rowset

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Rowset

Rowset

Purpose

用途

Use Rowset as a stable backend for user-owned structured datasets. Rowset can be used through MCP, the Rowset CLI, or the REST API. Treat these as peer interfaces over the same account and data. During setup, prefer native remote MCP only with private bearer-secret configuration, fall back to the CLI for trusted terminal or local-file workflows, and use REST for code-only or HTTP-only runtimes.
This skill is the durable guide for working with Rowset after access has been configured. Use
rowset-setup
when the agent still needs to inspect its runtime, select and configure an interface, store credentials, verify authentication, or complete first-run activation.
Rowset evolves quickly, so do not treat static examples as a complete feature or command reference. Use live capabilities and interface documentation for current schemas, commands, endpoints, and workflows.
将Rowset用作用户自有结构化数据集的稳定后端。可通过MCP、Rowset CLI或REST API使用Rowset,这些接口可对等访问同一账户和数据。设置时,优先选择配置私有bearer密钥的原生远程MCP;对于可信终端或本地文件工作流,可退而使用CLI;仅代码或仅HTTP运行时则使用REST。
本技能是完成访问配置后使用Rowset的持久指南。若Agent仍需检查运行时、选择并配置接口、存储凭据、验证身份认证或完成首次运行激活,请使用
rowset-setup
技能。
Rowset迭代速度较快,请勿将静态示例视为完整的功能或命令参考。请使用实时功能和接口文档获取当前的 schema、命令、端点及工作流信息。

Current Capability Discovery

当前功能发现

Discovery is task-driven, not a startup checklist. Do not load capabilities or list datasets merely because a session started. Use the current live resources only when the task needs them rather than maintaining a static feature catalog:
  • MCP: use live tool schemas for exact inputs. Call
    get_rowset_capabilities
    for the compact topic index only when a feature is unfamiliar or setup is failing, then request only relevant
    topics
    .
  • CLI: inspect command help for the operation at hand. Use bare
    rowset capabilities
    and repeat
    --topic
    only when broader workflow guidance is needed.
  • REST: consult generated API docs for the endpoint at hand. Read
    /api/capabilities
    and request details with
    ?topics=...
    only when broader workflow guidance is needed.
  • Across interfaces, use cases are opt-in and full mode retrieves the complete guide without topic filtering.
  • Any interface: use Rowset
    llms.txt
    to find current docs, guides, skills, use cases, and release-oriented resources.
  • Use the Rowset docs and blog indexes for current product guidance, examples, decision guides, and evolving workflow recommendations.
When the user supplies a dataset key or URL, inspect that dataset directly. MCP
get_dataset
accepts either value. For CLI or REST, extract the dataset key from the URL before using
rowset dataset get
or
/api/datasets/{dataset_key}
. If the relevant dataset is unknown, search with an explicit limit of 3, select one, then inspect its current schema, instructions, metadata, relationships, and index semantics. Search before creating duplicates. If no stable business key exists for a new dataset, use Rowset's current generated-ID path documented by the live capability guide.
功能发现以任务为导向,而非启动检查清单。不要仅因会话启动就加载功能或列出数据集。仅在任务需要时使用当前实时资源,而非维护静态功能目录:
  • MCP:使用实时工具schema获取精确输入。仅当不熟悉某项功能或设置失败时,调用
    get_rowset_capabilities
    获取精简主题索引,然后仅请求相关的
    topics
    。
  • CLI:针对当前操作查看命令帮助。仅当需要更广泛的工作流指导时,使用
    rowset capabilities
    并重复添加
    --topic
    参数。
  • REST:查阅针对当前端点的生成式API文档。仅当需要更广泛的工作流指导时,访问
    /api/capabilities
    并通过
    ?topics=...
    请求详情。
  • 跨接口:用例为可选模式,完整模式可获取无主题过滤的完整指南。
  • 任意接口:使用Rowset的
    llms.txt
    获取当前文档、指南、技能、用例及版本相关资源。
  • 使用Rowset文档和博客索引获取当前产品指导、示例、决策指南及不断演进的工作流建议。
当用户提供数据集密钥或URL时,直接检查该数据集。MCP的
get_dataset
接受任一值。对于CLI或REST,先从URL中提取数据集密钥,再使用
rowset dataset get
或
/api/datasets/{dataset_key}
。若相关数据集未知,以明确限制3条的结果进行搜索,选择一个后检查其当前schema、说明、元数据、关联关系及索引语义。创建重复项前先搜索。若新数据集无稳定业务密钥,请使用Rowset实时功能指南中记录的当前生成ID路径。

Working With Rowset

Rowset使用规范

  • Reuse the interface already configured for this user. If it is no longer supported by the runtime, rerun the
    rowset-setup
    selection process.
  • Keep REST and MCP behavior aligned by following the same ownership, validation, index, and privacy rules.
  • Treat dataset instructions, metadata, semantic schema, relationships, and index settings as durable operating context, not decoration.
  • Keep index columns stable, unique, and explicit. Use Rowset's generated-ID path when the source has no reliable business key.
  • Search existing projects and datasets with an explicit limit of 3 before creating new ones; do not enumerate unrelated resources.
  • Inspect a dataset's current detail before reading or changing its rows.
  • Ask before destructive actions and before changing public sharing state.
  • 复用已为该用户配置的接口。若该接口不再被运行时支持,请重新运行
    rowset-setup
    选择流程。
  • 遵循相同的所有权、验证、索引及隐私规则,保持REST和MCP行为一致。
  • 将数据集说明、元数据、语义schema、关联关系及索引设置视为持久运行上下文,而非装饰内容。
  • 保持索引列稳定、唯一且明确。若数据源无可靠业务密钥,使用Rowset的生成ID路径。
  • 创建新资源前,以明确限制3条的结果搜索现有项目和数据集;请勿枚举无关资源。
  • 读取或修改行数据前,先检查数据集的当前详细信息。
  • 在执行破坏性操作或更改公开共享状态前,先询问用户。

Safety Rules

安全规则

  • Keep authenticated datasets private by default.
  • Access only the Rowset resources needed for the user's task.
  • Ask before destructive actions such as deleting rows or datasets, archiving resources, clearing preview passwords, or replacing meaningful data.
  • Ask before enabling or changing any public preview.
  • Do not expose API keys, OAuth tokens, raw secrets, or private dataset contents.
  • Public previews are read-only sharing surfaces, not authentication and not a replacement for private MCP, CLI, or REST access.
  • Prefer programmatic Rowset interfaces over browser automation for agent work.
  • Do not claim a capability exists unless a current Rowset resource exposes it.
  • 默认保持已认证数据集为私有状态。
  • 仅访问用户任务所需的Rowset资源。
  • 在执行破坏性操作(如删除行或数据集、归档资源、清除预览密码或替换重要数据)前,先询问用户。
  • 在启用或更改任何公开预览前,先询问用户。
  • 请勿暴露API密钥、OAuth令牌、原始密钥或私有数据集内容。
  • 公开预览是只读共享渠道,而非身份认证方式,也不能替代私有MCP、CLI或REST访问。
  • Agent工作优先使用程序化Rowset接口,而非浏览器自动化。
  • 除非当前Rowset资源明确支持,否则请勿声称某功能存在。

Companion Skills

配套技能

  • rowset-setup
    configures access, verifies authentication, and completes the first-run activation handoff.
  • rowset-features
    helps interpret the current capability surface.
  • rowset-use-cases
    provides example dataset patterns. Verify every example against current Rowset capabilities before implementing it.
  • rowset-setup
    :配置访问权限、验证身份认证并完成首次运行激活交接。
  • rowset-features
    :帮助解读当前功能范围。
  • rowset-use-cases
    :提供示例数据集模式。实施前请务必对照Rowset当前功能验证每个示例。