One-click install
npx skills add https://github.com/kapilvirenahuja/garura --skill garura-prepare
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: garura:prepare
Source: https://github.com/kapilvirenahuja/garura/tree/main/core/components/plays/prepare
Command: npx skills add https://github.com/kapilvirenahuja/garura --skill garura-prepare

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It turns an epic’s locked inputs into implementation-ready, human-approved design artifacts (LLD, verification scenarios, and an execution plan) by fully characterizing code impact and test coverage first.

Core Features & Use Cases

  • Architecture-guided LLD generation: Produces interface-level design (tech.yaml) including API contracts, internal interfaces, frontend/backend specs, data specs, communication channels, and mock strategy—explicitly aligned to the locked architecture output.
  • Test-driven blast radius and baseline characterization: Maps test surface, computes change surface impact, identifies coverage gaps, and specifies baseline tests capturing current behavior before any design is generated.
  • Three-tier verification scenarios + executable task DAG: Creates scenarios.yaml (baseline/new/regression tiers) and plan.yaml (feature slices with depends_on chains and observable exit gates) with strict audience separation.
  • Guardrailed, checkpointed locking: Requires explicit human approval (Tether) at context assembly, blast radius, LLD, and scenario/plan stages; locks artifacts only after validation and resolution of open questions/high risks.

Quick Start

Run the prepare play for your epic so it produces locked tech.yaml, scenarios.yaml, and plan.yaml under {stm_base}/{issue}/context/design/.

Frequently Asked Questions about garura:prepare

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

FAQPage Schema
How do I generate implementation-ready LLD design artifacts from a locked epic?

Implementation-ready LLD design artifacts are generated by mapping test coverage and analyzing blast radius to produce locked tech.yaml, scenarios.yaml, and plan.yaml files. This process requires upstream locked specify and architecture artifacts as read-only inputs.

What is blast radius analysis in intent-driven development?

Blast radius analysis in intent-driven development characterizes code impact by mapping the test surface and computing change surface impact. It identifies coverage gaps and specifies baseline tests capturing current behavior before any design is generated.

How do I plan a task DAG with observable exit gates for feature implementation?

Planning a task DAG with observable exit gates involves generating a plan.yaml that structures feature slices with depends_on chains. This executable plan requires strict human checkpoint approvals before locking the final implementation scenarios.

Do I need upstream locked architecture artifacts to map test coverage and generate verification scenarios?

Upstream locked architecture artifacts are required to map test coverage and generate verification scenarios. This enterprise-grade workflow mandates that upstream specify, design, and architecture artifacts exist and remain read-only throughout the preparation process.

What is the best way to structure three-tier verification scenarios for regression testing?

Structuring three-tier verification scenarios is best achieved by generating a scenarios.yaml file that separates baseline, new, and regression test tiers. This structure ensures strict audience separation and aligns verification with the locked architecture output.