Agent skill

Arkcli Shared

arkcli 共享执行协议：首次配置入口、业务命令执行前的认证闸门、命令路由与选择顺序、输出/安全/二次确认规则。深度细节（身份解析、AK-SK 边界、API Key 恢复、实名闸门、profile 默认与漂移、临时数据面执行上下文、版本检查与显式升级、全局 flags、故障分流）按需在 references/ 加载。当用户第一次使用…

Apache-2.0Auto-check: notesMedia & Creative

Install Arkcli Shared

skills CLI

$ npx skills add volcengine/ark-cli --skill arkcli-shared -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install volcengine/ark-cli arkcli-shared --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/arkcli-shared .claude/skills/arkcli-shared && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "arkcli-shared" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-shared into .claude/skills/arkcli-shared/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-shared", 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

$skill-installer install https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-shared

Type 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.

skills CLI

$ npx skills add volcengine/ark-cli --skill arkcli-shared -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install volcengine/ark-cli arkcli-shared --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/arkcli-shared .agents/skills/arkcli-shared && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "arkcli-shared" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-shared into .agents/skills/arkcli-shared/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-shared", 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.

skills CLI

$ npx skills add volcengine/ark-cli --skill arkcli-shared -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install volcengine/ark-cli arkcli-shared --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/arkcli-shared .cursor/skills/arkcli-shared && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "arkcli-shared" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-shared into .cursor/skills/arkcli-shared/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-shared", 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

$ gemini skills install https://github.com/volcengine/ark-cli.git --path skills/arkcli-shared

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add volcengine/ark-cli --skill arkcli-shared -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install volcengine/ark-cli arkcli-shared --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/arkcli-shared .gemini/skills/arkcli-shared && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "arkcli-shared" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-shared into .gemini/skills/arkcli-shared/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-shared", 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.

GitHub CLI

$ gh skill install volcengine/ark-cli arkcli-shared

Installs 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).

skills CLI

$ npx skills add volcengine/ark-cli --skill arkcli-shared -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/arkcli-shared .github/skills/arkcli-shared && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "arkcli-shared" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-shared into .github/skills/arkcli-shared/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-shared", 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.

skills CLI

$ npx skills add volcengine/ark-cli --skill arkcli-shared -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install volcengine/ark-cli arkcli-shared --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/volcengine/ark-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/arkcli-shared .opencode/skills/arkcli-shared && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "arkcli-shared" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-shared into .opencode/skills/arkcli-shared/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-shared", 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-shared
GitHub stars: 140
Token cost: ~2.8k tokens
SKILL.md length: 773 words
Files: 6 (incl. references)
Skills in repo: 25
Repo updated: Sep 29, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Works in 4 steps: 先用产品命令 arkcli 或 arkcli + → 有对应 reference 文档先读 reference 再执行 → 产品命令确实不覆盖，最后才走 arkcli api（不要把 Raw API… → …
Media & Creative work in your project
SKILL.md covers 配置与首次使用, 调用归因协议, 统一 CLI 与 Profile and 命令路由与执行顺序, plus 7 more sections
Calls npm

What it does

Arkcli Shared is an agent skill from volcengine/ark-cli. arkcli 共享执行协议：首次配置入口、业务命令执行前的认证闸门、命令路由与选择顺序、输出/安全/二次确认规则。深度细节（身份解析、AK-SK 边界、API Key 恢复、实名闸门、profile 默认与漂移、临时数据面执行上下文、版本检查与显式升级、全局 flags、故障分流）按需在 references/ 加载。当用户第一次使用 arkcli、遇到未登录/鉴权失败、询问版本是否最新或要求升级 arkcli、需要判断该走产品命令还是 raw api、或任何 arkcli- skill 需要公共上下文时触发。

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/execution-context.md`, `references/global-flags.md` and `references/profile-defaults.md`).

It sits in Media & Creative. 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

Media & Creative work in your project

Example prompts

“/arkcli-shared”

Requirements

Node.js

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

先用产品命令 arkcli 或 arkcli +
有对应 reference 文档先读 reference 再执行
产品命令确实不覆盖，最后才走 arkcli api（不要把 Raw API Explorer 当默认入口）
读操作优先直接执行；写 / 删除 / 切换默认配置前必须确认用户意图

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:
- npm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
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 Shared loads about 2.8k tokens when it runs, and up to ~8.2k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 773 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~68
When it runs · the whole SKILL.md, loaded when a task matches: ~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~8.2k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:30

--profile` / `ARK_PROFILE` / 全局 flags / `.env` 谁覆盖谁）不对时，先看 [`../arkcli-config/SKILL.md`](../arkcli-config/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). 773 words, ~2,790 tokens.

Download SKILL.mdSave it as .claude/skills/arkcli-shared/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.

name: arkcli-shared
description: arkcli 共享执行协议：首次配置入口、业务命令执行前的认证闸门、命令路由与选择顺序、输出/安全/二次确认规则。深度细节（身份解析、AK-SK 边界、API Key 恢复、实名闸门、profile 默认与漂移、临时数据面执行上下文、版本检查与显式升级、全局 flags、故障分流）按需在 references/ 加载。当用户第一次使用 arkcli、遇到未登录/鉴权失败、询问版本是否最新或要求升级 arkcli、需要判断该走产品命令还是 raw api、或任何 arkcli-* skill 需要公共上下文时触发。
version: 2.2.3
metadata.cliHelp: arkcli --help

arkcli 共享规则

本 skill 是 arkcli 的统一执行协议入口。所有 arkcli-* skill 在执行前都应先读取本文件。

分层约定：本文正文只放"几乎每个任务都命中"的规则。稀有路径 / 查表类细节下沉到 reference，命中对应场景时再读：

场景读哪个
"我的 / my xxx" 自指资源过滤 ../arkcli-auth/references/identity-resolution.md
AK/SK 态能调什么 / 数据面 API Key 报错恢复 ../arkcli-auth/references/auth-modes.md
开通 / 部署 / 精调前的实名检查 ../arkcli-auth/references/realname-gate.md
+chat/+gen/+deploy 的默认资源与漂移 nudge references/profile-defaults.md
临时传入 Profile / API Key / Base URL / Endpoint / 模型名 references/execution-context.md
版本是否最新 / 刷新版本信息 / 显式升级 arkcli references/update.md
全局 flags 速查 references/global-flags.md
报错不知归类 / 故障分流 references/troubleshooting.md

场景	读哪个
"我的 / my xxx" 自指资源过滤	`../arkcli-auth/references/identity-resolution.md`
AK/SK 态能调什么 / 数据面 API Key 报错恢复	`../arkcli-auth/references/auth-modes.md`
开通 / 部署 / 精调前的实名检查	`../arkcli-auth/references/realname-gate.md`
`+chat`/`+gen`/`+deploy` 的默认资源与漂移 nudge	`references/profile-defaults.md`
临时传入 Profile / API Key / Base URL / Endpoint / 模型名	`references/execution-context.md`
版本是否最新 / 刷新版本信息 / 显式升级 arkcli	`references/update.md`
全局 flags 速查	`references/global-flags.md`
报错不知归类 / 故障分流	`references/troubleshooting.md`

配置与首次使用

首次使用或怀疑配置归因（--profile / ARK_PROFILE / 全局 flags / .env 谁覆盖谁）不对时，先看 ../arkcli-config/SKILL.md
profile 类写操作（create / use / set-default / keys / models / delete / rename）走 ../arkcli-profile/SKILL.md
看可用资源（endpoint / plan 模型 ID）走 ../arkcli-resources/SKILL.md
首次远端调用前，先看 ../arkcli-auth/SKILL.md
arkcli 是产品 CLI，不是 OpenAPI Action 浏览器；不要从 Action 名反推命令设计
安装: npm i @volcengine/ark-cli -g（公开版）
版本检查与显式升级按需读取 references/update.md；update.mode 的读取、写入与 automatic gate 仍走 ../arkcli-config/SKILL.md

调用归因协议

当 AI Agent 通过任意 arkcli-* 业务 skill 执行 arkcli 命令时，必须使用下面的单命令环境变量前缀。它既标记调用来源和 owning skill，也冻结本次 Skill workflow 的 CLI 版本：不做隐式 registry 更新检查、不打印更新提示、不在任一子命令结束后调度 automatic apply。人类直接在终端调用 arkcli 时不要手动补这些变量。

bash

ARKCLI_NO_UPDATE_NOTIFIER=1 \
ARKCLI_CALLER_TYPE=ai_agent \
ARKCLI_CALLER_NAME=<agent-id> \
ARKCLI_SKILL_NAME=<current-arkcli-skill> \
arkcli <command> ...

约定：

ARKCLI_CALLER_NAME 使用稳定 Agent ID，例如 codex / claude-code / opencode / openclaw / trae / cursor；无法可靠判断时用 unknown_agent
ARKCLI_SKILL_NAME 填当前业务 skill 名，例如 arkcli-gen / arkcli-chat / arkcli-models / arkcli-deploy
一般业务 workflow 不要把 arkcli-shared 填进 ARKCLI_SKILL_NAME，归因必须落到实际 owning skill；仅当本 skill 直接处理版本检查或显式升级时，它就是 owning skill，使用 ARKCLI_SKILL_NAME=arkcli-shared
ARKCLI_NO_UPDATE_NOTIFIER=1 的兼容变量名虽然只写了 notifier，但契约覆盖全部隐式更新活动：缓存读取/刷新、提示和 automatic 调度；它不阻止用户明确要求的 arkcli update / arkcli update --check
Skill 内每一条 arkcli 子命令都必须带完整前缀，不能只给第一条加；这样多命令 workflow 从开始到结束都使用同一已安装版本
只给当前命令加前缀，不要 export 到整个 shell 会话，避免串到后续无关命令

统一 CLI 与 Profile

当前 arkcli 的产品身份在编译时固定；Profile 只选择该产品内的身份与消耗切面，不能切换产品：

bash

arkcli profile create --type platform --set-default          # 新建火山 profile（旧 config init/switch 已 deprecated）
arkcli profile use <name>                                    # 切换默认 profile

切换 profile 会联动切换登录身份、API Key、控制面路由等上下文。详细命令树看 ../arkcli-profile/SKILL.md。不能从 Profile 的名称或 tenant 字段推断、切换当前编译产品。

只查当前身份/Profile 时，普通 CLI 使用 arkcli auth status / arkcli auth whoami；默认模型与路由使用 arkcli resources list --modality <text|image|video> 并按 Resources Skill 验证。profile show/list/keys list 可能同步远端 Key 并回写本地库存或默认 Key，不能作为常规 Chat/Gen 准入或“不改配置/Key”请求的无副作用查询。显式 Profile 管理任务保留这些命令，但先说明同步影响；不改用 deprecated config show/list 绕过限制。此边界同样约束业务 Skill/reference 的旧建议。只读核对身份与默认资源时，每次 Bash 调用只执行一条 arkcli auth status、auth whoami 或 resources list --modality ... --format json；直接检查该命令的原始 JSON 与执行状态。不要用 ; echo、管道截断或重定向包装核对命令，避免宿主拒绝或丢失事实来源。若命令被拒绝，报告未完成的核对，不把拒绝推断为账号或资源状态。

命令路由与执行顺序

优先按用户目标判断，而不是按命令名思考：

用户目标	路径	关键点
试用模型 / 快速验证效果	`auth` → `resources` / `models`（可选）→ `+chat` / `+gen`	Plan lane 用模型名；Platform lane 用 Endpoint
专项多模态理解（转写/抽取/字幕/框目标…）	`auth` → `+understand`	有明确产出形态时走 understand，不是 chat
语音模型发现 / 选型（TTS / ASR / 播客 / 音色 / 实时语音交互）	`auth` → `models search`	仅支持广场检索；不支持 `+chat` / `+gen` / `+deploy` / `+code-example` / `usage` / `pricing` / `onboard`
正式接入 / 稳定调用	`auth` → `models` → `infer endpoint list` → 没有就 `+deploy`	核心资源是 Endpoint，不是 +chat/+gen
排查存量调用 / 看消耗	`auth` → `usage`	—
本地 AI Agent 集成	`+connect`	—
明确查官方文档 / 读取文档 URL / 业务 Skill 缺少产品知识	`docs`	搜索后读取正文；不替代资源操作、鉴权、诊断和 CLI help

易混动词路由（避免选错 skill）：

列 / 绑 / 分 / 轮换席位 APIKey → arkcli-plans；用 / 消耗 / 还剩多少额度 → arkcli-usage
profile 写操作（create/use/set-default/keys）→ arkcli-profile；配置排障 / 老 yaml → arkcli-config
开放式带图对话 → +chat；生成图/视频 → +gen；有产出形态的理解 → +understand
语音合成 / TTS / 配音 / 朗读、或用户点名 doubao-seed-tts-* 等广场语音模型 → 只允许 models search 做发现与选型说明；不要转 +chat / +gen / +deploy / +code-example / usage / pricing。不要主动补充控制台 / OpenAPI / SDK 等非 arkcli 接入路径或链接，除非用户另问"官方文档在哪里"。如果用户只是要"把一个音频文件转文字"且未要求使用广场语音模型，可另走 +understand asr；不要把 +understand 解释成支持广场 ASR 模型。

命令选择顺序（始终按此）：

先用产品命令 arkcli <domain> <verb> 或 arkcli +<workflow>
有对应 reference 文档先读 reference 再执行
产品命令确实不覆盖，最后才走 arkcli api（不要把 Raw API Explorer 当默认入口）
读操作优先直接执行；写 / 删除 / 切换默认配置前必须确认用户意图

认证闸门

除 arkcli auth ...、arkcli profile list/show、arkcli +connect list、arkcli update ... 外，默认认为业务命令需要先过认证检查。不要跳过认证检查就连续重试一串业务命令。

先运行 arkcli auth status；已登录就继续目标命令
未登录 / 凭证失效：保持当前编译产品，按其认证 Skill 选择登录命令，不靠 Profile 推断或切换产品
- 火山：直接 Bash 执行 arkcli auth login volc-sso
- 执行前一句话告知用户"检测到未登录，正在启动 SSO 登录，请在浏览器完成授权"；Bash 调用设 timeout=600000（10 分钟）；成功后立即回到原始任务，不要停在 auth 结果
- SSO 同时覆盖控制面 BFF 和数据面，所以默认走 SSO；AK/SK 登录通道 0.1.16 暂关。CI / agent / 沙箱（非 TTY）走 arkcli auth login --no-browser 两段式：Phase 1 跑它拿 authorize_pending JSON 里的 authorize_url 转发给用户，待其浏览器授权后回粘 base64 授权码，再跑 arkcli auth login --no-browser --code <授权码> 完成（细节见 ../arkcli-auth/SKILL.md）。不要在非 TTY 直接指望它阻塞等粘贴（旧版会 EOF 崩）
- 启动 SSO 失败（无浏览器 / open 失败 / 端口占用 / 超时）→ 不原地重试，把 stderr 原样贴回用户、请其手动在终端登录后回来
- 登录流程细节、whoami、apikey 选择见 ../arkcli-auth/SKILL.md

追加闸门 / 错误恢复（命中才读，避免常驻）：

命中开通 / 部署 / 精调 / 激活模型（+deploy / infer endpoint create / train finetune create / models activate）→ 第一步先做实名检查，见 ../arkcli-auth/references/realname-gate.md
当前是 AK/SK 态、要判断能调什么，或数据面 API Key 报 401/403/AccessDenied 要恢复 → ../arkcli-auth/references/auth-modes.md
用户说"我的 / my xxx"要按身份过滤资源 → ../arkcli-auth/references/identity-resolution.md

Show full SKILL.md (263 more words)Show less

输出规则

全局 --format 支持 json、yaml、table、csv、jsonl、pretty；脚本场景优先用 json/yaml，需要抽字段时配合 --transform
stdout 只放结构化结果；解释 / 调试 / 错误都走 stderr
消费结构化输出时，禁止先用 head / tail / sed -n / head -c 按行或字节截断再解析。这样既可能破坏 JSON，也会漏掉数组后部的目标项、default 标记或 warning 对应的数据。输出较大时，优先使用命令自己的 --output <file>；没有该 flag 时只把完整 stdout 重定向到文件，再用 jq / yq 提取所需字段。
首次调用和决定结论的调用不得用 2>/dev/null 吞掉 stderr；scope 提示、软截断告警和可恢复错误可能只出现在 stderr。

安全规则

禁止输出完整 AK/SK、token、secret
写入、删除、切换配置前需要确认用户意图
只有已注册 Action 才能通过 arkcli api 调用
涉及创建 Endpoint、修改 profile、清理凭证等操作时，先看叶子命令 --help：支持 Client Preview 才能用 --dry-run；不支持时改用只读命令核对并取得明确确认，绝不生成不存在的 flag

意图澄清与结构化选择

意图澄清只解决“用户要操作哪个真实目标”，不代替写操作授权。用户目标已经唯一，或可从本轮输入与当前权威结果安全确定时，不要额外提问。确有歧义时遵守以下硬规则：

先做一次最小、有界的只读查询；候选只能来自本轮完整结构化结果，不能从模型记忆、示例或截断输出补全。
只允许用用户明确给出的硬约束和产品权威 eligibility 字段过滤候选；相关度排序、展示顺序、推荐语和 Agent 自己的优劣判断都不是硬约束，不得用主观“最合适”把 N 个候选自行收敛成 1 个。
按 0 / 1 / N 收敛：0 个时补充一个最关键条件；1 个时复述精确 ID 后继续；N 个且选择会改变远端结果时必须询问用户，并在用户选定前停止，不得进入下游 preview、create、update 或 delete。
N 个候选优先使用当前宿主提供的结构化选择能力，选项直接携带区分目标所需的真实 ID 与关键字段；可以标注推荐及依据，但推荐不能代替用户选择。通用 Skill 不写死任何宿主工具名，也不重复添加宿主自动提供的自由输入项。
宿主没有结构化选择能力时，退化为精简编号列表并要求用户回复精确 ID。用户选定后只沿原 workflow 继续，不重新查询同一批候选。
因 N 个候选停机询问时，除让用户选「这次用哪个」，一并给出把它固定下来的方式，让用户还能选「以后都用它」——该候选集有持久化开关时就说明怎么开：生成类模态默认值走 arkcli profile set-default --modality <image|video> <ep-id> 写当前 profile 的该模态默认值，下次同类请求不再询问。否则同类请求每次都要重新问一遍，无人值守场景会持续卡住。这是写操作，只在用户明确同意后执行；询问本身仍按上述规则停机，不要替用户预选。

任务型选型例外：用户要求创建 Managed Agent、未指定主模型时，按 owning arkcli-agent 的模型选择流程，允许根据本轮实时资格、详情与用户意图择优并说明依据，不必仅因候选多于一个就提问。择优不等于把多个候选谎称为唯一候选；明确硬约束必须有对应版本证据，费用/能力差异实质影响任务且无法安全判断时仍先询问。此例外不允许替换用户明确模型、切换身份/计费路径或为更新、删除等操作擅选已有资源，也不替代执行授权。

二次确认错误处理（human-in-the-loop）

高危操作（删除资源、变更凭证、产生费用等）需要二次确认。CLI 自动检测环境：交互式终端显示 Y/N 提示；非交互式（Agent 调用）返回 ExitValidation 错误、type="requires_confirmation"。

当 arkcli 返回 ExitValidation 且 type="requires_confirmation" 时：

不要直接报错给用户 —— 这是正常的二次确认流程
调用宿主提供的用户确认能力 —— 提示内容可从 CLI 错误的 hint 字段提取，或通用提示"即将执行高危操作，确认继续吗？"
用户确认 → 给原命令加 --yes flag 重试
用户取消 → 返回"操作已取消"

当前会触发二次确认的命令：plans personal rotate-apikey、plans team rotate-apikey、models activate <model-name>、profile delete <profile-name>、profile project [<project-name>]、config delete <profile-name>。后续新增高危命令遵循同一约定。

Agent 禁止行为

不要把 arkcli api 当默认入口
不要在未检查认证状态前连续重试业务命令
不要把中间步骤当最终结果；登录、查模型、切 profile 完成后应回到用户原始任务
不要在业务 skill 里重复共享规则；共享规则统一以本 skill（及其 references）为准
不要一概声称“试用不需要 Endpoint”：Plan lane 使用模型名，Platform lane 必须使用 Endpoint。按 references/execution-context.md 判断；正式接入仍走 +deploy
不要把广场可搜到的语音模型误写成 arkcli 已支持调用、部署、示例、用量或费用查询；语音模型在 arkcli 当前只承认 models search 发现能力。
不要把语音模型边界回答扩展成"去控制台开通 / 用 OpenAPI / 用 SDK 接入"的替代方案；当前 skill 只负责说明 arkcli 支持边界。
不要给业务命令增加临时 Project/Region override；根命令已删除 --project-name 与 --region。持久上下文通过 arkcli profile create/use 管理，单次切换使用 --profile。

参考

arkcli-auth — 认证状态检查、登录与退出登录；其 references/ 放身份解析 / AK-SK 边界 / API Key 恢复 / 实名闸门
arkcli-config — profile、base-url、region 配置排障
arkcli-api-explorer — 产品命令未覆盖时的 raw API 兜底入口
references/profile-defaults.md — profile 默认资源、漂移检测、跨模态
references/execution-context.md — 五类 Profile × 三种模态、临时 Key/Base URL/Endpoint 组合与 Client Preview 边界
references/global-flags.md — 常用全局 flags 速查
references/troubleshooting.md — 故障分流与能力边界

Files

SKILL.md and 5 other files (references) in skills/arkcli-shared of volcengine/ark-cli.

SKILL.md
references/execution-context.md
references/global-flags.md
references/profile-defaults.md
references/troubleshooting.md
references/update.md

Open the folder on GitHubat commit fb5b7be

Compare with similar skills

Arkcli Shared 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.

Arkcli Shared compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Arkcli Shared this skillvolcengine/ark-cli	140	—	~2.8k	Automated safety check: Notes	Apache-2.0	8 days ago
Gh Stackremotion-dev/remotion	62k	6 repos	~2.4k	Automated safety check: Pass	Custom licence	today
HyperFrames Media Useheygen-com/hyperframes	58k	2 repos	~2.1k	Automated safety check: Pass	Apache-2.0	today
Guizang Social Cardsop7418/guizang-social-card-skill	7.4k	1 repos	~7.8k	Automated safety check: Pass	AGPL-3.0	3 mo ago
Weekly Changelog Videoheygen-com/hyperframes	58k	—	~3.3k	Automated safety check: Pass	Apache-2.0	today
Anthropic Brand Stylinganthropics/skills	180k	29 repos	~559	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Gh Stack
remotion-dev/remotion
Official
Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack.
62k GitHub starsUsed in 6 repos~2.4k tokens
Media & CreativeAuto-check passed
HyperFrames Media Use
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
58k GitHub starsUsed in 2 repos~2.1k tokens
Media & CreativeAuto-check passed
Guizang Social Cards
op7418/guizang-social-card-skill
Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.
7.4k GitHub starsUsed in 1 repo~7.8k tokens
Media & CreativeAuto-check passed
Weekly Changelog Video
heygen-com/hyperframes
Turns a weekly changelog markdown file into a branded HyperFrames video with voiceover, animated mock-UI scenes and captions, using fonts, background and scripts bundled in the skill.
58k GitHub stars~3.3k tokensUpdated today
Media & CreativeAuto-check passed
Anthropic Brand Styling
anthropics/skills
Official
Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.
180k GitHub starsUsed in 29 repos~559 tokens
Media & CreativeAuto-check passed
MoneyPrinterTurbo Video Generator
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
129k GitHub stars~2.1k tokensUpdated today
Media & CreativeAuto-check: warnings

Questions about Arkcli Shared

What does Arkcli Shared do?

When should I use Arkcli Shared?

Arkcli Shared fits situations like: media & Creative work in your project.

How do I install Arkcli Shared in Claude Code?

Run `npx skills add volcengine/ark-cli --skill arkcli-shared -a claude-code`. Or copy the skill folder (skills/arkcli-shared in volcengine/ark-cli) into .claude/skills/arkcli-shared in your project. Claude Code loads it when a task matches its description.

How do I install Arkcli Shared in Codex?

Run `npx skills add volcengine/ark-cli --skill arkcli-shared -a codex`. Or copy the skill folder (skills/arkcli-shared in volcengine/ark-cli) into .agents/skills/arkcli-shared in your project. Codex loads it when a task matches its description.

Can I use Arkcli Shared 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-shared -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-shared, .gemini/skills/arkcli-shared, .github/skills/arkcli-shared and .opencode/skills/arkcli-shared in your project.

What does Arkcli Shared need to run?

Going by SKILL.md and its folder, Arkcli Shared needs the command-line tools its instructions call (npm). Our summary lists: Node.js.

Does Arkcli Shared access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Arkcli Shared safe to install?

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.

What licence does Arkcli Shared use?

Arkcli Shared 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 Shared use?

About 2.8k tokens (SKILL.md is roughly 11k 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 5.4k tokens, read only when the agent opens those files.

What are the alternatives to Arkcli Shared?

Skills that share tags, products or a category with Arkcli Shared: Gh Stack (remotion-dev/remotion, 62k stars), HyperFrames Media Use (heygen-com/hyperframes, 58k stars), Guizang Social Cards (op7418/guizang-social-card-skill, 7.4k stars) and Weekly Changelog Video (heygen-com/hyperframes, 58k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Arkcli Shared?

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.

Install Arkcli Shared

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

arkcli 共享规则

配置与首次使用

调用归因协议

统一 CLI 与 Profile

命令路由与执行顺序

认证闸门

输出规则

安全规则

意图澄清与结构化选择

二次确认错误处理（human-in-the-loop）

Agent 禁止行为

参考

Files

Compare with similar skills

Similar skills

More from volcengine/ark-cli

Related

Questions about Arkcli Shared