using-kilroy

Ingest English requirements into DOT graphs and validate graph semantics.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/dcgrigsby/nexrad --skill using-kilroy-dcgrigsby
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-kilroy
Source: https://github.com/dcgrigsby/nexrad/tree/main/.agents/skills/using-kilroy
Command: npx skills add https://github.com/dcgrigsby/nexrad --skill using-kilroy-dcgrigsby

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Operate Kilroy Attractor pipelines end-to-end: ingest English requirements into DOT graphs, validate graph semantics, run and resume pipelines with run config files, configure provider backends (cli/api), and debug runs from logs_root artifacts and checkpoints.

Core Features & Use Cases

  • Ingest requirements into DOT graphs and validate semantics.
  • Run and resume pipelines using run.yaml/run.json with checkpoints and logs_root artifacts.
  • Configure llm backends and model/providers and debug runs from logs and checkpoints.

Quick Start

Ingest English requirements into a DOT graph, validate the graph, then start a Kilroy attractor run with a run config file.

Frequently Asked Questions about using-kilroy

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

FAQPage Schema
How do I convert English requirements into a DOT graph for pipeline execution?

You can convert English requirements into a DOT graph by ingesting the text directly into the system, which validates the graph semantics before pipeline execution. This establishes the structure needed for downstream orchestration.

Can I resume an interrupted Kilroy Attractor pipeline run from a checkpoint?

Yes, you can resume an interrupted Kilroy Attractor pipeline run from a checkpoint. The system orchestrates resumption by loading the run config and utilizing logs_root artifacts to restore the previous execution state.

What is a run config file used for in backend pipeline orchestration?

A run config file like run.yaml or run.json is used to configure and execute backend pipelines. It specifies parameters for the run, enables checkpointing, and directs logs_root artifacts for observability and debugging.

Does the pipeline support both CLI and API provider backends for execution?

Yes, the pipeline supports both CLI and API provider backends for execution. You can configure llm backends, model providers, and execution interfaces within your run config to match your environment.

How do I debug a failed pipeline run using logs_root artifacts?

To debug a failed pipeline run using logs_root artifacts, inspect the generated logs and checkpoints saved during execution. These artifacts provide observability into the run state, allowing you to trace failures back to specific graph nodes.