cursor-data-engineering-knowledge-capture
Bind a Cursor agent (including Grok Bot cloud sessions) to the data-engineering-knowledge-capture ContentPack.
- License 许可
- MIT
- 最近更新
- 2026-09-13
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- cursor-data-engineering-knowledge-capture
- description
- Bind a Cursor agent (including Grok Bot cloud sessions) to the data-engineering-knowledge-capture ContentPack.
03 SKILL.md 正文
Cursor / data-engineering-knowledge-capture
Follow docs/CURSOR.md and docs/GROK_BOT.md.
- Identity:
grok-bot/data-engineering-knowledge-capture(or the operator-registered actor for this role). - Local Cursor may
/plugin install data-engineering-knowledge-capturefrom the Spillwave marketplace. - Cloud Cursor on a knowledge tree: pack first, write only via pack scripts, isolate with
brain_session.py. - Never document a private remote. Never write raw Markdown into the tree.
04 同仓库更多 Skills
dekc-walk
Walk a data lake/warehouse filesystem or ingest Fabric/Power BI inventory JSON into DEKC.
dekc-session
Open or close an isolated second-brain write session (worktree + PR). Use before writing knowledge when multiple agents share one knowledge remote.
dekc-semantic
Capture semantic models, metrics, dashboards, reports.
dekc-second-brain
Query the DEKC OKF second brain with design intents (reports, land data, metrics, impact). Uses standard concept schemas under schemas/okf-concepts/.
dekc-search
Full-text search over the DEKC knowledge bundle (AND terms, type filters). Use when finding tables, lineage, or metrics by keyword.
dekc-retrieve
Query-time DEKC retrieval. Spawn data-retriever; parent gets a summary card only. Use for Table, Metric, LineagePath, IngestionJob, Transformation, Dashboard, DataProduct, GlossaryTerm, BusinessObject questions.