SpillwaveSolutions/data-engineering-knowledge-capture

최근 기록된 소스 활동: 2026년 9월 12일 19:13

SkillsMP 카탈로그 업데이트: 2026년 11월 12일 12:52

수집된 skills: 24

GitHub 스타: 0
GitHub 포크: 1

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/SpillwaveSolutions/data-engineering-knowledge-capture.

저장소 README

README 원본 파일: README.md

README 원본 보기

README 전체 펼치기

# Data Engineering Knowledge Capture (DEKC) **Git-native second brain for data platforms** — schemas, tables, views, queries, SQL/DAX, lineage, medallion layers (bronze → silver → gold), semantic models, dashboards, reports, streams, jobs, business objects, and glossary terms. DEKC **extends [Project Knowledge Capture (PKC)](https://github.com/SpillwaveSolutions/project-knowledge-capture)** and **depends on [OKF](https://github.com/SpillwaveSolutions/okf-plugin)**. Multi-agent **walk loops** are designed with **[OKF Agent Graph (AGER)](https://github.com/SpillwaveSolutions/okf-agent-graph)** so orchestrators, scouts, judges, and synthesizers reverse-engineer real platforms (Azure Fabric, AWS, GCP) into the same portable graph. | | | |---|---| | **Plugin name** | `data-engineering-knowledge-capture` | | **Repo** | [SpillwaveSolutions/data-engineering-knowledge-capture](https://github.com/SpillwaveSolutions/data-engineering-knowledge-capture) | | **Version** | 0.5.3 | | **License** | MIT | | **Hosts** | Claude Code · Grok Build · Codex · OpenCode · Agent Plugins 1.0 · Grok Bot · LangChain Deep Agents | ## Docs | Doc | Audience | |-----|----------| | **[Retrieval ladder](./docs/designs/retrieval-ladder.md)** | Search/pack: SQLite index → rg → scan. Git stays truth. | | **[Noun-ownership migration](./docs/user_guide/noun-ownership-migration.md)** | Existing brains: `Workflow` → `IngestionJob`; mixed AGER/SAC types | | **[User guide](./docs/user_guide/user-guide.md)** | Install, walk a lake, promote business objects, multi-cloud recipes | | **[Design doc](./docs/designs/current_design_doc.md)** | Agent graph loops (AGER), Azure Fabric / AWS / GCP reverse engineering, streams & jobs | | **[Typed edges](./docs/typed-edges.md)** | Relation vocabulary for lineage and business meaning | | **[PORTS](./PORTS.md)** | Claude / Grok / Codex / OpenCode packaging | | **[Onboarding](./docs/ONBOARDING.md)** | Grok Bot / any host start | | **[Grok Bot](./docs/GROK_BOT.md)** | Cloud Grok Bot binding | | **[Deep Agents](./docs/LANG_CHAIN_DEEP_AGENTS.md)** | LangChain Deep Agents | | **[Isolation](./docs/ISOLATION.md)** | Worktree + PR write isolation | ## Multi-host | Host | How it loads | |------|----------------| | Claude Code | Marketplace / local plugin (`.claude-plugin`) | | Grok Build | Claude-compatible, zero-config (`.grok-plugin` pins identity) | | Codex | `.codex-plugin` + `hooks/codex-hooks.json` | | OpenCode | Skills + `AGENTS.md` | | Agent Plugins 1.0 | Root `plugin.json` | | Grok Bot | Skills + [docs/GROK_BOT.md](docs/GROK_BOT.md) (not a Claude-style install) | | LangChain Deep Agents | `skills=` / SkillsMiddleware — [docs/LANG_CHAIN_DEEP_AGENTS.md](docs/LANG_CHAIN_DEEP_AGENTS.md) | Write isolation (worktree + PR) is in [docs/ISOLATION.md](docs/ISOLATION.md). Public examples use fictional **lumenfield-detector** and **northstar-console** only. Point `SECOND_BRAIN_ROOT` at a path the human already has. Never hard-code a private remote. ## Why DEKC Data teams lose institutional memory in tribal knowledge: “what does this gold table mean?”, “which Event Hub lands into bronze?”, “which Glue job promotes silver → gold?”, “which DAX measure powers the exec dashboard?” DEKC turns lakehouse / warehouse / stream reality into a **reviewable OKF knowledge graph** that agents can walk, pack, and search — while promoting technical assets into **business objects with glossary definitions**. ## Nouns (this plugin) DEKC owns the **data plane**. Catalog / ContextPack live in okf-plugin. `AgentNode` / `Workflow` live in AGER. `Diagram` / `Wireframe` live in SAC. BusinessObject, Column, DQRule, Dashboard, DataCatalog, DataContract, DataDomain, DataLake, DataMart, DataProduct, Dataset, DaxArtifact, DesignPattern, GlossaryTerm, IngestionJob, Layer, LineagePath, Metric, Query, Report, Schema, SemanticModel, SourceSystem, SqlArtifact, StorageLocation, Stream, Table, Transformation, View. | Group | Nouns | |-------|-------| | Assets | Dataset, Table, View, Column, Schema, Query, SqlArtifact, DaxArtifact | | Platform | SourceSystem, DataLake, DataMart, DataCatalog, DataDomain, DataProduct, StorageLocation, Stream, Layer | | Movement | IngestionJob, Transformation, LineagePath, DataContract, DQRule | | Semantic | SemanticModel, Metric, Report, Dashboard, BusinessObject, GlossaryTerm | | Other | DesignPattern | `Dashboard`, `DataLake`, and `GlossaryTerm` also exist in SAC with architecture/runtime meaning. Orchestration graphs (`Workflow`) and walk-loop agents (`AgentNode`) belong to AGER — DEKC records jobs as `IngestionJob` / `Transformation`. Standard concept schemas: [`schemas/okf-concepts/`](./schemas/okf-concepts/). Registry: [`schemas/README.md`](./schemas/README.md). ## Second brain (core goal) DEKC is a **schema-typed OKF second brain** for data engineering work. Capture platform truth once; reuse it when you: | Intent | Command | |--------|---------| | **Design a report** | `python3 scripts/dekc_brain.py "executive revenue" --intent design-report` | | **Land new data** | `python3 scripts/dekc_brain.py "orders stream" --intent land-data` | | **Design a metric** | `python3 scripts/dekc_brain.py "GMV" --intent design-metric` | | **Impact analysis** | `python3 scripts/dekc_brain.py "gold order_daily" --intent impact` | Standard concept schemas: [`schemas/okf-concepts/`](./schemas/okf-concepts/) (Table, SourceSystem, Metric, Dashboard, BusinessObject, …). Registry: [`schemas/README.md`](./schemas/README.md). ```bash python3 scripts/dekc_schemas.py list python3 scripts/dekc_schemas.py validate --bundle sample-knowledge python3 scripts/dekc_index.py status --bundle sample-knowledge python3 scripts/dekc_index.py refresh --bundle sample-knowledge # self-heals; search/pack also refresh ``` ## Diagrams, wireframes & platform concepts Capture **Mermaid** and **PlantUML** listings inside OKF Markdown for: - Report/dashboard **wireframes** (PlantUML salt) - **Architecture**, **component**, **activity**, **state**, **class**, **ERD**, **sequence** diagrams (jobs, lakes, models) ```bash python3 scripts/dekc_diagram.py wireframe --name "Exec UI" --subject /dashboards/executive-revenue.md python3 scripts/dekc_diagram.py job-pack --workflow /workflows/daily-medallion-orders.md python3 scripts/dekc_diagram.py capture --name "Orders ERD" --kind erd --language mermaid --subject /tables/gold-order-daily.md ``` First-class platform types: **DataLake**, **DataMart**, **DataCatalog**, **DataDomain**, **DataProduct**, **Stream**, **StorageLocation**, **DQRule**, **IngestionJob**. ```bash python3 scripts/dekc_platform.py lake --name "Retail Lake" --platform fabric-onelake python3 scripts/dekc_platform.py catalog --name "Workspace Catalog" --engine unity python3 scripts/dekc_platform.py dq-rule --name freshness --target gold-order-daily --rule-type freshness python3 scripts/dekc_platform.py ingestion --name orders-stream-landing --mode streaming \ --streams orders-events --lands-as bronze-orders-raw python3 scripts/dekc_diagram.py ingestion-pack --job /ingestion/orders-stream-landing.md ``` See [docs/diagrams.md](./docs/diagrams.md). ## Ecosystem ```text okf-plugin (okf-graph-eng) portable OKF graph ops (validate, pack, impact) ▲ │ depends on okf-agent-graph (AGER) multi-agent loop schema (orchestrator/worker/judge, ▲ LoopPolicy, ScratchPad, tools, triggers) │ agent loops modeled with project-knowledge-capture (PKC) meetings, decisions, features ▲ │ extends data-engineering-knowledge-capture data assets, lineage, streams/jobs, glossary (this repo) ``` | System | Role | Repository | |--------|------|------------| | **OKF** | Graph format + impact / query / validate | [okf-plugin](https://github.com/SpillwaveSolutions/okf-plugin) | | **AGER** | Multi-agent loop / harness graph as OKF | [okf-agent-graph](https://github.com/SpillwaveSolutions/okf-agent-graph) | | **PKC** | Meetings, experiments, decisions, features | [project-knowledge-capture](https://github.com/SpillwaveSolutions/project-knowledge-capture) | | **DEKC** | Data assets, lineage, streams/jobs, semantic layer | this repo | ## What gets captured | Catalog | Examples | |---------|----------| | **Sources** | Fabric Lakehouse, S3 data lake, GCS bucket, API landing | | **Layers** | Bronze / silver / gold (medallion) | | **Schemas · tables · views · columns** | Physical + logical structure | | **Queries · SQL · DAX** | Models, measures, notebooks | | **Transformations · workflows · jobs** | dbt, Airflow, Glue, Data Factory, Dataform, Composer | | **Streams** | Event Hub, Kinesis, Pub/Sub, Kafka → landing tables | | **Lineage** | Multi-hop feeds / promotes_to paths | | **Semantic · metrics · dashboards · reports** | BI consumption surface | | **Business objects · glossary** | Human meaning of technical assets | | **Agents** | Walk receipts (AGER runs materialized as knowledge) | ## Install ### Claude Code ```bash # Graph + agent-loop substrate claude plugin marketplace add SpillwaveSolutions/okf-plugin claude plugin install okf-graph-eng@okf-plugin-marketplace claude plugin marketplace add SpillwaveSolutions/okf-agent-graph claude plugin install okf-agent-graph@okf-agent-graph-marketplace # Project reasoning (optional but recommended) claude plugin marketplace add SpillwaveSolutions/project-knowledge-capture claude plugin install project-knowledge-capture@pkc-plugin-marketplace # DEKC claude plugin marketplace add SpillwaveSolutions/data-engineering-knowledge-capture claude plugin install data-engineering-knowledge-capture@dekc-plugin-marketplace ``` ### Grok Build Grok Build loads Claude-compatible plugins with **zero extra config**. Optional identity pin: `.grok-plugin/marketplace.json`. ### Codex ```bash codex plugin marketplace add SpillwaveSolutions/data-engineering-knowledge-capture # /plugins → install data-engineering-knowledge-capture ``` ### OpenCode Skills + `AGENTS.md` policy; registration in `.opencode/plugin/dekc.json`. See [PORTS.md](./PORTS.md). ## Quick start ```bash # Scaffold knowledge/ python3 scripts/dekc_common.py init-bundle --repo . --bundle knowledge # Breadth-first RE plan (pause before specialist fan-out) python3 scripts/dekc_orchestrate.py --repo . --system "Retail Lake" \ --scan-root path/to/lake --plan-only # Walk a lake / SQL / job root (filesystem reverse engineer) python3 scripts/dekc_walk.py path/to/lake --repo . --bundle knowledge # or: --from-plan knowledge/.dekc/re-plan.json --area lake # Materialize lineage + promote gold → business objects python3 scripts/dekc_lineage.py --repo . --bundle knowledge materialize python3 scripts/dekc_business.py --repo . --bundle knowledge promote-layer --layer gold # Index second brain + health (search/pack refresh the index themselves) python3 scripts/dekc_index.py status --repo . --bundle knowledge python3 scripts/dekc_doctor.py --repo . --bundle knowledge python3 scripts/dekc_search.py "revenue" --repo . --bundle knowledge ``` Slash / skill entry points: `/dekc-init` · `/dekc-plan` · `/dekc-walk` · `/dekc-lineage` · `/dekc-business-object` · `/dekc-glossary` · `/dekc-semantic` · `/dekc-retrieve` · `/dekc-context` · `/dekc-search` · `/dekc-index` · `/dekc-doctor` ## Agent loop (AGER-shaped): producers + adversarial judges **Orchestrators:** `data-lake-walker` (default) · `reverse-engineering-orchestrator` (Fabric/AWS/GCP). **Query-time:** `data-retriever` (`/dekc-retrieve`) — search + pack stay in the sub-agent; the parent gets a summary card only. Not an RE worker. Producer workers fan out, then **adversarial skeptics grade reverse engineering with rubrics** before index/pack. Lead judge: **re-adversary-judge** (threshold **0.75**). Fail → re-plan or **retract** unproven claims — never invent edges to pass. ```text Trigger → Orchestrator (LoopPolicy: goal · max_turns · no_progress) │ Plan (dekc_plan.py) → ranked task list │ FanOut producers (only areas the plan listed) ├─ schema-scout · lineage-tracer · stream-job-scout ├─ report-cataloger · semantic-mapper ├─ airflow/glue/fabric/dbt/duckdb/notebook/dq scouts (signal-gated) │ FanOut adversaries (rubrics) — unchanged ├─ lineage-skeptic · business-skeptic ├─ stream-job-skeptic · coverage-skeptic · layer-auditor ▼ re-adversary-judge → reverse-engineering-rubric.md │ pass? ──no──► revise / retract ▼ yes index + pack (Synthesizer) + judgment receipt ``` | Rubric | Path | Threshold | |--------|------|-----------| | Reverse engineering (aggregate) | [evaluation/reverse-engineering-rubric.md](./evaluation/reverse-engineering-rubric.md) | 0.75 | | Lineage integrity | [evaluation/lineage-integrity-rubric.md](./evaluation/lineage-integrity-rubric.md) | 0.80 | | Business fidelity | [evaluation/business-fidelity-rubric.md](./evaluation/business-fidelity-rubric.md) | 0.72 | | Stream & job landing | [evaluation/stream-job-landing-rubric.md](./evaluation/stream-job-landing-rubric.md) | 0.70 | Automated baseline: `python3 scripts/dekc_grade.py --bundle knowledge` (skill `/dekc-grade`). Full cloud RE playbooks: [design doc](./docs/designs/current_design_doc.md). ## Sample knowledge [`sample-knowledge/`](./sample-knowledge/) — retail commerce medallion: **bronze.orders_raw → silver.orders → gold.order_daily** + LTV view, DAX measure, semantic model, executive dashboard, business objects, glossary (GMV). ```bash python3 tests/test_dekc.py python3 scripts/dekc_validate.py --bundle sample-knowledge python3 scripts/dekc_doctor.py --bundle sample-knowledge ``` ## Second-brain index Git + Markdown is the source of truth. Search and pack use a disposable ladder (SQLite FTS5 index → ripgrep → full scan). Deleting the accelerators is always valid recovery. See [retrieval ladder](./docs/designs/retrieval-ladder.md). > **Do not commit the index.** Add this to your `.gitignore` (a copy ships at > `templates/gitignore-fragment`): > > ```gitignore > **/.index/ > **/.dekc/index.sqlite > **/.dekc/index.sqlite-journal > **/.dekc/index.sqlite-wal > **/.dekc/index.sqlite-shm > ``` > > Do not ignore the whole `.dekc/` directory — repo-level config lives there. > `**/.index/` still ignores the old JSON inverted index from 0.4.x so it > cannot be re-committed. `dekc_index.py` writes: ```text <bundle>/.dekc/index.sqlite # incremental, mtime+size self-heal ``` ```bash python3 scripts/dekc_index.py status --bundle knowledge python3 scripts/dekc_index.py refresh --bundle knowledge python3 scripts/dekc_index.py drop --bundle knowledge ``` Search, pack, and doctor refresh the index themselves. `build` is an alias for `refresh --force`. Ranking stays in Python so scores match a full scan unless you pass `--engine fts`. `DEKC_NO_INDEX=1` / `--no-index` fall through to rg then scan. Missing `rg` is not an error. ## Config See [`.dekc/config.example.yml`](./.dekc/config.example.yml). ## License MIT — see [LICENSE](./LICENSE).

저장소 README를 불러오는 중…

이 저장소의 skills

소프트웨어 개발자 데이터 과학자 소프트웨어 품질 보증 분석가·테스터 기타 컴퓨터 관련 직업

직업 카테고리 4개 · 67% 분류됨

skill

직업 분류

설명

업데이트

data-engineering-knowledge-capture-deep-agents

미분류

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

원문 언어: 영어

2026-09-12

grok-bot-data-engineering-knowledge-capture

미분류

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

원문 언어: 영어

2026-09-12

dekc-plan

미분류

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.

원문 언어: 영어

2026-09-12

dekc-walk

미분류

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

원문 언어: 영어

2026-09-12

dekc-context

미분류

Build progressive-disclosure context packs for a data concept.

원문 언어: 영어

2026-09-12

dekc-retrieve

미분류

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.

원문 언어: 영어

2026-09-12

dekc-search

미분류

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

원문 언어: 영어

2026-09-12

dekc-second-brain

미분류

Query the DEKC OKF second brain with design intents (reports, land data, metrics, impact). Uses standard concept schemas under schemas/okf-concepts/.

원문 언어: 영어

2026-09-12

dekc-doctor

소프트웨어 품질 보증 분석가·테스터

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

원문 언어: 영어

2026-08-30

dekc-grade

소프트웨어 품질 보증 분석가·테스터

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

원문 언어: 영어

2026-08-30

dekc-index

소프트웨어 개발자

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.

원문 언어: 영어

2026-08-30

dekc-capture-table

데이터 과학자

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

원문 언어: 영어

2026-08-25

dekc-land-data

데이터 과학자

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

원문 언어: 영어

2026-08-25

dekc-platform

데이터 과학자

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

원문 언어: 영어

2026-08-25

cursor-data-engineering-knowledge-capture

기타 컴퓨터 관련 직업

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

원문 언어: 영어

2026-08-18

dekc-session

소프트웨어 개발자

Open or close an isolated second-brain write session (worktree + PR). Use before writing knowledge when multiple agents share one knowledge remote.

원문 언어: 영어

2026-08-16

dekc-diagram

소프트웨어 개발자

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

원문 언어: 영어

2026-08-09