kiro-validate-gap

Analyze gaps between feature requirements and existing codebase to inform implementation strategy.

Updated Jun 23, 2026
One-click install
npx skills add https://github.com/j5ik2o/marp-ai-base --skill kiro-validate-gap-j5ik2o
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kiro-validate-gap
Source: https://github.com/j5ik2o/marp-ai-base/tree/main/.agents/skills/kiro-validate-gap
Command: npx skills add https://github.com/j5ik2o/marp-ai-base --skill kiro-validate-gap-j5ik2o

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Before designing a new feature, teams need to understand what already exists in the codebase and what is missing. This Skill performs a structured gap analysis between approved requirements and the current code, producing multiple implementation options with effort and risk estimates. ## Core Features & Use Cases - Codebase Investigation: Scans existing modules, architecture patterns, conventions, and integration points relevant to the feature. - Multi-Option Analysis: Evaluates extend-existing, create-new, and hybrid implementation approaches with explicit trade-offs. - Effort & Risk Assessment: Labels work as S/M/L/XL effort and High/Medium/Low risk with justifications, and flags items needing further research. - Use Case: After approving requirements for a new payment feature, run the gap analysis to discover existing billing modules, identify missing capabilities, and save a research document that guides the design phase. ## Quick Start Run the gap validation for my feature to analyze how its requirements map against the existing codebase and save the findings to research.md.

Frequently Asked Questions about kiro-validate-gap

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

FAQPage Schema
How do I analyze gaps between requirements and an existing codebase?

Run the gap analysis after requirements are approved. It reads the requirements and steering documents, scans the codebase for existing patterns and integration points, then produces a requirement-to-asset map with gaps tagged as Missing, Unknown, or Constraint.

What inputs does the gap analysis need before running?

It requires an approved requirements.md file and a spec.json in the feature's spec directory, plus core steering files like product.md, tech.md, and structure.md. If requirements are missing, it stops and asks you to generate them first.

Does gap analysis decide which implementation approach to use?

No. It presents multiple viable options—extend existing components, create new components, or a hybrid—with trade-offs, effort, and risk labels. Final decisions are deferred to the design phase.

Where is the gap analysis output saved?

The analysis is written to research.md inside the feature's spec directory so it survives session boundaries. If the file already exists, new analysis is appended after a horizontal rule rather than overwriting prior research.

When should I skip gap analysis for a feature?

Gap analysis is optional and most valuable for brownfield projects with existing code. For greenfield features with no relevant codebase, you can proceed directly to the design phase since there are few existing patterns to evaluate.