design

Generate technical design documents and Jira-ready epics from PRDs.

6|16|Updated Mar 9, 2026
One-click install
npx skills add https://github.com/flightctl/ai-workflows --skill design-flightctl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: design
Source: https://github.com/flightctl/ai-workflows/tree/main/design
Command: npx skills add https://github.com/flightctl/ai-workflows --skill design-flightctl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Teams need a consistent, traceable process for turning a PRD into a technical design and a Jira-ready task breakdown, without losing alignment between requirements, architecture, and implementation planning.

Core Features & Use Cases

  • Design document drafting: Ingest a PRD and produce a structured technical design document with architecture, data model, API changes, risks, and open questions.
  • Decomposition into Jira work: Convert the design into Jira-ready epics and stories, including a coverage matrix that maps PRD requirements to the breakdown.
  • Review and publication workflow: Publish the design as a draft GitHub PR, respond to reviewer comments, and sync the approved decomposition to Jira (with dry-run and explicit approval gates).

Quick Start

Use the design skill to generate a technical design and task breakdown from a Jira Feature issue by running: /ingest EDM-2324, then /draft, then /decompose.

Frequently Asked Questions about design

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

FAQPage Schema
How do I turn a PRD into Jira-ready epics and stories?▼

You turn a PRD into Jira-ready epics and stories by ingesting the requirements, drafting a technical architecture, and decomposing it into a breakdown with a requirements coverage matrix. This ensures traceable alignment from design to implementation planning.

What is requirements traceability in technical design documents?▼

Requirements traceability in technical design documents maps PRD requirements directly to the decomposed Jira epics and stories via a coverage matrix. This prevents losing alignment between the architecture drafted and the implementation tasks generated.

Does the generated technical design publish directly to GitHub as a pull request?▼

Yes, the generated technical design publishes to GitHub as a draft pull request. The workflow includes explicit user approval gates and dry-run publication behavior to safely sync the approved decomposition to Jira.

Can I ingest a Jira feature issue to generate architecture and task decompositions?▼

Yes, you can ingest a Jira feature issue to generate architecture and task decompositions. Running the ingest command on a Jira issue triggers context ingestion, architecture drafting, and breakdown into Jira-ready stories.

What is the best way to handle external research and technical trade-offs during system design?▼

Handling external research and technical trade-offs during system design is managed through a dedicated research phase before architecture drafting. The workflow ingests context, performs research, and resolves trade-offs before decomposing into Jira tasks.