edge-pipeline-orchestrator

Automate the edge research pipeline from data intake to export.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/MileniumTick/skills --skill edge-pipeline-orchestrator-mileniumtick
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: edge-pipeline-orchestrator
Source: https://github.com/MileniumTick/skills/tree/main/skills/edge-pipeline-orchestrator
Command: npx skills add https://github.com/MileniumTick/skills --skill edge-pipeline-orchestrator-mileniumtick

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Orchestrates the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.

Core Features & Use Cases

  • Automates multi-stage orchestration across auto_detect, hints, concepts, drafts, review, and export stages to produce finalized strategies and artifacts.
  • Supports resume from drafts, dry-run mode, and selective export, enabling safe experimentation and auditability.
  • Integrates with LLM-guided hints and external scripts to form a cohesive, CLI-driven workflow that tracks artifacts like tickets, hints, concepts, drafts, and strategies.

Quick Start

Run the full edge pipeline from data intake to exported strategies with a single command.

Frequently Asked Questions about edge-pipeline-orchestrator

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

FAQPage Schema
How do I automate an end-to-end data pipeline from intake to export?

Yes, you can resume the edge research pipeline directly from drafts. The orchestrator supports resume capabilities to recover from interruptions, enabling safe experimentation and auditability without restarting the entire data intake and detection workflow.

Can I run a dry-run of the edge research pipeline before exporting strategies?

Yes, you can run a dry-run of the edge research pipeline. The orchestrator supports dry-run mode and selective export, enabling safe experimentation and auditability by testing the workflow from detection to draft generation without committing final artifacts.

Does the pipeline orchestrator support LLM-assisted hints integration?

Yes, the pipeline orchestrator supports LLM-assisted hints integration. It coordinates with LLM-guided hints and external scripts to form a cohesive workflow that tracks artifacts like tickets, concepts, drafts, and finalized strategies during the edge research process.

Do I need PyYAML to coordinate CLI-driven stage orchestration?

Yes, PyYAML is required to coordinate CLI-driven stage orchestration. The orchestrator depends on PyYAML to manage configurations for cross-script data passing, error handling, and multi-stage workflow tracking from auto_detect to export.

What is the best way to orchestrate OHLCV data flow through detection and review stages?

The best way to orchestrate OHLCV data flow is using a CLI-driven orchestrator that automates ticket processing through detection, hints, concepts, drafts, and review stages. It handles error handling and output artifact generation across the entire pipeline.