkcli-usage && 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-usage" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-usage into .agents/skills/arkcli-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-usage", 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-usage -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install volcengine/ark-cli arkcli-usage --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-usage .cursor/skills/arkcli-usage && 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-usage" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-usage into .cursor/skills/arkcli-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-usage", 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-usage--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-usage -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install volcengine/ark-cli arkcli-usage --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-usage .gemini/skills/arkcli-usage && 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-usage" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-usage into .gemini/skills/arkcli-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-usage", 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-usageInstalls 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-usage -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-usage .github/skills/arkcli-usage && 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-usage" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-usage into .github/skills/arkcli-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-usage", 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-usage -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-usage --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-usage .opencode/skills/arkcli-usage && 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-usage" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-usage into .opencode/skills/arkcli-usage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-usage", 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-usage- GitHub stars
- 140
- Token cost
- ~2.5k tokens
- SKILL.md length
- 831 words
- Files
- 6 (incl. references)
- Skills in repo
- 25
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
ARK 用量查询:usage stats(Token / 请求数,5-30 分钟延迟)、usage plan / usage balance --type plan(套餐额度快照)、usage plan-details(仅 Agent Plan 按模型时间序列,套餐内/外拆分)、usage balance(余额:免费额度 / 媒资库 / 套餐)、usage seats…
- Works in 5 steps: 区分命令失败、成功但空、存在 records 但合计为零；三者不能互相代替。 → 核对日期/时区、聚合延迟、所选口径、身份以及实际生效的… → Volc 个人平台统计仅在成功为空，或 CLI 明确报告本人没有… → …
- Tasks that involve Speech recognition and synthesis
- SKILL.md covers Step 0：先选用量口径，再确认身份, 适用场景, 业务定位 and 快速决策, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Arkcli Usage is an agent skill from volcengine/ark-cli. ARK 用量查询:usage stats(Token / 请求数,5-30 分钟延迟)、usage plan / usage balance --type plan(套餐额度快照)、usage plan-details(仅 Agent Plan 按模型时间序列,套餐内/外拆分)、usage balance(余额:免费额度 / 媒资库 / 套餐)、usage seats --with-usage(团队席位用量 by seat)。Coding Plan 只有 quota 快照，不能用 stats 冒充按模型套餐明细。命中关键词:用量 / 用了多少 / 还剩多少额度 / 套餐用了几成 / 套餐内套餐外 / 每个 seat 消耗。席位的列表 / 绑定 / 分配 / 轮换 APIKey 属管理范畴,走 arkcli-plans;本 skill 只回答用量。动词路由:用 / 消耗 / 多少 → 这里;列 / 绑 / 分 / 轮换 → arkcli-plans。反触发：TTS/ASR/语音模型用量不支持查询，只能转 models search 说明广场发现边界。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/arkcli-usage-balance.md`, `references/arkcli-usage-plan-details.md` and `references/arkcli-usage-plan.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-usage”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 区分命令失败、成功但空、存在 records 但合计为零；三者不能互相代替。
- 核对日期/时区、聚合延迟、所选口径、身份以及实际生效的 Project/过滤条件。近期记录未进入聚合不代表调用未发生；账号全范围不等于有所有资源权限，也不能先断言是 Project 隔离。
- Volc 个人平台统计仅在成功为空，或 CLI 明确报告本人没有 Endpoint 时，保留原日期/过滤条件改查 --mine --mine-by=apikey；已显式选 API Key 维度就不重复。鉴权、权限、网络错误不是空结果。两次均空也不自动删…
- 平台 records 的 ModelEndpoint 可交给 infer endpoint get ；AuthToken 是 Key 掩码标识，可用 apikey.list 的元数据核对归属，后缀有冲突时报告歧义，不取明文、不轮换 Key。
- Agent Plan plan-details 不提供 Endpoint / API Key 级归属，查到模型/Harness 消耗即到边界；Coding Plan 无模型/Harness 明细。不能跨口径拼出不存在的调用归属，也不因 CLI 报错改用记忆/检索结果充当账号数据。
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
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.
Network
No URLs in SKILL.md.
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 Usage loads about 2.5k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 130 tokens; SKILL.md has 831 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). 831 words, ~2,533 tokens.
Download SKILL.mdSave it as
.claude/skills/arkcli-usage/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- arkcli-usage
- description
- ARK 用量查询:`usage stats`(Token / 请求数,5-30 分钟延迟)、`usage plan` / `usage balance --type plan`(套餐额度快照)、`usage plan-details`(仅 Agent Plan 按模型时间序列,套餐内/外拆分)、`usage balance`(余额:免费额度 / 媒资库 / 套餐)、`usage seats --with-usage`(团队席位用量 by seat)。Coding Plan 只有 quota 快照，不能用 stats 冒充按模型套餐明细。命中关键词:用量 / 用了多少 / 还剩多少额度 / 套餐用了几成 / 套餐内套餐外 / 每个 seat 消耗。**席位的列表 / 绑定 / 分配 / 轮换 APIKey 属管理范畴,走 arkcli-plans;本 skill 只回答用量。**动词路由:**用 / 消耗 / 多少** → 这里;**列 / 绑 / 分 / 轮换** → arkcli-plans。反触发：TTS/ASR/语音模型用量不支持查询，只能转 models search 说明广场发现边界。
- version
- 1.3.5
- metadata.cliHelp
- arkcli usage stats --help
arkcli usage
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 — usage stats 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-stats.md,禁止直接盲目调用命令。
CRITICAL — usage plan 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-plan.md,禁止直接盲目调用命令。
CRITICAL — usage plan-details 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-plan-details.md,禁止直接盲目调用命令。
CRITICAL — Coding Plan / Coding Plan Team 当前不提供按模型套餐明细。这类问题只能用 usage plan --product coding-plan（团队版用 --product coding-plan-team）给 quota 快照并明说能力边界；禁止改跑 usage stats 后把 platform / Endpoint Token 统计冒充 Coding Plan 套餐按模型明细。
CRITICAL — 上述 Coding Plan 问题在本轮执行 usage plan 并说明边界后就停止。不主动追加 Endpoint / platform usage stats，因为它无法归因为 Coding Plan 套餐明细；只有用户在知道两者不同后另行明确要求「再看 platform / Endpoint 用量」，才开新查询。
CRITICAL — usage balance 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-balance.md,禁止直接盲目调用命令。
CRITICAL — usage seats 在执行之前,务必先用 Read 工具读取 references/arkcli-usage-seats.md,禁止直接盲目调用命令。
数据时效(务必先看):
usage stats走的是上游 BFF 的聚合管道,数据有 5–30 分钟延迟,定位为「日级 / 聚合分析」。 不要把它用于实时预算监控、限流、实时告警等需要秒级精度的控制场景——这类场景请直接读+chat/+gen等推理命令返回里的.usage字段(per-request、零延迟,详见 arkcli-chat 与 arkcli-gen)。
语音模型边界：TTS / ASR / 配音 / 朗读 / 播客 / 音色 / 实时语音交互，或
doubao-seed-tts-*/doubao-seed-asr-*/seedasr-*等广场语音模型，当前在 arkcli 只支持models search发现。不要用usage stats --model、usage plan-details或套餐/余额命令回答语音模型用量；直接说明 arkcli 不支持查询语音模型费用或用量。
stats / plan / plan-details / balance 区分:
stats出"按 token 计费的 inference 用量"(任何身份,5–30 分钟延迟)plan出"订阅套餐的 quota 快照"(AgentPlan / CodingPlan 个人版 + 团队版的"我用了几成 / 几号刷新")plan-details出"AgentPlan 按模型 / 套餐内外的时间序列调用明细"(AgentPlan 个人版 + 团队版,CodingPlan 没有按模型 endpoint)balance出"还剩多少 X"(余额视角,--type free-quota / media-asset / plan三选一)seats出"团队席位用量 admin 视角"(每个 seat 用了多少 / 套餐百分比;只是用量视图)。席位的列表 / 绑定 / 分配 / API Key 轮换 走arkcli-plans的plans team seat-list / seat-assign / rotate-apikey。用户问「我的套餐还剩多少额度」→
plan或balance --type plan(后者输出更精简);「我哪个模型用得最多」→ Agent Plan 用plan-details，Coding Plan 只能用plan给 quota 快照并说明不支持按模型拆分;「我今天用了多少 token」→stats;「我还剩多少免费额度 / 媒资库容量」→balance;「每个 seat 用了多少 / 团队席位用量分布」→seats --with-usage(纯管理类:谁绑了哪个 seat / 列出席位 / 分配席位 / 轮换 key →arkcli-plans)。
Step 0：先选用量口径，再确认身份
用户已明确套餐名称时，直接用 usage plan --product <plan>；Agent Plan 按模型明细用 usage plan-details --product <agent-plan|agent-plan-team> --start <日期>。订阅属于账号/子用户，不是由 active profile.type 决定；platform profile 不等于没有套餐，也不需要为查询先切成 plan profile。
- 平台 Token / 请求数 →
usage stats --start <日期>；用户说“我的”时首条就带--mine，追加--by model|endpoint|apikey不能删掉范围限制。 - 套餐额度 →
usage plan/usage balance --type plan；Agent Plan 明细 →plan-details；Coding Plan 只有 quota 快照，解释限制后停止，不补查平台桶冒充套餐明细。 - “我的用量”未指明口径时，结合本轮上下文确认是平台 Token 还是套餐额度；仍有歧义就问这一项。只有用户明确要合并查看时才查多个桶，并分开报告，不能把百分比、AFP、Token 直接相加。
subscribed:false只表示当前身份下该 SKU 没查到订阅，不证明其他身份无订阅，不触发自动切身份或平台查询。
身份核对遵守当前宿主的共享协议；已有执行上下文可复用，缺少摘要且确需核实时用 arkcli auth whoami --format json。普通查询不调用可能同步/回写 Key 的 profile show/list/keys list。确需另一身份时先确认目标，不能静默切 Profile、Key、Project 或账号范围。
时间与交付： stats / plan-details 必带 --start，没有 CLI 默认“近 7 天”；按用户时间词补齐 --start/--end，无日期时说明按今天查。长窗口按当前 reference 的限制分片，边界不重叠，保留用户原请求范围；无法覆盖的日期明确标注，不静默改成最近 30 天。回答同时标明口径、身份/范围、时间窗和数据延迟。
空结果与归属排查
- 区分命令失败、成功但空、存在 records 但合计为零；三者不能互相代替。
- 核对日期/时区、聚合延迟、所选口径、身份以及实际生效的 Project/过滤条件。近期记录未进入聚合不代表调用未发生；账号全范围不等于有所有资源权限，也不能先断言是 Project 隔离。
- Volc 个人平台统计仅在成功为空，或 CLI 明确报告本人没有 Endpoint 时，保留原日期/过滤条件改查
--mine --mine-by=apikey；已显式选 API Key 维度就不重复。鉴权、权限、网络错误不是空结果。两次均空也不自动删--mine；扩大账号范围须用户另行明确要求。 - 平台
records的ModelEndpoint可交给infer endpoint get <id>；AuthToken是 Key 掩码标识，可用apikey.list的元数据核对归属，后缀有冲突时报告歧义，不取明文、不轮换 Key。 - Agent Plan
plan-details不提供 Endpoint / API Key 级归属，查到模型/Harness 消耗即到边界；Coding Plan 无模型/Harness 明细。不能跨口径拼出不存在的调用归属，也不因 CLI 报错改用记忆/检索结果充当账号数据。
适用场景
- 查看当日或指定日期范围的推理用量(接受 5–30 分钟延迟)
- 看订阅套餐(AgentPlan / CodingPlan)的配额消耗 / 重置时间
- 看 AgentPlan 套餐内 vs 套餐外的按模型拆分明细
- 按模型、接入点、API Key 维度分组统计(stats)
- 分析 Token 消耗趋势、出对账报表
- 不适用于语音模型用量：用户问 TTS / ASR / 语音模型用了多少、剩余额度、调用次数时，不执行本 skill，转
arkcli-models说明只支持广场发现
业务定位
- 本 skill 对应"看存量调用结果和消耗"的场景,是离线 / 准实时分析入口
- 它通常发生在两类后置链路之后:
- Endpoint 已经存在,想按 endpoint 看使用情况
- 模型已经在被调用,想按 model / API Key 分析消耗
- 或:订阅了套餐,想看额度还剩多少
- 它不是创建 Endpoint 的入口,也不是试用模型的入口
- 它不是实时预算 / 限流 / 告警的数据源——实时控制请走 per-request
.usage字段(见上方 banner)
Show full SKILL.md (431 more words)Show less
快速决策
- 用户问"我的套餐还剩多少 / 用了几成 / 几号刷新 / 我有几个套餐":
arkcli usage plan(默认探所有 4 个 SKU:personal × 2 + team × 2,subscribed 桶才下发 usage 请求)arkcli usage plan --all:不探订阅,4 桶全跑(诊断 / Excel)arkcli usage plan --product=X:跳过探测,单查- 跟
balance --type plan是同一份数据;usage plan输出完整(带subscribed/updated_at),balance --type plan精简(去掉元字段)。一般默认走usage plan,只有用户明确把套餐余额跟"免费额度 / 媒资库容量"一起对账时,才走balance --type plan(三 type 一起跑节省心智)
- 用户问"我哪个模型用得最多 / 套餐内套餐外各占多少 / 团队某个子用户用得多":
arkcli usage plan-details --start <YYYY-MM-DD>（Day 粒度，Agent Plan personal；显式补日期）arkcli usage plan-details --product=agent-plan-team(团队版,自动找 caller seat 或显式--seat <id>)- Coding Plan 例外：不执行
plan-details或stats；只执行arkcli usage plan --product coding-plan(团队版用coding-plan-team)，并明确该结果只是 quota 快照、不是本周按模型明细，然后停止。用户未另行要求 platform / Endpoint 用量时，不主动补跑usage stats。
- 用户问"我的用量 / 我今天用了多少 token / 我的 endpoint 消耗":
- 先按 Step 0 确定口径；明确的平台 Token / Endpoint 问题直接查下述平台桶，不因 profile.type 自动追加套餐查询。
- 如果用户点名的是语音模型或 TTS / ASR 场景 → 不要继续查 usage；当前 arkcli 只承认语音模型广场发现，不支持语音模型用量查询
- 火山: 先
arkcli usage stats --start <YYYY-MM-DD> --mine（默认 endpoint 维度）- 返回
data_count > 0→ 直接从totals取合计 - 返回
data_count=0（用户没有 Endpoint 或近期未通过 Endpoint 调用）→ 立即重试arkcli usage stats --start <YYYY-MM-DD> --mine --mine-by=apikey - 不自动退化为账号全量；第二层也成功为空时，可询问用户是否另查整个账号。明确同意后按 stats 的第三层流程 保留其他参数、只移除 mine 限定，并标明“账号全量，可能包含其他用户”。这不是个人用量，也不授权切身份。
- 返回
- 用户问"我每个 APIKey 用了多少":
- 火山:
arkcli usage stats --start <YYYY-MM-DD> --mine --mine-by=apikey,从records[].AuthToken拆分
- 火山:
- 用户问"我账上还有多少免费 token / 模型免费额度 / 媒资库还能存多少":
arkcli usage balance --type free-quota(模型免费推理额度)arkcli usage balance --type media-asset(素材库容量)
- 用户问"团队席位用了多少 / 每个 seat 消耗 / 套餐百分比 by seat"(admin 用量视角):
arkcli usage seats --product agent-plan-team --with-usage(列席位 + 每个 seat 的 AFP 用量)- 不带
--with-usage也行,但只有基础元数据,没有用量数字 - 路由分工:本命令只回答"用量",不负责 seat 管理。"列席位 / 谁绑了哪个 seat / 给员工分配席位 / 轮换席位 APIKey" 全部走
arkcli-plans的plans team seat-list / seat-assign / rotate-apikey。Agent 路由这条问句先看动词:"用了 / 消耗 / 多少" 留这边,"绑 / 列 / 分 / 轮换" 跳过去 plans。
- 数据看起来不对:先查认证和 profile,再怀疑数据本身
Agent 快速执行顺序
- 先确认认证状态;不确定时先看
arkcli auth status - 先做最小查询,再逐步加时间范围和分组条件
- 结果异常时,先检查 profile / region / API Key 来源是否正确,再怀疑数据本身
- 如果用户要按 endpoint 看 usage,最好先确认 endpoint-id 已知
常见降级
- 鉴权错误:转
../arkcli-auth/SKILL.md - 查询范围或环境不对:转
../arkcli-config/SKILL.md - 用户其实还没有 Endpoint,只是在准备正式接入:转
../arkcli-deploy/SKILL.md - 用户想看套餐价格(不是用量):转
../arkcli-pricing/SKILL.md(pricing plans出 catalog 询价,usage plan出 quota 快照,两者是不同视角) - 用户想看结算金额 / 账单 / 花了多少钱(不是 token 用量):转
../arkcli-billing/SKILL.md(数据源是火山计费中心, T+1 出账; usage stats 是 BFF 推理聚合, 近实时) - 用户问语音模型 / TTS / ASR 的用量或额度:转
../arkcli-models/SKILL.md只说明广场可搜与 arkcli 不支持用量查询，不转 pricing / billing
命令一览
| 命令 | 说明 |
|---|---|
usage stats | 查询推理用量(Token / 请求数,按日 / 小时聚合,按 token 计费的 inference 视角) |
usage plan | 查询订阅套餐的额度快照(AgentPlan / CodingPlan,5h / weekly / monthly / session 周期的"用了多少 / 还剩多少 / 几号刷新")。默认探所有 4 个 SKU |
usage plan-details | 查询 AgentPlan 个人版 + 团队版 按模型 / Harness 的时间序列调用明细(套餐内 vs 套餐外拆分)。必传 --start，--product=agent-plan-team 切团队版 |
usage balance | 余额视角统一入口 --type free-quota / media-asset / plan(模型免费推理额度 / 素材库容量 / 套餐余额) |
usage seats | Admin 视角 列举企业版套餐下所有席位(SeatID / 绑定子用户 / billing 状态)。子用户调通常 AccessDenied |
自然语言触发词表
| 用户怎么说 | 对应命令 |
|---|---|
| "按模型明细 / 哪个模型用得最多 / 模型维度拆分 / 按模型时序 / 套餐内套餐外按模型" | arkcli usage plan-details |
| "coding plan 按模型明细 / coding plan 套餐内套餐外" | arkcli usage plan --product coding-plan，并明说只支持 quota 快照、不支持按模型时序明细；禁止用 usage stats 冒充 |
| "配额还剩多少 / 余额 / 还能用多少 / 用了几成 / 套餐额度" | arkcli usage plan 或 arkcli usage balance --type plan |
| "免费额度还有多少 / 模型免费额度 / 免费 token" | arkcli usage balance --type free-quota |
| "AFP 消耗 / 今日 AFP / 本周 AFP" | arkcli usage plan（AFP 就是套餐额度单位） |
| "我的用量 / 我今天用了多少 token / 推理用量 / token 消耗" | arkcli usage stats --start <YYYY-MM-DD> --mine |
参考
- arkcli-deploy -- 先创建 Endpoint,再按 endpoint 看 usage
- arkcli-pricing -- catalog 询价(
pricing plans),跟usage planquota 快照互补 - arkcli-shared -- 认证和全局参数
© 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 5 other files (references) in skills/arkcli-usage of volcengine/ark-cli.
- SKILL.md
- references/arkcli-usage-balance.md
- references/arkcli-usage-plan-details.md
- references/arkcli-usage-plan.md
- references/arkcli-usage-seats.md
- references/arkcli-usage-stats.md
Open the folder on GitHubat commit fb5b7be
Compare with similar skills
Arkcli Usage 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 Usage this skillvolcengine/ark-cli | 140 | — | ~2.5k | 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 | |
| Voice AI Ttssundial-org/awesome-openclaw-skills | 663 | — | ~2.3k | Automated safety check: Notes | None | |
| Video Cutzenstory-ai/video-recap-skills | 553 | — | ~1.6k | Automated safety check: Pass | MIT |
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.
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 Cut
zenstory-ai/video-recap-skills
把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节，读取 clipplan.json 与源视频， 输出 editedsource.mp4；随后 Agent 按输出时间线写 narration.json。支持单视频与多视频（sources manifest）拼剪， 本工具不读取、不映射旁白。
Local AI Use
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.
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 Deploy
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…
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。
Related
Categories
Questions about Arkcli Usage
What does Arkcli Usage do?
ARK 用量查询:usage stats(Token / 请求数,5-30 分钟延迟)、usage plan / usage balance --type plan(套餐额度快照)、usage plan-details(仅 Agent Plan 按模型时间序列,套餐内/外拆分)、usage balance(余额:免费额度 / 媒资库 / 套餐)、usage seats…. Arkcli Usage is an agent skill from volcengine/ark-cli.
When should I use Arkcli Usage?
Arkcli Usage fits situations like: tasks that involve Speech recognition and synthesis; tasks that involve Text to speech and voice.
How do I install Arkcli Usage in Claude Code?
Run `npx skills add volcengine/ark-cli --skill arkcli-usage -a claude-code`. Or copy the skill folder (skills/arkcli-usage in volcengine/ark-cli) into .claude/skills/arkcli-usage in your project. Claude Code loads it when a task matches its description.
How do I install Arkcli Usage in Codex?
Run `npx skills add volcengine/ark-cli --skill arkcli-usage -a codex`. Or copy the skill folder (skills/arkcli-usage in volcengine/ark-cli) into .agents/skills/arkcli-usage in your project. Codex loads it when a task matches its description.
Can I use Arkcli Usage 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-usage -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-usage, .gemini/skills/arkcli-usage, .github/skills/arkcli-usage and .opencode/skills/arkcli-usage in your project.
What does Arkcli Usage need to run?
SKILL.md names no scripts, command-line tools or credentials: Arkcli Usage is instructions for the agent only.
Does Arkcli Usage access the network?
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.
Is Arkcli Usage 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 Usage use?
Arkcli Usage 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 Usage use?
About 2.5k 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 12k tokens, read only when the agent opens those files.
What are the alternatives to Arkcli Usage?
Skills that share tags, products or a category with Arkcli Usage: 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 Voice AI Tts (sundial-org/awesome-openclaw-skills, 663 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Arkcli Usage?
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.