Using Datahub

作者 datahub-projectc6d0ded76eca無授權條款42 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫8 天前更新

This skill provides routing guidance for all DataHub interaction skills. It is injected at session start and helps map user intent to the correct skill. Do not invoke this skill directly — it is loaded automatically.

僅含說明AI & Agents
AI 產生的概覽

將 DataHub 目錄請求路由到正確 DataHub 互動技能的路由指南。

功能
此技能是五個 DataHub 目錄互動技能(Search、Enrich、Lineage、Quality、Setup)的路由指南。它提供將使用者意圖對應到適當技能與命令的路由表,以及針對模糊請求的消歧規則。它也說明了 datahub 命令的 CLI 歸屬慣例。此技能會在 session 開始時自動載入,不應直接呼叫。
適用情境
當請求涉及 DataHub 目錄,且需要判斷應由哪個 DataHub 技能處理時使用。它用於意圖路由,而非直接執行目錄操作。
執行需求
需要其引用的 DataHub 技能集;就 CLI 歸屬指引而言,還需要 datahub CLI。它不隨附指令碼,僅為說明性指示。

Using DataHub Skills

You have access to 5 DataHub catalog interaction skills. Use this guide to route the user's request to the correct skill.


Skill Routing Table

User IntentSkillCommand
Find or discover entities (search, browse, filter, list)Search/datahub-search
Answer a question about the catalog ("who owns X?", "how many X?")Search/datahub-search
Update metadata (descriptions, tags, glossary terms, ownership, deprecation)Enrich/datahub-enrich
Explore lineage (upstream, downstream, impact, root cause, dependencies)Lineage/datahub-lineage
Data quality (assertions, incidents, health checks)Quality/datahub-quality
Notifications (subscribe to assertion failures, incidents)Quality/datahub-quality
Install CLI, authenticate, verify connectionSetup/datahub-setup
Configure default scopes and profilesSetup/datahub-setup

Disambiguation Rules

When the intent is ambiguous, use these rules:

"Tag" requests

  • All tag operations (PII, sensitive, important, reviewed, team-x) → Enrich (general metadata)

"Domain" requests

  • Filter search to a domain → Search (scoped search)
  • Configure default domain → Setup (profile configuration)

"Quality" or "health" requests

  • Failing assertions, active incidents, health status → Quality
  • Create assertions, run quality checks, raise incidents → Quality
  • Subscribe to assertion failures or incidents → Quality
  • Metadata quality/documentation/ownership coverage → Use Search to gather the data and synthesize the answer

Lineage vs. Search

  • "What feeds into X" / "what depends on X" / "impact of changing X" → Lineage
  • "What dashboards use table X" → Lineage (relationship traversal)
  • "Who owns X" / "what is X" → Search (metadata lookup)

Setup vs. other skills

  • "Set up" / "install" / "authenticate" / "verify connection" → Setup
  • "Configure defaults" / "set default platform" / "create profile" → Setup
  • "Check if DataHub is working" → Setup (connectivity verification)

CLI Attribution

When running datahub CLI commands, pass -C skill=<name> on the root command so usage can be attributed:

bash
datahub -C skill=datahub-search search "revenue"datahub -C skill=datahub-enrich graphql --query '...'datahub -C skill=datahub-lineage lineage --urn "..."

Use the skill name from the YAML frontmatter. If -C is not recognized, omit it — the command works the same without it.


Critical Rules

  1. Never guess the skill. If the intent is genuinely ambiguous, ask the user to clarify.
  2. One skill per request unless the user explicitly asks for multiple operations.
  3. Lineage is for lineage only — not for general "what is this entity?" questions (that's Search).
  4. Search handles ad-hoc questions. "Who owns X?" and "what columns does X have?" are Search questions, not Lineage.
  5. Enrich handles all metadata writes — descriptions, tags, glossary terms, ownership, deprecation.
  6. Quality handles data quality — assertions, incidents, health checks, subscriptions.
  7. Setup handles environment and configuration — CLI install, auth, connectivity, default scopes.

來源與署名

來源:datahub-project/datahub-skills位於skills/using-datahub提交c6d0ded

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架