Text To Sfx
sonilo-ai/skills
Generate a sound effect from a text description using Sonilo — a UI chime, a whoosh, an impact, ambience, a stylized cue — when there is no video to match.
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。
$ npx skills add volcengine/ark-cli --skill arkcli-docs -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install volcengine/ark-cli arkcli-docs --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-docs .claude/skills/arkcli-docs && 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-docs" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-docs into .claude/skills/arkcli-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-docs", 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-docsType 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-docs -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install volcengine/ark-cli arkcli-docs --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-docs .agents/skills/arkcli-docs && 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-docs" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-docs into .agents/skills/arkcli-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-docs", 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-docs -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install volcengine/ark-cli arkcli-docs --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-docs .cursor/skills/arkcli-docs && 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-docs" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-docs into .cursor/skills/arkcli-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-docs", 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-docs--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-docs -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install volcengine/ark-cli arkcli-docs --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-docs .gemini/skills/arkcli-docs && 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-docs" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-docs into .gemini/skills/arkcli-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-docs", 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-docsInstalls 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-docs -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-docs .github/skills/arkcli-docs && 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-docs" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-docs into .github/skills/arkcli-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-docs", 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-docs -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-docs --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-docs .opencode/skills/arkcli-docs && 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-docs" agent skill from https://github.com/volcengine/ark-cli/tree/main/skills/arkcli-docs into .opencode/skills/arkcli-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "arkcli-docs", 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-docs检索、读取与总结方舟官方文档。用户给出 ark.volcengine.com 文档 URL 或 /docs/ 路径、要求读链接、官方说明、API 契约或必填字段,询问 CC Switch 等第三方客户端的方舟图形配置流程,以及官方网页读取失败时使用。不用于业务调用、资源操作、CLI 帮助或通用知识。
Arkcli Docs is an agent skill from 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。
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/commands.md`, `references/evals.md` and `references/failure-modes.md`).
It sits in Media & Creative. 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.
6 steps, taken from the step headings 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 Docs loads about 3.3k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 889 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). 889 words, ~3,272 tokens.
.claude/skills/arkcli-docs/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.CRITICAL — 开始前 MUST 先用 Read 工具读取 ../arkcli-shared/SKILL.md,其中包含认证闸门、调用归因前缀与命令选择顺序。
CRITICAL — 执行任何 docs 命令前,MUST 先用 Read 工具读取 references/commands.md;遇到报错 MUST 读取 references/failure-modes.md。
arkcli docs 只做一件事:把方舟官方文档变成可引用的事实来源。它不是通用搜索引擎,也不是 arkcli 自身用法的说明书。
下文 docs ... / resources list 等是命令路径缩写。给用户或工具的命令必须包含 arkcli 可执行文件名,说明文字放在命令外。复用已经选定的 MCP 配置,不用示例 URL 或占位值覆盖;只有已知真实端点且确需显式传递时才带端点参数。
下一步只给当前可执行的命令。 URL、位置等参数尚未返回时,不把后续读取加入命令列表;条件和备选方案用文字说明。MCP 即使返回 total_chunks,也先读取 next_chunk_start 指向的单块,再依据新响应决定下一步。认证失败时,当前步骤转交 arkcli-auth;登录完成后才恢复 Docs。
调用归因示例中的 <agent-id> 必须替换成实际宿主名;未知时用 unknown_agent,不要把未引用的尖括号占位符交给 shell。
明确的官方文档请求、第三方客户端 GUI 中的方舟接入步骤(如 CC Switch 选豆包)或其他 skill 委托的产品知识问题由本 skill 承接;先按下方反唤起清单确认最终目标。不要把 docs 当成不知道该用哪个命令时的兜底入口。
问 CC Switch 里如何选豆包时,优先定位对应套餐的官方 Claude Code「使用 CC Switch」章节,核对 GUI 槽位、专属 Key、Base URL 和 Model Name;不能把通用第三方工具文档的 /api/compatible 当成 Coding Plan 或 Agent Plan 的默认地址。用户未说明套餐时,分别说明已核实的 Coding Plan、Agent Plan 与按量接入条件,再请其选定;当前套餐支持的豆包模型名用对应 arkcli plans model-list --plan <plan> 校准。该控制面查询若因宿主凭证失败,只能给标明来源与套餐的文档示例,不能宣称是当前账号实时可选清单。
按请求选择入口,再执行对应命令:
| 请求 | 首个业务命令 |
|---|---|
| 浏览文档目录,最多 N 条 | docs list --limit N;N 为 1–100,无需关键词 |
| 明确在文档目录中按标题、描述或路径包含关键词筛选,最多 N 条 | docs list --query "<关键词>" --limit N;数量是请求参数,不另取更多后挑选 |
给出 /docs/... 路径或文档 URL | docs get "<原路径或 URL>" --compact;路径直接支持,不补域名 |
| 列公开 API 契约、接口及标识 | docs apis list;api --list 仅列本机注册 Action,不能代替公开目录 |
| 读精确 OpenAPI schema 或必填请求字段 | docs apis list → docs apis spec --id "<返回的 id>" |
| 搜索官方文档中的关键词,或未提供路径的知识检索 | docs search "<关键词或问题>";每页 N 条用 --top-k N |
给定官方文档 URL 就直接读取,包括“读这篇”“总结链接”“查某节”;不先做通用搜索。
WebFetch 失败不代表正文不可用,同一个 URL 可交给 docs get 的 CDN 链路。
面向用户引用正文时,使用同一次正文读取返回的文档站 url,以文档标题为链接文字,并保留返回的章节锚点。source_url 是实际读取的 CDN Markdown 来源,用于核对正文;仅在用户需要原始 Markdown 或版本取证时额外提供并明确标注。CLI 续读仍用 url 与 snapshot,不要把 source_url 传给 docs get。MCP 沿用返回的 url;仅有大纲不构成正文依据。
required、是否可省略、default 是三个不同事实:可选不等于有默认值;只有 schema 的 default 或已读官方正文明确声明时才写默认值,否则写“未声明”。oneOf / anyOf 及按 role 区分的对象必须逐分支表述:一个分支必填不等于所有对象必填,“A 或 B 至少其一”不能写成“A 必填”。用户只需顶层字段时,不扩写未经逐分支核对的嵌套规则。示例、客户端源码和 dry-run 不能代替官方请求 schema。docs list / docs search,核对返回的 items / results;保存到文件时先读回完整 JSON。第一页的 has_more、snapshot 和 next_offset 只能决定下一条命令,不能充当第二页内容。续页未完成就只报告已读页和缺口,不根据目录顺序或记忆补写条目。search 走签名的 OpenTOP Action(控制面,需要登录身份);get / list 读产品 CDN 上已发布的目录与 Markdown。两者的后端、上线节奏、故障域都不一样。arkcli docs list --query "<原查询>" 在已发布目录里本地过滤,确认后再下结论。不要线性翻完全部目录。next_action 就是这条降级指引;搜索链路故障时错误里的 hint 字段同样给出降级路径。照它做,不要改成「换个搜索词再试十次」。InvalidActionOrVersion 后停止 search;没有后端已恢复的新证据,不在目录降级之后再次安排搜索。--query 只在标题、描述、面包屑、路径上做本地子串匹配,不是语义检索。过滤结果为空时,换词或去掉 --query 再看完整目录,然后才能说「当前公开文档未覆盖」。search --top-k N(1–50);目录每页 N 条用 list --limit N(1–100),沿返回顺序展示。关键词和页大小不改变入口选择;明确搜索时先 search,收到失败或零命中后才按规则降级。docs list;MCP 不支持 --query,也不保证搜索和读取独立可用。后端能力表见 references/commands.md。docs get 返回 not_found」是正常状态,不是 bug。snippet 当全文用来回答问题。snippet 是片段,不含前提、限制、完整代码。docs list 找到该主题的当前路径,或用别的搜索结果重试;拿不到正文就明确告诉用户「这篇文档当前读不到」。已发布 Markdown 剥掉了 frontmatter、补齐了 H1,但保留了文档站的自定义排版标签,CLI 不做降级。实测一篇 9 KB 文档里能出现几十个。你会遇到:
<Card>、<Columns>、<ColumnsItem>、<Tabs>、<Tab>、<Note>、<Tip>、<Warning>、<Danger>、<APILink>、<Attachment>、<RenderMd>、<span id="...">,以及尾部带 {target="_self"} 属性块的非标准内联链接。图片是绝对 CDN URL。
纪律:
alt 与普通正文同等重要;不要把 <Card> / <Tab> 标签本身当成代码示例、配置片段或命令。alt,保留需要的围栏代码块,不抄排版标签。--section 和分块边界会退化:自定义标签里的标题不是 Markdown AST 标题,可能触发 section_unavailable;超大 DSL 块也可能被从中间切断。遇到这两种情况,改读全文并顺序拼接 content。本节适用于公共后端。MCP 从一开始就用 arkcli docs get "<返回的 url>" --chunk-start <next_chunk_start> --chunk-count 1 --compact 续读,不传 snapshot,也不声称版本固定。每次只生成下一次读取,拿到新结果后再判断是否继续,不预排后面的块。
snapshot 把「哪个发布版本 + 哪套分块边界」钉死,是续读的唯一正确方式。--chunk-start > 0 时 snapshot 必填。has_more=true 才用返回的 next_chunk_start 续读;已到末尾就说明读完,不猜下一块。arkcli docs list / search 命令中读取 JSON;输出过大才按 references/commands.md 保存并读回完整 JSON、提取 snapshot 和下一位置。续页报错先逐字核对实际入参与原响应;抄错应纠正,不删 snapshot、不把错误定位符造成的 404 归因于 CDN 或 offset。list 翻页必须带同一个 snapshot,同时保留原 --query(如有);snapshot 不保存筛选条件。用 list 返回的 snapshot 去 get,读到的就是列表里那个版本。--section 必须同时带大纲返回的 --snapshot,保证锚点与正文来自同一发布版本。--section "#<返回的 section.id>",使用章节读取返回的新 v2 snapshot 和 next_chunk_start。不能继续使用大纲的整页 snapshot,也不能省略 section 后按整页偏移读取。尚未拿到章节响应时,只安排首块章节读取。snapshot_expired 时从头重取(去掉 --snapshot,--chunk-start 回 0),不要猜 offset、不要拼接不同版本的内容。--section 返回的是 v2 章节 snapshot,绑定到具体章节:不能拿它读另一个章节、另一篇文档,也不能喂给 docs list。换章节就去掉旧 snapshot 从 chunk 0 重开。score 不能设绝对阈值score 是检索后端原始分数透传,没有归一化保证,不同查询之间不可比。total 配 total_scope(当前恒为 candidates):它是有界候选集里的唯一文档数,不是全库命中数。要说「一共有多少篇」只能用 docs list 的 total。has_more=true:带同一个 --snapshot 并把 next_offset 作为 --offset 翻页。不带 snapshot 翻页会重新检索并错位,CLI 会直接拒绝。搜索 snapshot 约 5 分钟过期,过期报 snapshot_expired,从第一页重来,不要拼接不同批次。docs apis list / apis spec 读公开 API schemalist 的 apis[] 是可枚举清单,里面的 id / path 是索引里的真实值。spec 的 content 是那一条 OpenAPI JSON。list 返回的 id 跑 spec --id(全局唯一)。--service 是文件名分组(chat、endpoints),多数分组不唯一;命令拒绝时改用 --id 或索引里的 --api-path。不要自己猜路径。docs apis list --transform 'apis.#.id' 缩小输出,再从返回值选择 --id。完整目录或 schema 被 Agent 截断时,读取工具保存的输出文件核实所需字段,不能用示例里的 ID 或截断预览代替。id、service、operation_id、method、path,使用 references/commands.md 的目录解析示例。总数用 len(apis)、分组数从完整数组计算;不从压缩后的回复估数,不按名字拆分推断 service,不把多个 ID 拼成并不存在的 CRUD 组合。摘要需明确是摘要,展示的 ID 保持完整可复制。apis[] 记录并原样保留,包括 method 与 path。只有所有记录的五列均已交付才称为「完整清单」;较长时用目录解析示例生成 TSV 并给出文件位置,不用缩写、通配符或手写组合重建目录。content 中目标 operation 的 requestBody、对应 schema 的 required 与引用到的定义。只有响应 schema 的预览不足以回答;先读保存的完整输出再解析内层 JSON,没有读到就明确说明证据不足。apis spec 当前不返回文档站地址。需要提供参数文档链接时,按接口名或标题用 docs search / docs list 定位,再用 docs get 核对是同一接口及对应参数页,引用其 url。api_path 是请求路径,不能当文档链接;未找到对应页面时说明缺口,不拼造 URL,也不把仅由 schema 确认的细节归给未核实的正文。messages,不能称 model 也已由正文确认。示例中出现字段不能证明必填。schema 内的 externalDocs.url 只是候选入口;未经同一产品 docs get 核对对应参数页,不把它作为已验证页面额外附给用户。references/commands.md 的 Python 管道示例输出请求结构与必填字段。spec 没有 --output 参数;--transform 只投影外层字段。content 是 JSON 字符串,须 json.loads 后读取,不能因其不是 dict 就停止。保存到文件后也必须读取并输出相关结构;文件大小或外层 keys 不是请求字段证据。search 仍走 OpenTOP,get / list 仍读文档 CDN。不要为了 API 契约去改这两条链路。--api-mcp-url、ARK_DOCS_API_MCP_URL、--docs-mcp-url、ARK_DOCS_MCP_URL、ARK_MCP_URL 任一存在时,apis 改走 MCP,不再读公开目录;MCP 不支持 --id。arkcli-auth;停止业务重试并读取 ../arkcli-auth/SKILL.md。已有登录授权时按 Auth Skill 在同一环境执行两段式 --no-browser;没有授权码时只执行第一阶段并等待,不提前给出带占位授权码的第二阶段命令,完成后恢复原 Docs 请求。不擅自运行 config init,不索要检索后端密钥,不把认证失败说成「文档功能不存在」。--compact 优先,避免正文双份。search。docs list --query "<原查询>";MCP 用普通 docs list。--outline 看结构,再用返回的 id 和 snapshot 走 --section。docs apis list → 公共目录用返回的 id;MCP 用返回的 service 或 api-path。ARKCLI_NO_UPDATE_NOTIFIER=1 ARKCLI_CALLER_TYPE=ai_agent ARKCLI_CALLER_NAME=<agent-id> ARKCLI_SKILL_NAME=arkcli-docs \
arkcli docs search "怎么降低首 token 延迟" --top-k 5
ARKCLI_NO_UPDATE_NOTIFIER=1 ARKCLI_CALLER_TYPE=ai_agent ARKCLI_CALLER_NAME=<agent-id> ARKCLI_SKILL_NAME=arkcli-docs \
arkcli docs get "<search 返回的 url>" --compact --chunk-count 1搜不到或搜索失败时,用目录本地过滤,不要线性翻完全部文档:
ARKCLI_NO_UPDATE_NOTIFIER=1 ARKCLI_CALLER_TYPE=ai_agent ARKCLI_CALLER_NAME=<agent-id> ARKCLI_SKILL_NAME=arkcli-docs \
arkcli docs list --query "首 token 延迟" --limit 20长文档先看大纲再定向取章节,比盲拉正文块便宜:
ARKCLI_NO_UPDATE_NOTIFIER=1 ARKCLI_CALLER_TYPE=ai_agent ARKCLI_CALLER_NAME=<agent-id> ARKCLI_SKILL_NAME=arkcli-docs \
arkcli docs get "<search 返回的 url>" --outlinesearch 返回的 URL 若带 #锚点,默认 get 仍读整页。要只读一节,优先用 --outline 返回的 id——搜索锚点在整页命中时是文档 H1 的 slug,不在大纲里,直接喂给 --section 会报 section_not_found:
ARKCLI_NO_UPDATE_NOTIFIER=1 ARKCLI_CALLER_TYPE=ai_agent ARKCLI_CALLER_NAME=<agent-id> ARKCLI_SKILL_NAME=arkcli-docs \
arkcli docs get "<search 返回的 url>" --section "#<headings 返回的 id>" --snapshot "<outline 返回的 snapshot>" --compact --chunk-count 1search:results[] 含 title / url / snippet / score / source,以及可选 breadcrumbs / updated_at;顶层有 query、next_action,以及翻页用的 snapshot、total、total_scope、has_more、next_offset。
list:items[] 含 title / url / description / breadcrumbs;顶层有 total(当前目录可见文档数,不是搜索候选数)、has_more、next_offset、revision、snapshot、next_action。
get:title、breadcrumbs、url(面向用户引用的文档站地址,也是 CLI 文档定位地址)、source_url(正文读取实际使用的 CDN Markdown 来源,用于取证核对)、content、chunks[]、total_chunks、has_more、next_chunk_start、revision、snapshot、next_action,以及用了 --section 时的 section{id,title}。--compact 只输出一份正文在 content,省掉 chunks 和 raw_text,其余引用/续读字段全保留。
get --outline:返回 headings[](每项 id / title / level)和引用、snapshot 元数据;content 为空字符串,省略 chunks,不下载正文。headings[].id 就是发布侧锚点,可直接作为 --section "#<id>"。
breadcrumbs 已经剥掉发布侧的根节点(原始数据首项恒为「根目录」,英文文档也一样),所以 search、list、get 三处的面包屑口径一致,第一项就是真实的一级栏目。
出现下面任一情况,不要用 arkcli docs:
| 用户实际在问 | 正确去向 | 为什么不是 docs |
|---|---|---|
调某个原始 OpenAPI Action、构造 --params | arkcli-api-explorer(arkcli api <Action>) | docs 是文档,不是 Raw API 调用通道 |
| 有哪些模型、模型参数 / 上下文 / 模态 | arkcli-models(models search / models get) | 模型广场是结构化事实源,文档散文不是 |
| 我这个账号 / profile 现在能用哪些模型和 Endpoint | arkcli-resources(resources list) | 可用性是账号态,文档里查不到 |
| 我的调用为什么慢 / 报错 / 失败率高 | arkcli-doctor | 诊断要读实时指标,不是读文档 |
| 把 skill 装到本地 Agent、连接 Agent | arkcli +connect(arkcli-shared) | 安装动作与文档检索无关 |
| 我现在登录的是谁、用的哪个 profile / project / region | arkcli-auth 或 arkcli-profile | 本机状态不在文档里;docs 也不做认证预检 |
| 给我一段能跑的调用代码 | arkcli-code-example(arkcli +code-example) | 代码示例有专门的结构化接口 |
| 某个 arkcli 命令怎么用、有哪些 flag | arkcli <命令> --help 或该命令的 owning skill | CLI 自身用法以 help 为准,文档站可能滞后 |
| 与方舟无关的通用检索(天气、新闻、第三方库文档) | 宿主自带的 Web 工具 | docs 只索引方舟官方文档 |
补充边界:
references/commands.mdreferences/failure-modes.mdreferences/evals.md© 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 3 other files (references) in skills/arkcli-docs of volcengine/ark-cli.
Open the folder on GitHubat commit fb5b7be
Arkcli Docs 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 Docs this skillvolcengine/ark-cli | 140 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Text To Sfxsonilo-ai/skills | 115 | 1 repos | ~1.6k | Automated safety check: Notes | MIT | |
| Video To Musicsonilo-ai/skills | 115 | 1 repos | ~4k | Automated safety check: Notes | MIT | |
| Resolve Audiosamuelgursky/davinci-resolve-mcp | 3.4k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Canvasight OpenNiall-Young/Canvasight | 213 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Premiere Captionsayushozha/AdobePremiereProMCP | 116 | — | ~724 | Automated safety check: Pass | MIT |
sonilo-ai/skills
Generate a sound effect from a text description using Sonilo — a UI chime, a whoosh, an impact, ambience, a stylized cue — when there is no video to match.
sonilo-ai/skills
Score a video with original music using Sonilo — the model watches the cut and matches pacing, motion, and emotion, returning either the audio or a new video with the score muxed in.
samuelgursky/davinci-resolve-mcp
Audio and Fairlight work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.
Niall-Young/Canvasight
Open, reopen, attach, and verify Canvasight's Codex native widget, or explicitly open a browser fallback.
ayushozha/AdobePremiereProMCP
Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro.
guaardvark/guaardvark
Generate full songs with vocals or instrumentals (ACE-Step) and sound effects or ambience (Stable Audio Open) on the user's GPU through Guaardvark's Audio Foundry.
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
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…
Works with
Categories
检索、读取与总结方舟官方文档。用户给出 ark.volcengine.com 文档 URL 或 /docs/ 路径、要求读链接、官方说明、API 契约或必填字段,询问 CC Switch 等第三方客户端的方舟图形配置流程,以及官方网页读取失败时使用。不用于业务调用、资源操作、CLI 帮助或通用知识。. Arkcli Docs is an agent skill from volcengine/ark-cli.
Arkcli Docs fits situations like: media & Creative work in your project.
Run `npx skills add volcengine/ark-cli --skill arkcli-docs -a claude-code`. Or copy the skill folder (skills/arkcli-docs in volcengine/ark-cli) into .claude/skills/arkcli-docs in your project. Claude Code loads it when a task matches its description.
Run `npx skills add volcengine/ark-cli --skill arkcli-docs -a codex`. Or copy the skill folder (skills/arkcli-docs in volcengine/ark-cli) into .agents/skills/arkcli-docs 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-docs -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-docs, .gemini/skills/arkcli-docs, .github/skills/arkcli-docs and .opencode/skills/arkcli-docs in your project.
SKILL.md names no scripts, command-line tools or credentials: Arkcli Docs 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 Docs 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 3.3k tokens (SKILL.md is roughly 13k 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 8.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Arkcli Docs: Text To Sfx (sonilo-ai/skills, 115 stars), Video To Music (sonilo-ai/skills, 115 stars), Resolve Audio (samuelgursky/davinci-resolve-mcp, 3.4k stars) and Canvasight Open (Niall-Young/Canvasight, 213 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.