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-datasetsgit 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-datasets)<a href="https://agentmods.dev/skills/volcengine/ark-cli/arkcli-datasets"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-datasets/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-datasets"><img src="https://agentmods.dev/badge/skills/volcengine/ark-cli/arkcli-datasets.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 | $0.00063 | $0.00946 |
| Opus 5.5 | $0.00025 | $0.00378 |
| Sonnet 5.5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
arkcli-datasets 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 1mo 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.
What it actually says
ArkCLI 数据集
先读取 ../arkcli-shared/SKILL.md，遵循认证、输出、安全、Client Preview 和二次确认规则。
能力范围
- 创建 Dataset 及首个
V1，或为已有 Dataset 创建新版本。 - 从本地
.jsonl文件或同一 TOS bucket 下的对象映射数据。 - 根据基础模型的精调配置解析准确
DatasetSchema并执行服务端校验。 - 查询、更新、删除 Dataset，查询版本，下载版本中的 TOS 对象。
- 为
train finetune create产出稳定的<dataset-id>:<version-id>引用。
只处理精调任务本身时改用 ../arkcli-train-finetune/SKILL.md。不要用 Raw API 模拟已有的 dataset 产品命令。
执行守卫
- 先执行
arkcli auth status；认证失败时按 shared skill 恢复。 - 执行前读取目标叶子命令的
--help，以当前安装版本为准。 --dataset-format只接受LLMSft、LLMPretrain、LLMDPO、LLMRL、EmbeddingSft、ImageGenSft、VideoGenSft；不要发送展示文案或其他后端 SchemaType。--local与--tos-uri互斥。本地输入只接受.jsonl，最多 20 个文件；多个 TOS URI 必须属于同一 bucket。--tos-uri必须能被当前身份列举且至少包含一个.jsonl；不能复用 CLI 上传结果中的ds-ds/*暂存路径，应使用已注册版本的ark/dataset/<dataset-id>/<dataset-version-id>/路径或其他可读数据路径。- 创建和新增版本会先逐个校验输入；
ValidateDataset.StorageRawLocation.Storage不发送AccountID，但随后两种工作流的CreateDatasetVersion.Storage都必须发送当前账号的数值型AccountID。CreateDatasetVersion不发送可选的Name，CLI 也不提供该参数；正式版本号完全以服务端响应中的Version为准。任一步失败都保留已上传对象或已创建 Dataset，不臆造回滚。 dataset version get <dataset-id> <Vn|dsv-*> --preview读取每个对象最多 100 KiB（102400 字节）内容，与控制台 Dataset 预览上限一致；版本 SID 仍可省略 Dataset ID。下载既支持dataset download ... --version ...，也支持dataset version download <dataset-id> <Vn|dsv-*>，且都不覆盖已有文件。- 删除前先展示版本数、存储路径数以及可获取时的对象数和总字节数，再单独确认。
- 创建、版本创建、校验、下载、更新、删除支持叶子级
--dry-run。只读的 list/get 不使用--dry-run；version get --preview是真实只读查询，不是 Client Preview。 - Client Preview 只展示离线计划；它不上传、不校验服务端数据，也不代替删除确认。
Volc 本地上传使用当前 profile 对应区域的 TOS endpoint，并启用 bucket rename。
工作流
- 创建、维护、校验、下载：读取
references/commands.md。 - Dataset 接入精调：完成 Dataset 后读取
../arkcli-train-finetune/references/create.md。 - 维护者评测：读取
references/evals.md。
只加载当前任务需要的 reference。
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.
- 1mo ago First seen · 42 lines · 63 tokens per session scan A 59dcd3658cfa
arkcli-datasets is a skill published in the GitHub repository volcengine/ark-cli (143 stars, last pushed 8d ago), licensed Apache-2.0. It adds 63 tokens to every session and 946 once invoked, about $0.0003 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
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC)…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.