# Weighted Data Pipeline

> ---

- Skill: `jinze-lee/weighted-data-pipeline` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add jinze-lee/weighted-data-pipeline`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jinze-lee/weighted-data-pipeline/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: Jinze-Lee (https://skillmd.com/u/jinze-lee)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/jinze-lee/weighted-data-pipeline

---

---
name: weighted-data-pipeline
description: Follow the bundled weighted data-processing pipeline. Use this skill only when the user explicitly invokes `$weighted-data-pipeline`. Do not auto-select this skill for general data-processing or weighted-analysis tasks.
---

# Weighted Data Pipeline

## Overview

Use [references/source-note.md](references/source-note.md) as the source of truth for this skill.

Only use this skill when the user explicitly names `$weighted-data-pipeline`.

Do not use this skill based on topic similarity alone.

## Workflow

1. Read [references/source-note.md](references/source-note.md) first.
2. Follow the note's pipeline order, data handoff points, and file-role distinctions closely.
3. Replace stale file paths, script names, and intermediate outputs with current project equivalents instead of copying blindly.
4. Preserve the original pipeline logic while adapting to the present workspace.
5. If the note conflicts with the current user request, follow the current request and explain the adjustment.

## Source

- Bundled original note: `references/source-note.md`
- Installed skill name: `$weighted-data-pipeline`