infer-mvp-recommendation-from-code

Infer shipped MVP scope from scan-index.json evidence into Markdown artifacts.

3|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/kapilvirenahuja/garura --skill infer-mvp-recommendation-from-code
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: infer-mvp-recommendation-from-code
Source: https://github.com/kapilvirenahuja/garura/tree/main/core/components/skills/infer-mvp-recommendation-from-code
Command: npx skills add https://github.com/kapilvirenahuja/garura --skill infer-mvp-recommendation-from-code

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reconstructs what your codebase already treats as v1 by inferring primary and deferred capabilities from scan-index.json, so product-keeper can produce an MVP scope proposal grounded in real shipped behavior instead of guesswork.

Core Features & Use Cases

  • MVP reverse-engineering in brownfield codify: infers “what IS the MVP” from release signals, entry points, churn, and README feature enumeration.
  • Evidence-based classification: groups capabilities into primary use cases when churn+entry points/readme support exists, and flags deferred capabilities using thin-code signatures such as empty modules, disabled/commented routes, TODO-heavy files, or v0/experimental path patterns.
  • Guardrailed artifact generation: validates inputs, optionally halts if an authoritative MVP artifact already exists in product LTM, writes the inferred scope to STM, and emits both a decision manifest and a resolution trace for checkpoint review.

Example use case: during /codify, take scan-index.json for a mature repository and produce scope/mvp-recommendation.md that lists shipped MVP primary use cases and clearly separates deferred capabilities that are scaffolded or not truly released.

Quick Start

Ask the product-keeper workflow to run infer-mvp-recommendation-from-code for issue N using scan-index.json, and have it write scope/mvp-recommendation.md under the issue’s STM evidence directory.

Frequently Asked Questions about infer-mvp-recommendation-from-code

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

FAQPage Schema
How do I infer MVP scope from existing codebase evidence?

To infer MVP scope from existing codebase evidence, analyze repository scan-index.json files to reverse-engineer primary and deferred capabilities using release signals, entry points, and README feature enumeration, producing an evidence-grounded markdown artifact.

How do I reverse-engineer MVP features for a brownfield system?

Reverse-engineer MVP features for a brownfield system by scanning release history, code churn, and entry points to distinguish shipped primary use cases from deferred capabilities marked by empty modules or disabled routes.

Can I use churn analysis to identify deferred capabilities in a mature repository?

Yes, you can use churn analysis alongside thin-code signatures like empty modules, commented routes, and TODO-heavy files to classify deferred capabilities that are scaffolded but not truly released in a mature repository.

What is the best way to generate an MVP recommendation from code evidence?

The best way to generate an MVP recommendation from code evidence is to apply deterministic planning during codify workflows, validating inputs and emitting a decision manifest with a resolution trace for checkpoint review.

Does MVP inference work if an authoritative MVP artifact already exists in product LTM?

MVP inference can optionally halt if an authoritative MVP artifact already exists in product LTM, preventing overwrites and ensuring the new scope recommendation respects existing long-term memory constraints.

How do I classify primary use cases using code evidence during codify?

Classify primary use cases during codify by grouping capabilities where churn, entry points, and README enumeration align, while flagging experimental path patterns as deferred to ensure accurate scope definition.