Seedance
songguoxs/seedance-prompt-skill
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…
arkcli doctor 统一入口,覆盖 CLI 健康、account、error、infer-endpoint、model、metrics、report 与 Ark 图片/视频来源特征验证。用户给 1-20 个媒体 URL 并问是否由 Ark/Seedance/Seedream 生成时,走 doctor +verify-origin:整批只披露并确认一次费用,确认前不发…
$ npx skills add volcengine/ark-cli --skill arkcli-doctor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install volcengine/ark-cli arkcli-doctor --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-doctor .claude/skills/arkcli-doctor && 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-doctor" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-doctor into .claude/skills/arkcli-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-doctor", 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-doctorType 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-doctor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install volcengine/ark-cli arkcli-doctor --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-doctor .agents/skills/arkcli-doctor && 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-doctor" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-doctor into .agents/skills/arkcli-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-doctor", 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-doctor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install volcengine/ark-cli arkcli-doctor --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-doctor .cursor/skills/arkcli-doctor && 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-doctor" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-doctor into .cursor/skills/arkcli-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-doctor", 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-doctor--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-doctor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install volcengine/ark-cli arkcli-doctor --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-doctor .gemini/skills/arkcli-doctor && 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-doctor" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-doctor into .gemini/skills/arkcli-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-doctor", 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-doctorInstalls 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-doctor -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-doctor .github/skills/arkcli-doctor && 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-doctor" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-doctor into .github/skills/arkcli-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-doctor", 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-doctor -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-doctor --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-doctor .opencode/skills/arkcli-doctor && 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-doctor" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-doctor into .opencode/skills/arkcli-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-doctor", 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-doctorarkcli doctor 统一入口,覆盖 CLI 健康、account、error、infer-endpoint、model、metrics、report 与 Ark 图片/视频来源特征验证。用户给 1-20 个媒体 URL 并问是否由 Ark/Seedance/Seedream 生成时,走 doctor +verify-origin:整批只披露并确认一次费用,确认前不发…
Arkcli Doctor is an agent skill from volcengine/ark-cli. arkcli doctor 统一入口,覆盖 CLI 健康、account、error、infer-endpoint、model、metrics、report 与 Ark 图片/视频来源特征验证。用户给 1-20 个媒体 URL 并问是否由 Ark/Seedance/Seedream 生成时,走 doctor +verify-origin:整批只披露并确认一次费用,确认前不发 Create/Get 业务请求,最终完整转交服务端 JSON,禁止解释 IsOfficial。其余错误码(包括 ServerOverloaded、ModelNotOpen)、模型名、ep-xxx、失败/慢/超时/限流、健康度、P99/Cache、内容审核、DNS/TCP/TLS/时钟等按正文诊断路由。来源验证不判断内容真假、版权归属、法律认证或内容安全。安装/登录/profile/API Key 归 arkcli-shared/auth;纯用量明细归 arkcli-usage;部署、Endpoint CRUD、模型元信息归对应 skill。
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `CONTRIBUTING.md`, `references/error-codes.md` and `references/evals.md`).
It sits in Media & Creative, covering AI video generation. It works with Seedance. 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.
7 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 (its code samples are bash).
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 Doctor loads about 4.9k tokens when it runs, and up to ~47k if it reads all its reference files. Until then it costs about 119 tokens; SKILL.md has 1,022 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). 1,022 words, ~4,862 tokens.
.claude/skills/arkcli-doctor/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.CRITICAL — 开始前 MUST 先用 Read 工具读取 ../arkcli-shared/SKILL.md(认证闸门、命令选择顺序、输出与安全规则)。
arkcli doctor 是 Ark CLI 唯一的对外诊断收口。所有诊断与修复建议都从 arkcli doctor [<scope>] [<id>] 出,诊断命令默认只读;修复动作按命令输出的建议和对应 reference 执行。Agent 拿到用户的报错 / 资源 ID / 含糊问题后,先用本 skill 决定走哪条路径,再 delegate 到对应 scope reference 或错误码 reference。
边界:安装、版本、登录、profile、AK/SK 认证类问题归
arkcli-shared/arkcli-auth;这里只覆盖arkcli doctor命令家族(业务侧诊断)。
本 skill 一次性覆盖八个平行 domain。每个 domain 一份 reference,按用户场景路由:
| Domain | 命令 | Reference | 解决什么 |
|---|---|---|---|
| CLI 健康(默认) | arkcli doctor | references/scope-cli.md | 本地二进制版本 / 网络联通 / 时钟偏差 / 当前 profile 认证——onboarding 首查 |
| account | arkcli doctor account | references/scope-account.md | identity / realname / balance / IAM Ark 系统预置策略 / VMP 三段 / TOS 开通 |
| 错误码 | arkcli doctor error <code> | references/error-codes.md | 单错误码翻译成结构化诊断 + 修复(含生视频 5 个 subtype + 通用 Ark/公共码) |
| infer-endpoint | arkcli doctor infer-endpoint <id> | references/scope-infer-endpoint.md | 单接入点状态 / 用量 / 错误率 / 配额压力 |
| model | arkcli doctor model <name> | references/scope-model.md | 跨接入点的模型整体诊断(用量 / 配额 / top endpoint / 模态自适应指标) |
| metrics | arkcli doctor metrics <id> | references/scope-metrics.md | 36 条具名 PromQL 查询(指标值直出,不打健康判定,给 LLM/SRE 拿数) |
| report | arkcli doctor report | references/scope-report.md | seedance 2.x 效果问题上报(badcase → 方舟排障平台) |
| verify-origin | arkcli doctor +verify-origin ... | references/verify-origin.md | 对 1-20 个图片/视频 URL 创建来源特征验证任务并轮询官方结果 |
arkcli doctor # CLI 健康(默认 scope,install/connect/config)
arkcli doctor account # 账号级诊断(→ references/scope-account.md)
arkcli doctor infer-endpoint <ep-id> # 单接入点诊断(→ references/scope-infer-endpoint.md)
arkcli doctor model <model-name> # 模型维度诊断(→ references/scope-model.md)
arkcli doctor metrics <query-id> # 具名 PromQL 查询(→ references/scope-metrics.md)
arkcli doctor error <error-code> # 错误码查表(只读,→ references/error-codes.md)
arkcli doctor report --task-id ... --feedback ... # seedance 2.x 效果问题上报(→ references/scope-report.md)
arkcli doctor +verify-origin <url> [url...] # 1-20 个媒体来源特征验证(→ references/verify-origin.md)普通诊断命令是扁平 verb;
+verify-origin是显式的任务型 workflow。--window <duration>(默认 24h)控制 VMP 时间窗;结构化输出优先使用--format json。修复建议由诊断结果和 reference 给出,不要给 doctor 命令拼接未注册的参数。
用户要验证一个或多个图片/视频是否包含 Ark、Seedance、Seedream 生成来源特征时:
references/verify-origin.md;--yes,获取整批费用披露;这一步不获取 invoker,也不发 Create/Get 业务请求;--yes,该确认覆盖整批所有 URL;该路由不用于判断媒体内容真假、假新闻、版权归属、法律认证、内容安全、画质或播放质量。IsOfficial=True/False/Null 只能按服务端原值转交,Agent 不得自行下结论。
用户给了具体 Ark 错误码、但没有模型名或 ep-xxx 时,先执行一次只读 arkcli doctor error <code> --format json,再按返回的 category、subtype、root_cause 和对应 reference 解释;不能仅凭报错文案或记忆直接给确定性根因。ModelNotOpen 的查表含义是当前账号未开通该模型,不能无证据扩写成 Key 失效、模型名拼错或网络故障。ServerOverloaded 是服务资源紧张,不能改写成账号配额耗尽;流量突增/冷启动是通用可能原因,不是对该 Request ID 的取证。用户没给具体资源 ID、单次 Trace 时,保留未知并请求所需证据,不编造该资源的健康度或本次请求原因。
聚合 doctor model / doctor infer-endpoint / doctor metrics 只能描述指定时间窗的总体分布,不能证明用户某一次请求采用了非流式、未限制输出、默认高思考档或重试,也不能从 TPOT/Token 均值反推出那次端到端时延的唯一原因。需要单次根因时核对对应请求配置和 Trace,或在相同输入上分别实测档位;没有这些证据就把配置方案写成待验证建议,而不是“已定位的根因”。
[!IMPORTANT] 诊断意图优先于上报意图:先检查用户是否要求“检查 / 诊断 / 排查 / 分析原因 / 为什么 / 看健康 / 看指标”等诊断动作。只要存在任一诊断意图,即使同时说“并上报”,也必须先走
doctor model或doctor infer-endpoint;诊断返回report_suggestion且确认是效果类后,再询问用户,用户同意才进入 report(Path A)。只有用户明确要求“直接上报 / 提交 badcase / 反馈到方舟”,且没有任何诊断诉求,上下文又确认是 Seedance 2.x + 效果类问题,才可跳过诊断进入scope-report.md的 Path B。用户只是描述“字幕错 / 角色漂移 / 闪烁”等效果问题、但没有说要上报时,同样不得直接跑 report。
[!WARNING] 第一步 MUST 做:扫一遍用户消息里有没有资源 ID(模型名 like
doubao-*/seed-*或ep-xxx)。除上方已经满足全部门槛、且不含诊断意图的纯上报 Path B 外,只要有资源 ID,就 MUST 走doctor <scope> <id>,不管同时有没有错误码。资源 ID 在场时直接doctor error <code>是错误路径——会丢掉错误率分布、top endpoint、配额压力等关键诊断信号。反例自检(如果你打算这么干,停下来):
❌ 用户说「我的 doubao-seedance-1-0-pro 一直报 ContentRiskBlocked」 → 你跑
arkcli doctor error ContentRiskBlocked✅ 正解:跑
arkcli doctor model doubao-seedance-1-0-pro,再按返回的错误码分布加载error-codes.md的 subtype 段❌ 用户说「ep-xxx 报 ModelAccessDenied」 → 你跑
arkcli doctor error ModelAccessDenied✅ 正解:跑
arkcli doctor infer-endpoint ep-xxx,再加载error-codes.md的 model_access_denied 段
用户消息(自然语言 / 错误 JSON / "看看 ep-xxx" / 错误码 / request_id)
│
▼
① 抽取关键值:error_code / error_message / resource_id (ep-xxx / model-name) / request_id
│
▼
② 按下表决定 Path(**有 resource_id 一律 Path 1 / Path 3**,不要降级到 Path 2)
│
▼
③ 跑相应 doctor 命令 + 加载对应 reference
│
▼
④ 摘 findings + recommended_fixes 给用户(不复述完整 JSON)
│
▼
⑤ 修复命令一律先给用户看、等确认;不要替用户执行写操作| 有错误码 | 无错误码 | |
|---|---|---|
| 有资源 ID | Path 1(最理想):跑 doctor <scope> <id> + 加载 error-codes.md 对应 subtype | Path 3:跑 doctor <scope> <id> 看整体(状态/用量/错误率/配额) |
| 无资源 ID | Path 2:直接 doctor error <code> 查表 → 加载 error-codes.md;不跑 scope | Path 4/5:只有 request_id 或啥都没有 → 追问用户要资源 ID 或具体错误信息 |
暂不支持 request_id 反查能力(涉及鉴权与平台内部数据)。Path 4/5 不要瞎猜,直接追问。
只有 request_id / x-request-id / LogID 时,明确说明当前 doctor 不能反查单条
日志或 trace;请求用户补充错误码/完整错误 JSON、资源 ID,或发生时间与症状。
不要把 Request ID 传给 doctor error 当错误码,也不要把资源聚合诊断称为该请求的
调用链。只有 ID 且无法补充时,保留它供工单/支持排查,不承诺控制台必有跨服务日志权限。
先区分证据来源:doctor error 是本地错误码目录,返回的 root_cause 是通用解释,
不是对该账号或某个 Request ID 的日志取证。资源诊断和 metrics 的聚合值必须带上实际
资源、时间窗口与可用状态;空数组、缺失字段、查询失败不能改写成“零错误”或“健康”。
建议修复不等于已经修复;没有执行并验证的动作只能列为下一步。
最终回答必须把内容分为以下三类,不能把相关性或建议写成已证实根因:
request_id 时属于这一类,不能声称已查到该请求的日志或 trace。[!IMPORTANT] Path 1 vs Path 2 不要走错:只要用户消息里既给了错误码又给了资源 ID(模型名 /
ep-xxx),MUST 走 Path 1(先doctor <scope> <id>拿到该资源在该错误码上的真实分布 / 占比 / top endpoint,再加载error-codes.md对应 subtype 解读修复)。不要直接doctor error <code>当成 Path 2 处理——那会丢失模型上下文(错误率分布、top endpoint、配额压力等关键诊断信号)。Path 1 触发条件示例:
- 「我的 doubao-seedance-1-0-pro 一直报 ContentRiskBlocked」 →
doctor model doubao-seedance-1-0-pro,不是doctor error ContentRiskBlocked- 「ep-xxx 报 ModelAccessDenied」 →
doctor infer-endpoint ep-xxx,不是doctor error ModelAccessDenied- 只有用户只给错误码 / 错误 JSON、没给资源 ID 时(Path 2),才直接查表。
[!NOTE] 不要为
doctor model/doctor infer-endpoint做兜底前置调用:这两条命令内部已经先跑model.exists/endpoint.exists,覆盖了"模型/接入点是否存在"。不要在调用前先跑arkcli models list/arkcli infer endpoint list/arkcli auth status等做存在性 / 身份兜底——doctor 命令失败时会自己报清楚原因(404 / VMP precheck / 鉴权),按它的输出处理即可,多余兜底徒增 token 消耗。
按 scope 找 reference:
| scope | reference | 触发的用户语义 |
|---|---|---|
| 默认(CLI 健康) | references/scope-cli.md | 刚装 arkcli 能用吗 / 突然跑不通 / 网络联通 / 时钟偏差 / 当前 profile 认证 |
account | references/scope-account.md | 没权限 / 账号被冻结 / 子账号没 Ark 权限 / VMP 跨服务授权 / 实名 / 余额 / TOS |
infer-endpoint | references/scope-infer-endpoint.md | ep-xxx 报 429 / 慢 / 状态异常 / 报某错误码 / 想看用量与配额压力 |
model | references/scope-model.md | 跨接入点看模型整体;模型级配额压力;按模态自适应的延迟与生成时长指标 |
所有错误码诊断细则集中在一个文件:references/error-codes.md。arkcli doctor error <code> 返回的 JSON 里 reference 字段统一指向该文件,subtype 字段告诉你跳到哪个小节。
| 业务领域 | subtype | 跳节 |
|---|---|---|
| 方舟错误码 | input_real_face | error-codes.md §1.1.1 |
| 方舟错误码 | input_copyright | error-codes.md §1.1.2 |
| 方舟错误码 | input_content_safety | error-codes.md §1.1.3 |
| 方舟错误码 | output_video_copyright | error-codes.md §1.1.4 |
| 方舟错误码 | output_video_safety | error-codes.md §1.1.5 |
| 方舟错误码 | model_access_denied | error-codes.md §1.2 |
| 方舟错误码 | rate_limit_exceeded | error-codes.md §1.3 |
其余 Volc 原生码已在
error-codes.md各 section 索引表里覆盖(含 HTTP / 释义 / 处理方式)。error-codes.md顶部目录是首要导航入口。doctor 的前置依赖闸门(VMP / TLS / TOS 跨服务授权)不是 API 错误码,由
arkcli doctor account输出 +arkcli-shared/arkcli-auth联合处理。新错误码贡献流程:
CONTRIBUTING.md。
doctor 命令家族输出两套 JSON schema——按命令分。
arkcli doctor / account / infer-endpoint / model)arkcli doctor <scope> <id> --format json 返回一份结构化 JSON。不要做严格 schema 校验——字段会随版本增减(如 TTFT/TPOT/replicas 等指标),按字段名按需取;这不表示支持 request_id 反查。
注意:默认 CLI scope(arkcli doctor 无参)的 schema 是扁平三段(installation / connectivity / configuration),跟业务 scope 的通用字段(checks[] / findings[])不对齐——CLI 段项目固定且少,直接看字段即可。业务 scope 遵循下表:
| 顶层字段 | 含义 |
|---|---|
scope | cli / account / model / infer-endpoint |
subject | 资源 ID(model name / endpoint id),CLI 与 account 留空 |
window | VMP 时间窗(如 24h) |
checks[] | 各 check 项的 raw 结果:{ id, status: pass/warn/fail/skip, value, message } |
findings[] | 聚合后的问题清单:{ severity, error_code?, root_cause, evidence } |
recommended_fixes[] | 修复建议:{ id, kind: skill/url/command, target, reversibility } |
error.blocking_dependency? | 前置依赖未通过(如 VMP 三段授权失败),命令终止 + 引导 fix |
arkcli doctor error <code> 单错误码查表这条命令是只读查表——不需登录、不消耗推理 token——把一个错误码翻译成结构化诊断。返回字段:
| 字段 | 含义 |
|---|---|
category | 顶层类别(如 policy / permission / quota / infrastructure) |
subtype | 类别下的子类型(如 input_real_face / model_access_denied / rate_limit_exceeded) |
code | 命中的火山真实错误码(原值回显,用于确认输入原码) |
root_cause | 根因,用户友好的一句话 |
hint | 修复指引(可跑的命令,或需用户做的动作) |
rules | 触发信号候选;多个 = 复合错误码,需消歧(按 reference 里的判定步骤择一) |
needs_backend | 依赖但尚未上线的能力(如 deface)——不要假装能自动修 |
skill | 固定 arkcli-doctor(就是本 skill) |
reference | 统一是 error-codes(指向 references/error-codes.md);用 subtype / code 定位具体小节 |
给用户看时:按“证据 / 推断 / 未知”分层,摘 findings + recommended_fixes(scope 命令)或 root_cause + reference 段里的修复方案(error 命令),不要复述完整 JSON;建议执行需用户二次确认。
doctor 默认输出的是聚合统计值(如 error_rate、ttft.p99、tpm_peak)——一个数概括一段时间,足够判断"健康吗 / 配额够吗"。
底层数据来自 VMP 的 Prometheus 时序流,但 doctor model / doctor infer-endpoint 当前只返回聚合统计,不提供切换为原始时序的参数。聚合会平均掉突发与抖动,回答不了“是不是某一刻爆发的 / 是稳定高还是脉冲撞顶”;需要原始时序时,转到 references/scope-metrics.md 核对现有具名查询或 raw 查询能力,不要编造参数。
| 用户问什么 | 用哪种 |
|---|---|
| "现在怎么样 / 健康吗" | 聚合(默认) |
| "什么时候开始 / 持续多久 / 突发还是稳态" | 原始时序 |
详细决策规则与每类指标的时序分析方法见 references/scope-infer-endpoint.md 的"聚合统计 vs 原始时序"段。
arkcli doctor 默认只读体检,不消耗推理 token、不改任何资源。doctor +verify-origin 会创建远端异步任务,Volc 新建批次可能收费;整批只确认一次,确认前禁止获取 invoker 或发任何请求。+gen / +chat,先把命令给用户看、等确认。needs_backend 字段非空(如 deface)时如实告诉用户该能力尚未上线,给可行替代。--auto-bindarkcli doctor metrics / model / infer-endpoint 三条命令都依赖 VMP(托管 Prometheus)数据,调命令前会按顺序自动检测三件事:
GetSubscription)—— 账号是否已开通 VMP;CheckServiceLinkedRole,ServiceName=ark)—— 是否已为 ark 建过服务关联角色;ListTelemetryConfigs)—— 是否已把某个 VMP workspace 绑到 ark observability。任何一步没通过,命令直接报 *output.ExitError 并附 LinkOpenMgmtCloudProduct 跳转链接(云产品开通页 + cloudProduct 抽屉),不会替用户开通订阅或建 SLR——这两步必须在控制台勾「同意条款」。
只有"前两步通过、第三步缺绑"这一种情形可以让 CLI 自动收尾:
# 默认行为:未绑定时直接报错并提示加 --auto-bind
arkcli doctor metrics request.qpm
# 自动建 ark_default workspace(vmp.standard.15d / 防误删)+ 调
# CreateTelemetryConfig 绑到 ark observability
arkcli doctor metrics request.qpm --auto-bind
arkcli doctor model <model-name> --auto-bind
arkcli doctor infer-endpoint <endpoint-id> --auto-bind行为细节:
ark_default;metrics 子命令显式传 --workspace-id <uuid> 时跳过 precheck,尊重多账号 / 联调场景。什么时候建议加 --auto-bind:
什么时候不加:
doctor 对 RPM/TPM 配额压力的阈值是写死的(用户后续可配置):
| 占比 | severity | 表现 |
|---|---|---|
≥95% | fail | 已经/即将限流,立即提配额 |
≥80% | warn | 高压,建议提配额或调流量分布 |
≥50% | info | 健康但有空间 |
<50% | pass | 充裕 |
错误率默认阈值 5% 以上 warn,具体 scope 的 reference 可在自己的细则里覆盖。
arkcli-shared / arkcli-autharkcli-deploy(不是诊断)arkcli-infer-endpointarkcli-usagearkcli-modelsreferences/scope-cli.md — CLI 健康检查(默认 scope)细则references/scope-account.md — 账号级诊断细则(identity / compliance / permissions / ecosystem)references/error-codes.md — 错误码总册(生视频 + 通用 Ark + 公共码)references/scope-infer-endpoint.md — 单接入点诊断细则references/scope-model.md — 单模型诊断细则references/scope-report.md — seedance 2.x 效果问题上报(badcase report)references/verify-origin.md — 1-20 个图片/视频来源特征验证、整批费用确认与严格结果转交references/evals.md — 来源验证 trigger、一次整批确认、恢复与严格转交回归CONTRIBUTING.md — 加错误码 / scope check / fixer 的贡献入口© 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 10 other files (references) in skills/arkcli-doctor of volcengine/ark-cli.
Open the folder on GitHubat commit fb5b7be
Arkcli Doctor 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 Doctor this skillvolcengine/ark-cli | 140 | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Seedancesongguoxs/seedance-prompt-skill | 2.9k | 1 repos | ~2.5k | Automated safety check: Pass | None | |
| SN Motion HTMLOpenSenseNova/SenseNova-Skills | 5.7k | — | ~2.2k | Automated safety check: Notes | MIT | |
| Seedance Prompt Endexhunter/seedance2-skill | 4.2k | — | ~3.8k | Automated safety check: Pass | MIT | |
| Seedance Japanese Prompt ExamplesEmily2040/seedance-2.0 | 7.5k | 1 repos | ~898 | Automated safety check: Pass | MIT | |
| Seedance 2 5 Video Directorliyue-aigc/seedance-2-5-video-director | 546 | — | ~3.5k | Automated safety check: Pass | MIT |
songguoxs/seedance-prompt-skill
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成"…
OpenSenseNova/SenseNova-Skills
Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.
dexhunter/seedance2-skill
Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation.
Emily2040/seedance-2.0
Provides Japanese prompt patterns and safe example rewrites for Seedance 2.0 video generation, with reference tags kept intact and each example labeled by risk.
liyue-aigc/seedance-2-5-video-director
Design, derive, optimize, diagnose, and rewrite scripts or copy-ready prompts specifically for Dreamina/即梦 Seedance 2.5.
dexhunter/seedance2-skill
为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。
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 doctor 统一入口,覆盖 CLI 健康、account、error、infer-endpoint、model、metrics、report 与 Ark 图片/视频来源特征验证。用户给 1-20 个媒体 URL 并问是否由 Ark/Seedance/Seedream 生成时,走 doctor +verify-origin:整批只披露并确认一次费用,确认前不发…. Arkcli Doctor is an agent skill from volcengine/ark-cli.
Arkcli Doctor fits situations like: tasks that involve AI video generation.
Run `npx skills add volcengine/ark-cli --skill arkcli-doctor -a claude-code`. Or copy the skill folder (skills/arkcli-doctor in volcengine/ark-cli) into .claude/skills/arkcli-doctor in your project. Claude Code loads it when a task matches its description.
Run `npx skills add volcengine/ark-cli --skill arkcli-doctor -a codex`. Or copy the skill folder (skills/arkcli-doctor in volcengine/ark-cli) into .agents/skills/arkcli-doctor 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-doctor -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-doctor, .gemini/skills/arkcli-doctor, .github/skills/arkcli-doctor and .opencode/skills/arkcli-doctor in your project.
SKILL.md names no scripts, command-line tools or credentials: Arkcli Doctor 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 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 Doctor 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 4.9k tokens (SKILL.md is roughly 19k 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 42k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Arkcli Doctor: Seedance (songguoxs/seedance-prompt-skill, 2.9k stars), SN Motion HTML (OpenSenseNova/SenseNova-Skills, 5.7k stars), Seedance Prompt En (dexhunter/seedance2-skill, 4.2k stars) and Seedance Japanese Prompt Examples (Emily2040/seedance-2.0, 7.5k 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.