constructing-workflows

Design and edit pipelines_v2 workflows with runner specs and metadata.

4|1|Updated May 20, 2026
One-click install
npx skills add https://github.com/concordance-co/xenon --skill constructing-workflows
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: constructing-workflows
Source: https://github.com/concordance-co/xenon/tree/main/.agents/skills/constructing-workflows
Command: npx skills add https://github.com/concordance-co/xenon --skill constructing-workflows

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Design and editing of pipelines_v2 workflow files in this repo. Covers workflow file structure, runner specs, dataset patterns, row alignment, section metadata, report inputs, and the decision boundary between first-class specs and workspace-local transforms.

Core Features & Use Cases

  • Step-by-step guidance for authoring and reshaping workflows to align with pipelines_v2 conventions
  • Clear rules for selecting runner specs, dataset construction, and metadata sections
  • Practical examples and patterns for maintaining a single source of truth across workflows

Quick Start

Inspect an existing workflow under workflows/ or workspaces/ and adapt it using the recommended first-class specs and workspace-local transforms.

Frequently Asked Questions about constructing-workflows

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

FAQPage Schema
How do I design pipelines_v2 workflows with proper runner specs and dataset patterns?

To design pipelines_v2 workflows, you must enforce structure by specifying explicit runner specs, defining dataset construction patterns, and maintaining a single source of truth for workflow sources to ensure proper row alignment.

What is the boundary between first-class specs and workspace-local transforms in pipelines_v2?

The boundary between first-class specs and workspace-local transforms separates globally enforced workflow configurations from localized data transformations, ensuring safe Modal mounting practices and consistent metadata sections across the repository.

How do I maintain a single source of truth when editing pipeline workflows?

Maintain a single source of truth for pipeline workflows by adapting existing files under the workflows/ or workspaces/ directories, using recommended first-class specs and workspace-local transforms to align with pipelines_v2 conventions.

Does pipelines_v2 workflow construction require explicit runner specs for Modal mounting?

Yes, pipelines_v2 workflow construction requires explicit runner specs to enforce structure and ensure safe Modal mounting practices, preventing configuration drift between workflow planning and dataset execution.

What are the limitations when reshaping pipelines_v2 workflow file structure?

Reshaping pipelines_v2 workflow files is constrained by strict rules for section metadata and report inputs, requiring careful alignment of dataset patterns and row structures to avoid breaking existing runner spec configurations.