material-pipeline

Orchestrate daily Medium article selection, translation, excerpt extraction, image compression, and publishing.

4.7k|260|Updated Dec 29, 2021
One-click install
npx skills add https://github.com/beatai-org/beatai --skill material-pipeline
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: material-pipeline
Source: https://github.com/beatai-org/beatai/tree/main/.claude/skills/material-pipeline
Command: npx skills add https://github.com/beatai-org/beatai --skill material-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gray-matter, marked, yaml, cwebp, gif2webp, node, and includes scripts (resource) components.

What problem does it solve?

Material pipeline automates the repetitive workflow of selecting Medium articles, downloading full text, translating them, extracting excerpts, compressing images, and publishing the results—so you can run a reliable daily publishing cadence.

Core Features & Use Cases

  • End-to-end orchestration: coordinates the list → fetch → translate handoff → excerpt extraction → image compression → human review → publish flow into one operational pipeline.
  • Cross-day de-duplication: ensures the same slug isn’t re-processed within a configurable lookback window by maintaining an append-only sub-list/<date>.json.
  • Controlled publication: writes translated outputs to materials/output/<date>/, then uses review.js to select which items to publish and publish.js to land them into configured targets (with optional _meta.json registration).

Quick Start

Tell your AI to run the pipeline end-to-end by saying: 跑一遍今日素材.

Frequently Asked Questions about material-pipeline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate a daily Medium article translation and publishing pipeline?

Cross-day de-duplication prevents the same slug from being re-processed within a configurable lookback window by maintaining an append-only sub-list date JSON file for deterministic tracking.

How does content de-duplication work across recurring daily publishing pipelines?

Cross-day de-duplication prevents the same slug from being re-processed within a configurable lookback window by maintaining an append-only sub-list date JSON file for deterministic tracking.

Can I use cwebp and gif2webp for image compression in a content publishing workflow?

A manual review gate is enforced via review.js to select which translated items get published, ensuring deterministic file-structure handoffs before final publication via publish.js.

What's the best way to set up a manual review gate before publishing translated content?

A manual review gate is enforced via review.js to select which translated items get published, ensuring deterministic file-structure handoffs before final publication via publish.js.

Do I need Node and gray-matter to run a Medium content fetch and metadata sync pipeline?

Yes, Node is required for execution, while gray-matter and yaml handle frontmatter parsing and metadata sync for deterministic file-structure handoffs across pipeline stages.

How do I ensure idempotent operations when downloading and translating Medium articles?

Idempotent operations are guaranteed by enforcing strict path and environment contracts, writing translated outputs to dated materials output directories, and applying cross-day de-duplication.