/file-pipeline

Process inbound lesson files into researched markdown outputs via pipeline.yaml.

Updated May 14, 2026
One-click install
npx skills add https://github.com/bonjohen/claude-local --skill file-pipeline
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: /file-pipeline
Source: https://github.com/bonjohen/claude-local/tree/main/bundle/skills/file-pipeline
Command: npx skills add https://github.com/bonjohen/claude-local --skill file-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Inbox lesson files pile up and require consistent routing, research, validation, and writing without manual bookkeeping.

Core Features & Use Cases

  • Automated inbound routing via a state-machine pipeline: Detects topic ideas, conversation/context pastes, or complete lessons from the inbox and moves items through processing, done, and error folders.
  • Research-grounded lesson generation: Performs WebSearch and WebFetch to fill gaps and generates a lesson using the morelessons schema with required fields like original_source, difficulty, and phase.
  • Operational control for reliability: Supports status reporting, retrying failed files, and scheduling a durable cron to run the pipeline twice daily.

Quick Start

Run the pipeline once by executing the command: python C:/Projects/morelessons/scripts/file_pipeline.py process

Frequently Asked Questions about /file-pipeline

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

FAQPage Schema
How do I automate research and lesson generation from markdown files in an inbox folder?

To automate lesson generation, you can use a file pipeline with a state machine to route inbound markdown files from a drop folder, perform web research to fill gaps, and output completed lessons with frontmatter. It processes topic ideas and context pastes automatically.

What is a state machine file pipeline for processing inbound lesson files?

A state machine file pipeline is an automated routing system that detects inbound lesson files and moves them through processing, done, and error folders. This ensures consistent research, validation, and traceable retries without manual bookkeeping.

How do I schedule automated file processing and research pipelines to run twice daily?

You can schedule automated file processing by configuring a durable cron job within your pipeline.yaml file. This schedules the pipeline to run twice daily, automatically routing and researching inbound lesson files without manual intervention.

Does the lesson generation pipeline require a specific folder structure and configuration file?

Yes, the pipeline requires a pipeline.yaml configuration file and an EXTERNAL_LESSONS_PATH folder structure. It uses this setup to route files through processing, done, and error directories and generates outputs in data/lessons/ using the morelessons schema.

How do I retry failed lesson files that get stuck during the research and validation workflow?

Failed lesson files are automatically moved to an error folder for traceable retries. You can rerun the pipeline process command to reattempt research and validation on these files, ensuring no inbound lessons are lost during processing.

What schema and metadata fields are used when generating researched lesson markdown outputs?

The pipeline generates markdown outputs using the morelessons schema with frontmatter fields like original_source, difficulty, and phase. This ensures completed lessons are properly structured after automated web research and validation.