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-api-explorergit 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-api-explorer)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-api-explorer"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-api-explorer/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-api-explorer"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-api-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.02235 |
| Opus 5.5 | $0.00017 | $0.00894 |
| Sonnet 5.5 | $0.00008 | $0.00447 |
| Haiku 4.5 | $0.00004 | $0.00224 |
Grade A, and why
arkcli-api-explorer 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arkcli api（Raw API Explorer）
CRITICAL — 开始前 MUST 先用 Read 工具读取 ../arkcli-shared/SKILL.md，其中包含认证、配置覆盖排查与命令选择顺序
CRITICAL — 只有在现有产品命令和业务 skill 确实不覆盖时，才允许进入本 skill；禁止把 arkcli api 当默认入口。
CRITICAL — 任何 arkcli api ... 调用前，MUST 先用 Read 工具读取 references/arkcli-api.md，禁止盲目猜参数与输出结构。
使用原则
-
unknown action先查本地api --list，使用完整注册名，不凭近似业务名猜 Action；MissingParameter按当前契约里的字段名与大小写补齐，不轮流试Id/ID/KeyID。 -
查询 API Key 时，先读 Auth 的 API Key 查询与交付：list 只定位元数据，授权导出才用真实
Id调apikey.get_raw，不默认回显明文或轮换。 -
安装态未必有仓库源码：优先读同版本 Skill/reference 与已注册目录；能访问源码时再查 req/resp JSON tag。没有确定的契约来源就说明缺口并停止，不能虚构本地
internal/apis文件已被检查。 -
先产品命令：
arkcli <domain> <verb>或arkcli +<shortcut> -
再 skill / reference：确认是否已有稳定入口与正确参数
-
最后才
arkcli api：仅用于低频、专业或高风险的底层 Action 验证与兜底
不要因为某个 Action 存在，就反推出新的顶层 skill 或 cmd/ 命令；只有升级为稳定产品能力时，才考虑补 shortcuts/。
适用场景
- 现有产品命令确实无法覆盖需求（且该需求不值得做成标准命令或
+shortcut） - 需要验证某个已注册 Action 的输入输出契约（例如排障、回归验证、确认 transport 可达）
- 需要确认 registry 中是否已存在某个 Action（用于开发或排查 “注册缺失”）
唤起信号（When To Trigger）
- 用户明确提到：
action/operation/registry/ “已注册 Action” / “契约验证” - 用户给出：
arkcli api ... --params ...并需要你补全/排错 - 用户遇到：
unknown action/ 需要确认某个 Action 是否存在 - 开发场景：在
internal/apis/<domain>/新增 operation 后，要快速验证能否--list与可调用
反唤起信号（When NOT To Trigger）
- 用户要公开 API 契约目录、接口标识、OpenAPI schema 或必填请求字段：转
arkcli-docs的docs apis list/spec。api --list只列二进制本地注册的 Action，不是公开 API 目录，也不提供完整 OpenAPI schema。 - 用户目标是：对话（
+chat）、生成（+gen）、部署（+deploy）、用量（usage）、查模型（models）等已有稳定产品路径 - 用户只是鉴权失败/未登录/环境 profile 混乱（应先走
auth/config，不要把问题导向api） - 用户只是想“找一个命令怎么用”（优先
arkcli <domain> --help+ 对应 skill/reference）
Agent 快速执行顺序
- 先判断用户目标是否已有产品入口：
arkcli <domain> --help，并优先转对应业务 skill - 如果只是认证/配置问题，不要误判为需要
api：- 认证失败先转
../arkcli-auth/SKILL.md - profile/base-url/region 覆盖混乱先转
../arkcli-config/SKILL.md
- 认证失败先转
- 枚举已注册 Action（无参等价于 list）：
arkcli api --listarkcli api
- 定位契约与必填字段（禁止猜 JSON）：
- 查同版本 reference/官方契约；仓库可用时再查
internal/apis/<domain>/对应 req/resp 结构体，安装态没有源码时不得声称已检查 - 同一 Action 因
MissingParameter/InvalidParameter连续失败两次，且错误没有给出确定值时，停止更换相近字段名试错；回到注册 operation、req/resp tag 或官方契约确认。禁止循环枚举Scene/Type/BizType等猜测字段。
- 查同版本 reference/官方契约；仓库可用时再查
- 先用叶子命令的 Client Preview 核对最终 descriptor 和 payload：
arkcli api <registered-action> --params '{...}' --dry-run- Preview 是纯本地行为，不登录、不请求后端、不证明权限、配额或资源存在
- 只读优先；写操作在 Preview 后仍必须二次确认，然后去掉
--dry-run执行：arkcli api <registered-action> --params '{...}'- payload 自身的
"DryRun":true是后端字段；未加 CLI--dry-run时仍会发出真实网络请求
- 输出尽量稳定、减少噪声：
- 优先用全局
--transform '<gjson path>'提取关键字段 - 只有排障需要时才开
--debug（会输出请求/响应调试信息到 stderr）
- 优先用全局
What ships with it
2 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 · +4 lines 781d632bd202
- 22d ago Changed · +1 lines · -14 tokens per session 176c66af91ed
- 29d ago Changed · +1 lines 291370e02667
- 1mo ago First seen · 109 lines · 56 tokens per session scan A 246e8be0ce58
arkcli-api-explorer is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 2,235 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
bun-file-io
Use this when you are working on file operations like reading, writing, scanning, or deleting files. It summarizes the preferred file APIs and patterns used in this repo. It also notes when to use filesystem helpers for directories.
protocolsio-integration
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io…
knowledge-shared-api-and-runtime-schemas
Shared request and response definitions for the server and web app, with runtime checks for incoming data and cleaned JSON schemas for tools. TypeBox is the library used to describe these data shapes.