Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add volcengine/ark-cli --skill arkcli-docsgit clone --depth 1 https://github.com/volcengine/ark-cliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/volcengine/ark-cli/arkcli-docs)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-docs"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-docs"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.06831 |
| Opus 5.5 | $0.00036 | $0.02732 |
| Sonnet 5.5 | $0.00018 | $0.01366 |
| Haiku 4.5 | $0.00009 | $0.00683 |
Grade A, and why
arkcli-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli docs
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。
唤起信号（When To Trigger）
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。
回答前核对
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。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 17d ago Changed · +6 lines · +16 tokens per session ddf179c00841
- 22d ago First seen · 206 lines · 75 tokens per session scan A 7aa2e48160f8
arkcli-docs is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 91 tokens to every session and 6,831 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other skills, from other repositories
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
batch-file-ops
Batch-Dateioperationen (Löschen, Verschieben, Kopieren, Auflisten) mit Glob-Mustern. CLI-Werkzeug für effiziente Dateisystem-Operationen. Ohne Abhängigkeiten.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…