From Mega Brain
Creates or updates OKF concept files from raw input to document tables, metrics, APIs, or concepts in a knowledge base.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mega-brain:ingestThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turns raw input (schema dump, API doc, user description, table definition) into one OKF-formatted `.md` file committed to the knowledge base.
Turns raw input (schema dump, API doc, user description, table definition) into one OKF-formatted .md file committed to the knowledge base.
Look for existing OKF files: any .md with type: frontmatter, or index.md / log.md in the project. If none exist, stop and tell the user to run /mega-brain:init first.
If .mega-brain.json defines dir, save new concepts under that directory. Otherwise, choose a sensible location (docs/, project root, etc.) consistent with existing OKF files.
Check if a concept with the same name already exists. If so, ask whether to update it or create a new one.
One .md file per concept. Only type is required:
---
type: <concept type>
title: <display name>
description: <one sentence, plain language, no jargon>
resource: <URL to the actual resource, if any>
tags: [<tag1>, <tag2>]
timestamp: <ISO 8601 date>
---
<body: exact schema, formula, join patterns, examples, caveats>
| Type | Use for |
|---|---|
BigQuery Table | BQ tables with schema |
BigQuery Dataset | BQ datasets |
Table | Non-BQ database tables |
Metric | KPI or business metric with formula |
API | REST/GraphQL endpoints |
Runbook | Operational procedures |
Concept | Business or domain terminology |
Service | Internal microservices |
Pipeline | ETL or data pipelines |
Types are freeform — add your own.
description: one sentence, plain languageresource URL if there's a live resource (BQ console URL, API endpoint, dashboard)[Name](relative-path.md) — this builds the knowledge graphdocs/tables/<slug>.md or <config-dir>/tables/<slug>.md)index.md: - [Title](path) — descriptionlog.md: <date> — added <title>timestampdescription to one sentence — push additional detail into the bodynpx claudepluginhub guhcostan/claude-mega-brain --plugin mega-brainScans project docs and migrates them into OKF format for Claude's knowledge base. Handles READMEs, schemas, API specs, runbooks, and data models.
Authors, maintains, and consumes OKF knowledge bundles (markdown + YAML frontmatter) for project knowledge like services, APIs, schemas, metrics, and decisions. Use when capturing or updating project knowledge.
Enriches DataHub metadata: adds/updates descriptions, tags, glossary terms, ownership, deprecation, domains, data products, structured properties, and documents.