Home / datawithbaraa / claude-code-data-engineering-skills · GitHub

metadata SKILL.md skillA

metadata from datawithbaraa/claude-code-data-engineering-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add datawithbaraa/claude-code-data-engineering-skills/metadata@git:20261029.2e2b6c2

Pins git:20261029.2e2b6c2 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: datawithbaraa/claude-code-data-engineering-skills
Path: skills/metadata/SKILL.md
Versions recorded: 1
Latest version: git:20261029.2e2b6c2, committed Oct 29, 2026
Size: 2,032 bytes
Repository stars: 81
License: MIT

Use when the metadata of a source has to be built or extended, to describe every table and column, the names and types from the data with a script, the descriptions from the documents, never guessed.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Metadata

The job: extend the metadata of a source from its files and its documents. Facts from the data, descriptions from the documents, nothing invented.

Input: the source, its data files, its documents, and one example table written by hand.

## Steps

1. Read the example: one source, one table, the format to follow. Table name, description, then every column with its name, type, key and description.
2. Point at the data of the source: the exports or the landing files, one file per table.
3. Write a Python script that reads every file, every column as text first, and extracts the table names, the column names and the data types. IDs stay strings and keep their leading zeros. The script does this, not the model, so nothing is invented.
4. Take the keys from the profile of the source, never from a guess.
5. Read only the documents the data engineer points at: PDFs, handbooks, data dictionaries.
6. Take every description from the documents. A description must trace to a document.
7. Where the documents say nothing, leave the description empty and list it. Never guess a description.
8. Write every table into the metadata file, in the format of the example.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add datawithbaraa/claude-code-data-engineering-skills/metadata@sha256:c6f119c67db774d2

The line at the top of this page pins the label git:20261029.2e2b6c2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_wg5uyk43iejcndw3.svg)](https://markdownregistry.com/a/art_wg5uyk43iejcndw3)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 29, 2026.

version	committed	commit	size	audit
git:20261029.2e2b6c2 latest	2026-10-29	2e2b6c2	2,032 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2032 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

datawithbaraa/claude-code-data-engineering-skills · 81 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wg5uyk43iejcndw3
GET https://markdownregistry.com/api/v1/resolve?ref=datawithbaraa/claude-code-data-engineering-skills/metadata
GET https://markdownregistry.com/api/v1/blob/c6f119c67db774d24bcf9463dd2912ddd639f2a47a990e2238a44501f2643b3a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from datawithbaraa/claude-code-data-engineering-skills

CLAUDE.md CLAUDE.md file

datawithbaraa/claude-code-data-engineering-skills · CLAUDE.md

git:20261029.a57f353 · audit A · 81 stars

big-review SKILL.md skill

datawithbaraa/claude-code-data-engineering-skills · skills/big-review/SKILL.md · Use once a month, or when the platform feels slow, heavy or cluttered, to review the whole platform from the query logs…