Declarative Agent Developer
microsoft/work-iq
Create, build, deploy, and localize declarative agents for M365 Copilot and Teams.
arkcli agent:管理 ARK Managed Agents,包括 Agent / Skill / Env / Session / File / Memory Store / Vault / MCP OAuth。控制面优先走 ForTop/OpenTOP,Session 运行时和 Files 走数据面直联。
$ npx skills add volcengine/ark-cli --skill arkcli-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install volcengine/ark-cli arkcli-agent --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-agent .claude/skills/arkcli-agent && 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-agent" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-agent into .claude/skills/arkcli-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-agent", 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-agentType 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-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install volcengine/ark-cli arkcli-agent --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-agent .agents/skills/arkcli-agent && 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-agent" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-agent into .agents/skills/arkcli-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-agent", 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-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install volcengine/ark-cli arkcli-agent --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-agent .cursor/skills/arkcli-agent && 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-agent" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-agent into .cursor/skills/arkcli-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-agent", 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-agent--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-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install volcengine/ark-cli arkcli-agent --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-agent .gemini/skills/arkcli-agent && 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-agent" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-agent into .gemini/skills/arkcli-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-agent", 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-agentInstalls 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-agent -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-agent .github/skills/arkcli-agent && 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-agent" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-agent into .github/skills/arkcli-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-agent", 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-agent -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-agent --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-agent .opencode/skills/arkcli-agent && 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-agent" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-agent into .opencode/skills/arkcli-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-agent", 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-agentarkcli agent:管理 ARK Managed Agents,包括 Agent / Skill / Env / Session / File / Memory Store / Vault / MCP OAuth。控制面优先走 ForTop/OpenTOP,Session 运行时和 Files 走数据面直联。
Arkcli Agent is an agent skill from volcengine/ark-cli. arkcli agent:管理 ARK Managed Agents,包括 Agent / Skill / Env / Session / File / Memory Store / Vault / MCP OAuth。控制面优先走 ForTop/OpenTOP,Session 运行时和 Files 走数据面直联。
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `references/agent.md`, `references/debug-export.md` and `references/evals.md`).
It sits in Backend & APIs, covering OAuth and OpenID Connect. It works with Model Context Protocol. 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.
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 these keys or tokens, usually read from environment variables:
ARK_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Arkcli Agent loads about 3.7k tokens when it runs, and up to ~34k if it reads all its reference files. Until then it costs about 43 tokens; SKILL.md has 1,179 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 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.
The full file from volcengine/ark-cli at commit fb5b7be, republished under its Apache-2.0 licence (© volcengine). 1,179 words, ~3,707 tokens.
.claude/skills/arkcli-agent/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.CRITICAL — 开始前 MUST 先读取 ../arkcli-shared/SKILL.md。
当用户需要创建、查询、调试或联通 ARK Managed Agent 时使用本 skill。核心原则:先用稳定产品命令,不要直接猜 OpenTOP Action;Session 运行时资源、事件、线程、Files API 走数据面直联;MCP OAuth 登录先查后端 provider,再用 arkcli agent +mcp-login。
执行前按“先选路径”读取对应 reference;只读相关 reference,不需要一次性加载全部细节。用户请求如果已经明确是创建、复制、挂文件、聊天、MCP 登录等写操作,完成必要确认/消歧后直接执行,不要只给命令建议。
仅咨询参数含义、命令用法或解读已有完整 stdout 时,能从文档与当前证据回答就直接回答, 不为概念解释发起 live 查询。只有账号当前配置、资源状态或模型实时可用性等问题才查服务端。 已拿到完整结果时复用它;名称搜索/grep 无命中不等于资源不存在,先确认目标是 Agent、 Environment 还是 Session。用户提供明确 ID 时直接查对应资源,不先列全量清单。
| 用户输入 | AI Agent 的处理 |
|---|---|
| 未指定 Agent 主模型 | 创建任务有自然语言意图时,用 arkcli agent model list --query "<用户意图>" --format json 完整取候选并有据择优;仅列白名单时用 arkcli agent model list --format json。明确硬指标再按具体版本查 metadata,不凭记忆拼 ID |
| 需要为工具选择绑定模型 | 用 agent model list --usage tool --format json;不默认加 --primary-only,选中的 items[].model 填入 Tools[].Configs[].Models[].ID,不修改 Agent 主模型 |
| 未指定 Skill | 先查本账号 custom skill;没有合适候选再查 market/SkillHub skill |
| 给出本地 Skill zip | 先调用 agent skill create --zip,拿到返回的 skill-... ID 和版本后再创建 Agent |
| 未指定工具 | 使用 CLI 注入的完整默认工具集;显式传 --tool 时全量替换默认工具 |
| 未明确要求多模态工具 | 不查询工具模型,不添加多模态工具集、image_generate/video_generate 或其 Models;保留普通默认工具,不能因所选模型支持多模态输入而自行添加 |
| 未指定环境 | 创建 Session 时自动选择当前项目最新环境;没有可用环境才提示创建或传入环境 ID |
| 创建成功 | 必须回读 agent agent get <agent-id> --format json,展示服务端最终的 Model、System、Tools、Skills、McpServers 和扩展配置 |
| 用户期待 Agent 回复 | 短请求使用 +new session ... --message 或 events send ... --stream;大 payload / 长耗时任务使用 events send --poll,或 send 立即返回后按 cursor 轮询 events / 使用 +tail,不要让所有任务都阻塞等待 |
模型、Agent、Skill、MCP provider 等目标无法唯一确定时,遵循
arkcli-shared 的 0/1/N 结构化选择契约:先做一次最小
只读查询,选项只取本轮完整结构化结果中的真实 ID 和区分字段。多个候选会改变远端结果
时使用宿主结构化选择能力;唯一候选直接继续。选择目标只完成消歧,不等于授权后续创建、
更新或删除。
创建任务的主模型选型例外:默认由 AI 按本轮 --query 详情、实时资格与用户意图
择优,复述真实 items[].model 和依据;不能只因有多个候选就停下来问,也不能把排序第一
当作证据或把择优说成“只有一个模型可用”。用户明确的硬指标须用对应版本 metadata
验证;不能自动换身份、计费路径、超出预算或替换用户明确给出的模型。
只有多个候选的能力、版本或费用会实质影响结果且无法从用户意图安全判断时,才进入
模型选择停点:展示真实候选,用户选定前不得查询 Agent Skill,也不得执行 preview、
agent agent create/update、+new-agent、+iterate 或准备后续参数。此时选项是当前
回合的最终输出,之后不再探测写命令 --help 或调用其他工具。择优不替代执行授权,
也不适用于复制、更新、删除时对已有 Agent 的目标消歧。
| 用户意图 | 首选命令 | 细节 |
|---|---|---|
| 创建 / 更新 / 删除 Managed Agent | arkcli agent agent ... | references/agent.md |
| 复制已有 Agent 并改名 / 局部覆盖配置 | arkcli +new-agent --fork <agent-id> [--name <new-name>] | references/agent.md |
| 为创建 Agent 选择可用模型 | arkcli agent model list | references/agent.md |
| 为生图/生视频等支持模型绑定的工具选择模型 | arkcli agent model list --usage tool | references/agent.md |
| 查询模型运行参数的可选值和默认值 | arkcli agent model config <foundation-model-name> | references/model-config.md |
| 创建 Agent 时选择 Skill | 默认先查 custom,未命中再查 market;用户明确指定 market 时跳过 custom | references/skills.md |
| 查询/使用本账号 custom skill | 先 agent skill list --source custom --limit 100,无匹配时沿 NextPage 传 --page 继续;需要完整候选时再用 --page-all / --skill <skill-id> | references/skills.md |
| 查询 Ark Skill / 跨来源查询 | agent skill list --source ark 或 --source all;Ark Skill 只读 | references/skills.md |
| 上传本地 custom skill zip | arkcli agent skill create --zip <file> 或 agent agent create --skill-zip <file> | references/skills.md |
| 扫描或导入 GitHub Skill | agent skill github scan <repo> / `agent skill github import <repo> --path ... | --all` |
| 管理 custom Skill 版本 / 删除 Skill | 先完整列出版本,再按“非 latest → latest → Skill”的依赖顺序删除 | references/skills.md |
| 创建运行环境 / 会话 | arkcli agent env ... / arkcli agent session ... | references/session-files.md |
| 自托管环境 / Work Queue 排障与停止任务 | agent env create --runtime-type self_hosted / agent env work list/get/stats/stop | references/self-hosted.md |
| Environment 初始化脚本 | arkcli agent env create/update --setup-script @./bootstrap.sh | references/session-files.md |
| Session 一次性覆盖 Agent / Environment | arkcli agent session create --agent-overrides ... --environment-overrides ... | references/session-files.md |
| 升级已有 Session 的模型 / Agent 版本 / 运行配置 | arkcli agent session upgrade <session-id> | references/session-upgrade.md |
| Session 创建时绑定 TOS 目录 | 用户明确提供地址后使用 arkcli agent session create --tos-path tos://<bucket>/<prefix>/;未提供时先询问,不猜路径 | references/session-files.md |
| 选择/继续 Managed Agent 会话 | arkcli +new session | references/events-chat.md |
| 直接创建新会话并聊天 | arkcli +new session <agent-id> --environment-id <env-id> | references/events-chat.md |
| 给已有会话发消息或实时看回复 | 默认 events send 只负责写入;需要 SSE 回复时加 --stream 自动跟随 event cursor(--wait 保留为兼容别名),实时入口默认请求 agent.message / agent.thinking Event Deltas;也可使用 +tail/events stream,--no-event-deltas 回退完整事件;+new session/+iterate 内部自动使用补偿 channel | references/events-chat.md |
| 主动压缩会话上下文 | `arkcli agent session compact <session-id> [--instructions <text | @file>]` |
| 看 session 诊断 / 导出诊断包 | arkcli +debug <session-id> / arkcli +export <session-id> | references/debug-export.md |
| 上传文件并挂到已有 session | arkcli agent session resources add <session-id> --path <file> | references/session-files.md |
| 只上传 / 查询 Files API 文件 | arkcli agent file upload/list/get/wait/delete | references/session-files.md |
| 管理 memory store / memories | arkcli agent memory-store ... | references/interfaces-gaps.md |
| 查询可挂载 MCP / 管理 Vault / Credential / MCP OAuth | arkcli agent vault oauth-provider list / arkcli agent vault ... / arkcli agent +mcp-login ... | references/mcp-vault.md |
--usage agent 按 ep_agent.support 选择主模型;--usage tool 按具体版本的 epa_tool_model.support 选择工具模型,两者不取交集。两种查询都不默认加 --primary-only,也不默认按 primary_version 排除候选;只有用户明确要求“只看主版本”时才加。items[].model,不是内部 id(如 epm-*)。只给支持绑定的工具配置 Models;字段含义与完整 Tools 替换示例见 工具模型绑定。cache.source/fetched_at/expires_at;只有需要刷新时才加 --refresh-cache,不要每次查询都强刷。失败冷却为 1 分钟,强刷也不能绕过;错误不等于空候选。name + version 查询 ListModelMetaDatas 后筛选;无额外要求不逐模型补查。流程、字段与缺失值处理见 按具体版本筛选。agent model config 查询运行参数,不提供工具支持性。用户明确给出的模型 ID 仍交给创建/更新接口判断,不把缓存查询变成写入硬拦截。完整参数、缓存隔离与 query 模式边界见 查询说明。type=platform 的 Profile,不自动使用 Agent Plan / Coding Plan(含团队版)的套餐凭证。登录成功不代表默认 Profile 支持 MA。auth status --format json 核对类型;默认是套餐类型时,对本次命令指定已确认的 --profile <platform-profile>,不自动执行 profile use 改全局默认。没有可用 Platform 或身份/项目不明确时,按 Profile Skill 处理并取得确认,不猜名称或跨账号重试。--api-key 或 ARK_API_KEY,此时即使默认是套餐 Profile,也不会因其类型被拦截。优先级为 --api-key > ARK_API_KEY > Platform Profile 的 Key;Key 的有效性与权限由服务端验证,认证失败时停止,不跨账号重试。--env 使用标准数据面地址,不继承 Profile 的套餐或自定义路由。仅提供 Key 即可调用数据面,无 Profile 也不必额外提供地址。显式 --base-url / ARK_BASE_URL 优先,但必须同时显式提供 Key;只覆盖地址不能替换套餐凭证。arkcli auth status --format json,处理未登录、SSO 过期或 STS refresh 失败。仅使用显式 Key 的数据面调用不要求先登录。managed_agent_profile_required 时停止,不改走 raw API 绕过。离线 --dry-run 不检查在线资格,预览成功不代表真实调用成功。上述覆盖均只影响本次调用,不修改默认 Profile 或保存的 Key。--env prod,不要再默认跑 stg。--env stg 和配套 Key;未指定地址时 MA 数据面自动使用标准 stg 地址。若显式提供地址,确认它也属于目标环境(显式地址不会被 --env 改写)。arkcli auth login --no-browser 拿 URL;用户贴回 base64 code 后,再跑 arkcli auth login --no-browser --code <code>。--page-all;未显式传单页大小时,CLI 默认每页取 100 条。默认最多请求 10 页,可用 --page-limit <N> 调高,--page-delay <ms> 控制页间隔。Page、PageNumber、PageToken、after,并合并结果。agent model list、memory-store creators、session resources list 没有可用分页契约,不要为它们假设 --page-all 能补全结果。命中 --page-limit 后应检查返回的 NextPage、has_more 或 TotalCount,判断是否仍有未拉取数据。delete 命令在真实 TTY 且未传 --yes 时会显示不可逆警告并询问 [y/N];输入 y/yes 才会调用后端,其他输入会取消。--yes 时返回 type=requires_confirmation,不会调用后端。只有用户已经明确确认删除目标后,调用方才可以补 --yes 重试。--dry-run 不是全域能力。只有命令自身 --help 列出该 flag 时才可用;
当前主要覆盖可由本地 payload 确定的 Env/Session/Memory/Vault/Credential
写请求,以及 agent agent create/update/delete、agent skill create/update/delete
和 agent file upload/delete,以及会写本地文件的 agent skill download、
+export。+new-agent、+iterate、MCP login 与所有纯读命令都不注册。
Client Preview 只生成零网络 preview.v1 计划;它不代替真实执行前的开通、
版本/依赖校验或删除确认。arkcli 命令。不要把 session create、写入 ID、events send、events list 用 &&、;、管道或 heredoc 串成一个长命令。session create、Agent 创建、文件上传等写操作成功后,立即从结构化输出提取并保存 ID;下一次调用使用已经确认的字面量 ID,不要依赖同一 shell 中的变量赋值继续执行。session get、events list 或 +debug 诊断;不要让后续命令被前一个阻塞步骤掩盖。arkcli --format json 独立返回,再在下一步解析结果。这样即使请求超时,也能区分是创建、发送还是回查阶段失败。session create 超时后结果可能未知。先用 session list/get 按返回的标题、Agent、环境和创建时间检查是否已经创建,再决定是否重试;没有幂等键时不要盲目重复创建。events send 超时后也可能已经被服务端接收。先用返回的 event cursor、发送时间或最近的 user event 查询 events list;确认没有接收记录后才允许重试,避免重复发送用户消息。events send --stream 达到 stream 等待上限后会自动切换为 events list polling,默认再等待 120 秒;--wait 保留相同行为作为兼容别名。两阶段都超时才返回带 cursor 恢复命令的非 0 错误。此时不要重发原消息,继续 list/poll 同一个 cursor。events list/get 属于只读请求,可以使用有限次数、指数退避的重试;继续使用同一个 after cursor,不要因为重试而从历史开头重新读取。| 命令 | 说明 |
|---|---|
arkcli agent agent list/get/create/update/delete/versions | Agent CRUD + 版本 |
arkcli agent model list | 默认查询主模型,items[].model 用于 --model;--usage tool 查询工具模型,结果用于 Configs[].Models[].ID;--query 可增强详情/排序 |
arkcli +new-agent | Agent create 增强入口;支持 --fork/--from 复制已有 Agent 后创建新 Agent |
arkcli +iterate | 更新 Agent 配置,创建新 Session,并进入 one-shot/REPL 试运行;--environment-id/--env-id 可选,省略时自动选择最新环境 |
arkcli agent skill search/list/get/create/update/delete/versions/download/set-protection/github | Market/custom/Ark Skill 查询、GitHub 导入、custom Skill 保护与版本管理;Ark Skill 只读 |
arkcli agent env list/get/create/update/delete | Environment CRUD;当前 env list 没有 --status,状态筛选规则见 session-files.md |
arkcli agent session list/get/create/update/delete | Session CRUD |
arkcli agent session upgrade <session-id> | 升级已有 Session 运行配置,返回受理状态;使用 snake_case 请求并回读验证 |
arkcli agent session resources list/add/get | 数据面 session resources;get 是 CLI 基于 list 的本地筛选 |
arkcli agent session events list/send/stream | 数据面 events;stream 默认请求 Event Deltas 并输出 SSE/NDJSON 行;--no-event-deltas 回退完整事件;user.custom_tool_result 必须带 custom_tool_use_id,user.tool_result 仅允许 self_hosted,CLI 会前置校验 |
arkcli agent session compact <session-id> | 主动压缩上下文;正常 thread idle/end_turn + session idle/end_turn 表示命令完成,compacted 事件是可选的实际压缩确认 |
arkcli agent session threads list/get | 数据面 threads |
arkcli agent file list/get/upload/wait/delete | 数据面 Files API |
arkcli agent memory-store list/get/create/update/delete | Memory Store CRUD |
arkcli agent memory-store memories list/get/create/batch-create/update/delete | Memory CRUD |
arkcli agent vault list/get/create/update/delete | Vault CRUD |
arkcli agent vault oauth-provider list | 查询后端已注册 MCP Provider;返回的 MCP server 信息可用于 Agent --mcp-server |
arkcli agent vault oauth-flow create | 裸创建 Vault OAuth Flow,适合脚本自带 redirect URL |
arkcli agent vault credentials list/get/create/update/delete | Credential CRUD |
arkcli agent +mcp-login | 托管 MCP OAuth 登录:本地 callback + CreateVaultOAuthFlow + 等待 credential 创建 |
arkcli +chat <prompt> | Responses API 快速对话;不要把它当 Managed Agent session 入口 |
arkcli +tail <session-id> | 人类可读 event stream |
arkcli +new session | Managed Agent session 选择器;可继续已有 session,或选 agent/env 起新 session |
arkcli +new session <agent-id> --environment-id <env-id> | Managed Agent 新 session 直达入口;固定先创建新 session,再 REPL / one-shot |
arkcli +debug <session-id> | 聚合 session、events、resources、threads 做诊断 |
arkcli +export <session-id> | 导出诊断 tar.gz |
复杂字段如 Tools、Skills、McpServers、Multiagent、Metadata、Tags 支持 JSON/YAML 文件、stdin 或结构化 flags。TOP 请求使用 CamelCase,inline 对象兼容常见 lower/snake case alias;session upgrade 是例外,使用原生 snake_case,只读取显式文件/flags,不自动读取 stdin。创建成功回显必须展示服务端最终的身份、模型、System、Tools、Skills、MCP 和扩展配置,不能只展示摘要;需要核对完整结果时用 agent agent get <agent-id> --format json 或 --format yaml。
Memory get 的 --view 语义:默认按 basic 请求,只返回 metadata 和 ContentSha256;--view full 保留 Content。若服务端仍在 basic 下返回 Content,CLI 会在输出层剥离 Content,但这只能控制输出,不能挽回已经产生的网络传输;服务端仍需正确实现 View 参数以节省带宽。
references/agent.md:创建、复制、查找 Agent、默认工具、工具模型绑定与查询缓存。references/skills.md:Market skill 搜索、custom skill zip 上传、skill ref 组装。references/session-files.md:Env / Session / Files API / Session resources。references/events-chat.md:events send/list/stream、+new session 选择器、+tail。references/mcp-vault.md:Vault、Credential、MCP OAuth、Agent 挂 MCP。references/debug-export.md:+debug、+export、端到端验证模板。references/interfaces-gaps.md:接口链路和当前 gap。references/evals.md:Agent/Skill/GitHub/Compact 最小评估用例。© 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 11 other files (references) in skills/arkcli-agent of volcengine/ark-cli.
Open the folder on GitHubat commit fb5b7be
Arkcli Agent 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 Agent this skillvolcengine/ark-cli | 140 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | |
| Declarative Agent Developermicrosoft/work-iq | 1k | — | ~3.2k | Automated safety check: Pass | Custom licence | |
| Review Security ReportPrefectHQ/fastmcp | 28k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Entra Agent Idmicrosoft/GitHub-Copilot-for-Azure | 255 | 3 repos | ~4k | Automated safety check: Pass | MIT | |
| Neo4j Aura Agent Skillneo4j-contrib/neo4j-skills | 114 | — | ~3.8k | Automated safety check: Notes | MIT | |
| Frontmcp Auth UIagentfront/frontmcp | 146 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 |
microsoft/work-iq
Create, build, deploy, and localize declarative agents for M365 Copilot and Teams.
PrefectHQ/fastmcp
Review FastMCP vulnerability reports before accepting, rejecting, patching, scoring, or publishing them.
microsoft/GitHub-Copilot-for-Azure
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant)…
neo4j-contrib/neo4j-skills
Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance.
agentfront/frontmcp
A skill your agent uses when customizing, branding, or replacing the built-in FrontMCP OAuth pages (the login, consent, federated-select, incremental-authorization, and error pages) with your own…
Xquik-dev/x-twitter-scraper
Connect, verify, and troubleshoot Xquik's remote MCP server.
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。
Works with
Categories
arkcli agent:管理 ARK Managed Agents,包括 Agent / Skill / Env / Session / File / Memory Store / Vault / MCP OAuth。控制面优先走 ForTop/OpenTOP,Session 运行时和 Files 走数据面直联。. Arkcli Agent is an agent skill from volcengine/ark-cli.
Arkcli Agent fits situations like: tasks that involve OAuth and OpenID Connect.
Run `npx skills add volcengine/ark-cli --skill arkcli-agent -a claude-code`. Or copy the skill folder (skills/arkcli-agent in volcengine/ark-cli) into .claude/skills/arkcli-agent in your project. Claude Code loads it when a task matches its description.
Run `npx skills add volcengine/ark-cli --skill arkcli-agent -a codex`. Or copy the skill folder (skills/arkcli-agent in volcengine/ark-cli) into .agents/skills/arkcli-agent 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-agent -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-agent, .gemini/skills/arkcli-agent, .github/skills/arkcli-agent and .opencode/skills/arkcli-agent in your project.
Going by SKILL.md and its folder, Arkcli Agent needs credentials named ARK_API_KEY. Our summary lists: A credential in ARK_API_KEY.
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 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.
Arkcli Agent 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 3.7k tokens (SKILL.md is roughly 15k 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 30k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Arkcli Agent: Declarative Agent Developer (microsoft/work-iq, 1k stars), Review Security Report (PrefectHQ/fastmcp, 28k stars), Entra Agent Id (microsoft/GitHub-Copilot-for-Azure, 255 stars) and Neo4j Aura Agent Skill (neo4j-contrib/neo4j-skills, 114 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.