claudecodex

data-engineering-knowledge-capture

Data Engineering Knowledge Capture. The data-plane second brain (29 nouns). Data jobs are IngestionJob, not AGER Workflow. Fail-closed 1/4-window ContextPack token budget.

3 on GitHubby Rick Hightowerv0.5.3MITupdated 2 days agoproductivity
/

Plugin data-engineering-knowledge-capture from marketplace spillwave-second-brain in SpillwaveSolutions/second-brain-marketplace. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (24)

  • cursor-data-engineering-knowledge-capture

    Bind a Cursor agent (including Grok Bot cloud sessions) to the data-engineering-knowledge-capture ContentPack.

  • data-engineering-knowledge-capture-deep-agents

    Bind data-engineering-knowledge-capture for LangChain Deep Agents / Deep Agents Code.

  • grok-bot-data-engineering-knowledge-capture

    Bind a Grok Bot agent to Data Engineering Knowledge Capture. Isolation, identity, deterministic writes.

  • dekc-business-object

    Promote tables/views to business objects with glossary definitions.

  • dekc-capture-query

    Capture SQL or DAX query artifacts.

  • dekc-capture-table

    Capture a table with columns, layer, schema into DEKC/OKF.

  • dekc-context

    Build progressive-disclosure context packs for a data concept.

  • dekc-design-report

    Use the DEKC second brain to design a new report/dashboard from existing metrics, gold tables, business objects, and glossary.

  • dekc-diagram

    Capture Mermaid or PlantUML diagrams (architecture, component, activity, state, class, ERD, sequence) and PlantUML wireframes for reports/dashboards into the DEKC second brain.

  • dekc-doctor

    Health check: validation, business coverage, orphans, toolchain (rg / FTS5 / sqlite index).

  • dekc-glossary

    Author glossary terms linked to business objects.

  • dekc-grade

    Grade reverse-engineering quality with automated rubric scores and adversarial judge protocol. Use after walks, before claiming RE complete.

  • dekc-index

    Refresh, inspect, or drop the disposable SQLite/FTS5 knowledge index. Use when search/pack is slow, after a large git checkout, or when the user asks about the DEKC index.

  • dekc-init

    Scaffold a DEKC knowledge bundle with medallion catalogs.

  • dekc-land-data

    Use the DEKC second brain to plan landing new stream or batch data into bronze (and beyond) with sources, jobs, contracts, and lineage.

  • dekc-lineage

    Extract and materialize data lineage paths and mermaid diagrams.

  • dekc-plan

    Breadth-first reverse-engineering plan — map scan roots and optional exports, rank focus areas, emit deep-dive checklists. Pause here before spawning specialists. Not query-time retrieve.

  • dekc-platform

    Capture data lakes, data marts, data catalogs, domains, products, streams, storage locations, and data quality rules into the DEKC second brain.

  • 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.

  • dekc-search

    Full-text search over the DEKC knowledge bundle (AND terms, type filters). Use when finding tables, lineage, or metrics by keyword.

  • 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-semantic

    Capture semantic models, metrics, dashboards, reports.

  • 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-walk

    Walk a data lake/warehouse filesystem or ingest Fabric/Power BI inventory JSON into DEKC.

Slash commands (21)

  • /data-engineering-knowledge-capture:dekc-business-object

    Promote tables/views to business objects with glossary definitions.

  • /data-engineering-knowledge-capture:dekc-capture-query

    Capture SQL or DAX query artifacts.

  • /data-engineering-knowledge-capture:dekc-capture-table

    Capture a table with columns, layer, schema into DEKC/OKF.

  • /data-engineering-knowledge-capture:dekc-context

    Build progressive-disclosure context packs for a data concept.

  • /data-engineering-knowledge-capture:dekc-design-report

    Design a report from the DEKC second brain

  • /data-engineering-knowledge-capture:dekc-diagram

    Capture Mermaid/PlantUML diagrams and report wireframes

  • /data-engineering-knowledge-capture:dekc-doctor

    Health check: validation, business coverage, orphans, index.

  • /data-engineering-knowledge-capture:dekc-glossary

    Author glossary terms linked to business objects.

  • /data-engineering-knowledge-capture:dekc-grade

    Grade DEKC reverse-engineering with rubrics and adversarial skeptics

  • /data-engineering-knowledge-capture:dekc-index

    Refresh, inspect, or drop the disposable SQLite/FTS5 knowledge index.

  • /data-engineering-knowledge-capture:dekc-init

    Scaffold a DEKC knowledge bundle with medallion catalogs.

  • /data-engineering-knowledge-capture:dekc-land-data

    Plan landing new data using the DEKC second brain

  • /data-engineering-knowledge-capture:dekc-lineage

    Extract and materialize data lineage paths and mermaid diagrams.

  • /data-engineering-knowledge-capture:dekc-plan

    Breadth-first RE plan. Map scan roots, rank areas, emit checklists. Pause before specialist fan-out.

  • /data-engineering-knowledge-capture:dekc-platform

    Capture lakes, marts, catalogs, streams, storage, DQ rules

  • /data-engineering-knowledge-capture:dekc-retrieve

    Query-time retrieval. Spawn data-retriever; parent keeps a summary card only.

  • /data-engineering-knowledge-capture:dekc-search

    Full-text search over the DEKC knowledge bundle (AND terms, type filters).

  • /data-engineering-knowledge-capture:dekc-second-brain

    Query DEKC second brain with design intent (report, land-data, metric, impact)

  • /data-engineering-knowledge-capture:dekc-semantic

    Capture semantic models, metrics, dashboards, reports.

  • /data-engineering-knowledge-capture:dekc-session

    Open or close an isolated second-brain write session (worktree + PR).

  • /data-engineering-knowledge-capture:dekc-walk

    Walk a data lake/warehouse filesystem and capture tables, SQL, DAX, parquet datasets.

Subagents (25)

  • adf-scout

    Thin Azure Data Factory specialist. Spawn only when the RE plan lists orch-adf.

  • airflow-scout

    Enrich Airflow DAGs after the deterministic walk. Spawn only when the RE plan lists orch-airflow.

  • business-skeptic

    Adversarial DEKC subagent that grades business objects and glossary fidelity. Rejects vacuous definitions and gold tables without promotion. Uses business-fidelity rubric.

  • composer-scout

    Thin Cloud Composer specialist. Spawn only when the RE plan lists orch-composer.

  • coverage-skeptic

    Adversarial DEKC subagent that challenges structural coverage — phantom tables, wrong medallion layers, schemas without children, index staleness. Feeds re-adversary-judge.

  • cron-loader-scout

    Thin cron / K8s CronJob loader specialist. Spawn only when the RE plan lists orch-cron.

  • data-lake-walker

    Primary DEKC Orchestrator for walking data lakes/warehouses. Spawns producer workers, then adversarial skeptics and re-adversary-judge with rubrics before accepting reverse-engineering results. For multi-cloud RE (Fabric/AWS/GCP), prefer reverse-engineering-orchestrator.

  • data-retriever

    Retrieve DEKC data-plane context without contaminating the parent. Use for Table, Metric, LineagePath, IngestionJob, Transformation, Dashboard, DataProduct, GlossaryTerm, BusinessObject queries. Search, score fit, pack, optionally deepen/lineage. Returns a summary card only.

  • dbt-elt-scout

    Enrich dbt projects after the deterministic walk. Spawn only when the RE plan lists elt-dbt.

  • dq-scout

    Capture cheap DQRule markers (GE / Soda / dbt tests). Spawn only when the RE plan lists dq.

  • duckdb-scout

    Capture/enrich DuckDB files and SQL. Spawn only when the RE plan lists duckdb.

  • fabric-pipeline-scout

    Enrich Fabric pipelines/notebooks from export JSON. Spawn only when the RE plan lists orch-fabric.

  • glue-job-scout

    Enrich Glue job scripts after the deterministic walk. Spawn only when the RE plan lists orch-glue.

  • layer-auditor

    DEKC health baseline subagent — bronze/silver/gold coverage, orphans, missing promotions, index freshness, validation. Feeds re-adversary-judge; not a substitute for adversarial skeptics.

  • lineage-skeptic

    Adversarial DEKC subagent (Judge worker) that attacks lineage edges. Demands SQL/job/config evidence; recommends retracting unproven feeds/transforms_to/promotes_to hops. Uses lineage-integrity rubric.

  • lineage-tracer

    DEKC subagent for SQL/DAX/pipeline lineage and medallion promotions (bronze→silver→gold).

  • notebook-scout

    Extract SQL from .ipynb and Fabric notebooks. Spawn only when the RE plan lists notebooks.

  • re-adversary-judge

    Lead adversarial JudgeAgent for DEKC reverse engineering. Aggregates lineage-skeptic, business-skeptic, stream-job-skeptic, and coverage-skeptic under the reverse-engineering rubric; emits pass/fail, hard fails, and revise list for the orchestrator.

  • report-cataloger

    DEKC subagent for dashboards, reports, DAX measures, and BI tool bindings.

  • reverse-engineering-orchestrator

    AGER-style Orchestrator for reverse-engineering Azure Fabric, AWS, or GCP (or generic lakes) into DEKC. Plans fan-out, enforces LoopPolicy budgets, and only accepts work that passes adversarial rubric judges. Use for multi-cloud RE, stream/job landing capture, and graded walks.

  • schema-scout

    DEKC subagent for discovering schemas, tables, columns, and data contracts in a lake/warehouse. Use when inventorying technical structure.

  • semantic-mapper

    DEKC subagent that converts tables/views/queries into business objects with glossary definitions, metrics, and semantic models.

  • stepfunctions-scout

    Thin Step Functions ASL specialist. Spawn only when the RE plan lists orch-stepfunctions.

  • stream-job-scout

    DEKC Worker that captures streams and jobs which land or transform data (Event Hubs/Kinesis/Pub/Sub, pipelines, Glue, Dataflow, Airflow). Parent domain for orchestration + ELT when the RE plan lists those areas.

  • stream-job-skeptic

    Adversarial DEKC subagent that grades stream and job landing capture. Flags missing producers, missing bronze landings, and invented streams on batch-only systems. Uses stream-job-landing rubric.

Hooks (1)

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/scripts/dekc-curate.sh"

View source on GitHub

More from SpillwaveSolutions/second-brain-marketplace

All 27 plugins →

System Architecture Capture. The what-is-running second brain (139 architecture/runtime nouns). Fail-closed 1/4-window ContextPack token budget.

21 skills · 18 commands · 20 agents · hooks

3

Project Knowledge Capture. The why second brain: meetings, decisions, TicketLink / WikiTicket work types. Fail-closed 1/4-window ContextPack token budget.

28 skills · 25 commands · 2 agents · hooks

3

okf-time-series

claudecodex

OKF Time Series (OTS). Chronological spine for agent memory: Session → Hour → Day → Week → Month → Year. Snapshot-first telemetry; install is not capture.

12 skills · 10 commands

3

okf-agent-graph

claudecodex

AGER: Orchestrator / Doer / Judge / Synthesizer loops as OKF graphs. WriteEvent is the write journal, not an AGER noun. Fail-closed 1/4-window ContextPack.

11 skills · 8 commands · 2 agents

3

okf-graph-eng

claudecodex

OKF graph engine. Owns Catalog and ContextPack only. Domain nouns live in PKC / SAC / DEKC / AGER. Fail-closed PostToolUse validate.

10 skills · 7 commands · 1 agent · hooks

3

Research Knowledge Capture (RKC). Layer 0 research second brain: areas, subjects, ResearchQuestion, Claim, Evidence, Finding. Query-time research-retriever returns a summary card only. Fail-closed ContextPack.

9 skills · 7 commands · 2 agents · hooks

3

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain data-engineering-knowledge-capture?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins27 plugins