opl-runway-compute-operator

Diagnose OPL Runway compute setup issues and classify execution failures across compute paths.

8|5|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/gaofeng21cn/one-person-lab --skill opl-runway-compute-operator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: opl-runway-compute-operator
Source: https://github.com/gaofeng21cn/one-person-lab/tree/main/plugins/opl-foundation-skills/skills/opl-runway-compute-operator
Command: npx skills add https://github.com/gaofeng21cn/one-person-lab --skill opl-runway-compute-operator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Users working with OPL Runway compute resources often face unclear failure points when setting up local, SSH, SLURM, Modal, or managed endpoint environments, leading to stalled work and incomplete handoff documentation for ops teams.

Core Features & Use Cases

  • Multi-path compute diagnosis: Identifies issues across local shell, SSH hosts, SLURM clusters, Modal jobs, managed endpoints, and Runway-selected providers.
  • Structured failure classification: Categorizes problems into environment, credential, network, provider capacity, submission contract, execution, harvest, or authority gap types to pinpoint root causes quickly.
  • Contract-light handoff briefs: Generates concise, evidence-backed debug notes for ops teams, including observed receipts, recommended next steps, and forbidden unproven claims.
  • Use Case: If a user's SLURM job submission fails with a quota error, this skill classifies the failure as provider_capacity, lists the relevant receipt ID, and provides the exact next Runway command to check quota status.

Quick Start

Use the opl-runway-compute-operator skill to diagnose why your SSH connection to the compute cluster is failing and prepare a handoff brief for your infrastructure team.

Frequently Asked Questions about opl-runway-compute-operator

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

FAQPage Schema
How do I diagnose OPL Runway compute environment setup failures across SSH and SLURM?

Diagnosing OPL Runway compute environment failures involves classifying issues across local shell, SSH hosts, SLURM clusters, Modal jobs, and managed endpoints by analyzing fresh Runway JSON output and provider receipts to pinpoint root causes.

What is the best way to classify SLURM job submission errors in a Runway compute environment?

Classifying SLURM job submission errors involves categorizing them into environment, credential, network, provider capacity, submission contract, execution, harvest, or authority gap types to quickly pinpoint the underlying root cause.

How do I prepare a debug handoff brief for infrastructure ops teams after a compute provider failure?

Preparing a debug handoff brief for infrastructure ops teams involves generating concise, evidence-backed notes including observed provider receipts, recommended next Runway commands, and forbidden unproven claims to ensure clear operator handoffs.

Does this compute diagnosis approach require fresh Runway JSON output to validate readiness status?

Yes, validating compute readiness status requires fresh Runway or Connect JSON output, or provider receipts, enforcing strict authority boundaries that forbid unproven runtime claims.

Why does my SSH connection to the compute cluster fail during Runway provider selection?

SSH connection failures during Runway provider selection typically stem from credential issues, network problems, or authority gaps, which this skill diagnoses by classifying the failure type and listing relevant receipt IDs.

What are the limitations of diagnosing Runway compute paths without provider receipts?

Without provider receipts, diagnosing Runway compute paths cannot validate compute readiness status, as strict authority boundaries require fresh JSON output or receipts to prevent unproven runtime claims.