feature-research

Searches existing codebase architecture to plan complex feature implementations.

Updated Jul 31, 2026
One-click install
npx skills add https://github.com/AarnavBaddam/skills --skill feature-research-aarnavbaddam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: feature-research
Source: https://github.com/AarnavBaddam/skills/tree/main/feature-research
Command: npx skills add https://github.com/AarnavBaddam/skills --skill feature-research-aarnavbaddam

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Implementing a complex feature without understanding existing architecture leads to duplicated patterns, inconsistent conventions, and missed integration points across modules and services. ## Core Features & Use Cases - Pattern Discovery: Runs codebase_search with natural language queries to find existing implementations similar to the planned feature. - Integration Mapping: Identifies API boundaries, data models, background jobs, config conventions, and tests to mirror. - Use Case: Before adding a new notification system spanning routes, database tables, and background workers, use this Skill to locate how similar features were built and produce an implementation plan matching repo conventions. ## Quick Start Research the existing codebase for patterns similar to the new billing feature and propose an implementation plan.

Frequently Asked Questions about feature-research

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

FAQPage Schema
How do I research existing code patterns before building a new feature?

Run codebase_search with a natural language description of the feature, asking for similar implementations including endpoints, data models, background tasks, and tests. Then extract reusable patterns and integration points from the results.

How to avoid duplicating code when adding a feature across multiple modules?

Search the codebase for existing implementations of similar features first. Identify the feature's shape (routes, state, DB, jobs, UI), then mirror the conventions and tests already established in the repository.

When should I do architecture research before implementing a feature?

Do it when the feature spans multiple modules or services, when you need existing patterns for similar functionality, or when you must identify API boundaries, data models, and tests. Small single-file changes usually do not require it.

What should a codebase search query include for feature research?

Use a natural language question describing the feature and explicitly request endpoints, data models, background tasks, and tests. A template like 'Find existing implementations similar to <feature>' works well.

What are the limitations of codebase search for feature planning?

Search results depend on how well the query describes the feature and may miss indirectly related code. It identifies patterns and integration points but does not replace reviewing the actual files before finalizing an implementation plan.