claudecodex

dbt-wiki

Local-only two-layer knowledge base for dbt projects — semantic Q&A over manifest + column lineage.

7 on GitHubby koukov3.3.2MITupdated 6 days ago
/

Plugin dbt-wiki from marketplace monkey-skills in kouko/monkey-skills. Commands read from the repo's manifest — 6 days ago.

What it installs

Skills (9)

  • ingest

    Record dbt tribal knowledge not in manifest/schema.yml (sort_key rationale, dialect gotchas, incident links) into a model's User Notes (survives rescan). Use for 'remember that fct_orders…', 'add note to <model>', '備註 fct_X'. To query, use query.

  • init

    First-time setup: scaffold .dbt-wiki/ from manifest.json + compiled SQL (sqlglot column lineage) + inline comments — pages, index, lineage DAG, CLAUDE.md. Needs dbt parse && compile first. Use for 'init dbt-wiki' or '初始化'. Later updates→rescan.

  • pack

    Package .dbt-wiki/ into a portable, warehouse-agnostic analytics Agent Skill a teammate can use with their own warehouse tool — knowledge + SQL guidance, not an executor. Use for 'package the dbt-wiki knowledge' or 'export for a teammate'.

  • query

    Answer any dbt question from .dbt-wiki/: model structure, column lineage, config, schema.yml, refactor impact, ingested notes — before reading dbt/ files. Use for 'trace column', 'what feeds X', 'rename impact', '依賴什麼'. Setup→init, updates→rescan.

  • redistill

    Re-distill the stale knowledge pages rescan flagged — LLM rewrites entities/metrics/concepts whose derived_from evidence changed, grouped by domain, skipping mature (human-certified) pages. Use for 'redistill', 're-distill stale knowledge', 'knowledge pages are stale', '重蒸餾知識頁'. This is the LLM half

  • rescan

    Evidence-layer-only refresh (advanced, 0 LLM): re-scan .dbt-wiki/ evidence — diff manifest md5, reprocess only changed resources, re-run sqlglot lineage, preserve User Notes, flag stale knowledge pages. Use ONLY when the ask is explicitly the cheap evidence half: 'rescan dbt-wiki', 'evidence only, 0

  • review

    Human certification loop for dbt-wiki pages — lists pages needing review (developing or mature-but-stale), prioritizes by risk, certifies each → mature. Use for 'review pages', 'certify', 'what needs review', '審核'. Query → query.

  • update

    THE maintenance verb for dbt-wiki — one full pass: (optional) ingest new tribal knowledge → rescan evidence → gated redistill of stale knowledge → phantom-column lint gate → review handoff → scorecard. Runs every mechanical step, then hands the human-judgment part to review. Use for 'update dbt-wiki

  • using-dbt-wiki

    Family-entry router for dbt-wiki — the knowledge base distilled from a dbt project (manifest + compiled SQL + column lineage) into .dbt-wiki/. Use when unsure which dbt-wiki skill applies: first-time setup, bringing the wiki up to date, asking a dbt question, or certifying pages. Triggers: 'dbt wiki

View source on GitHub

More from kouko/monkey-skills

All 21 plugins →

obsidian

claudecodex

Obsidian vault workflows (notes/markdown/diagrams/canvas) + LLM wiki layer (defuddle needs CLI).

23 skills · 1 agent

7

gws-toolkit

claudecodex

Google Workspace toolkit on the official gws CLI (drive/docs/sheets/gmail; Claude Code CLI only).

18 skills · 1 command

7

Pipeline copywriting toolkit — 14 skills from intake to audit, grounded in PASONA/Cialdini/FTC.

14 skills · 2 agents

7

Three-layer investing research toolkit — data, analysis, report skills.

15 skills · 1 agent

7

domain-teams

claudecodex

Domain-expert team skills (planning/code/design/research/copywriting) with quality-gate checkpoints.

11 skills · 2 agents

7

four-dx-coach

claudecodex

Multi-scope coach for the 4 Disciplines of Execution — Socratic coach + single-artifact audit modes.

12 skills

7

Similar plugins

ruflo-rvf

claude

RVF format for portable agent memory, session persistence, and cross-platform transfer

2 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

data-agent-kit

claudecodex

This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.

37 skills

anthropics/claude-plugins-official 47,076

Atlan

claude

Atlan data catalog plugin for Claude Code. Search, explore, govern, and manage your data assets through natural language. Powered by the Atlan MCP server with semantic search, lineage traversal, glossary management, data quality rules, and more.

1 skill · 1 MCP server

anthropics/knowledge-work-plugins 35,601

Snowflake SQL, data pipelines (Dynamic Tables, Streams+Tasks), Cortex AI functions, Snowpark Python, and dbt integration. Includes query helper script, reference guides, and troubleshooting.

1 skill

alirezarezvani/claude-skills 29,725

data-agent-kit

claudecodex

This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.

37 skills

google/skills 24,091

dex

claudecodex

Analytics engineering skills for warehouse exploration, dbt and semantic modeling, and schema-drift maintenance. Three skills (explore, transform, maintain) drive a local engine: warehouse reads are read-only and cost-gated, and project edits come back as reviewable diffs. Requires a local shell and uv; first use downloads the pinned engine from PyPI. No hooks, no MCP servers.

3 skills

davepoon/buildwithclaude 3,741

Maintain dbt-wiki?

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 plugins21 plugins