skills.rest
Ohmnia
OhmniaCOMMUNITY
Explore all skills by this author →
GitHub

feature-research

Searches codebase for existing patterns before implementing new features.

Updated Jul 13, 2026
Search Tags:#architecture#software engineering#implementation planning#code patterns#feature research#codebase search
One-click install
npx skills add https://github.com/Ohmnia/site-build --skill feature-research-ohmnia
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: feature-research
Source: https://github.com/Ohmnia/site-build/tree/main/.opencode/skills/feature-research
Command: npx skills add https://github.com/Ohmnia/site-build --skill feature-research-ohmnia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When implementing a complex feature that spans multiple modules, developers risk duplicating existing patterns or violating established conventions. This Skill guides a structured codebase search to surface reusable patterns, integration points, and tests before writing any code. ## Core Features & Use Cases - Pattern Discovery: Uses codebase_search with natural language queries to find similar existing features, endpoints, data models, and background tasks. - Convention Matching: Identifies config and feature-flag conventions plus tests to mirror, so new code matches the repository's style. - Implementation Planning: Produces a plan grounded in the repo's actual architecture before implementation begins. - Use Case: Before adding a new notification system, run the research workflow to find existing event handlers, queue patterns, and API boundaries, then build a plan that reuses them. ## Quick Start Ask the AI to research the codebase for existing implementations similar to your planned feature before writing any code.

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?▼

Define the feature's shape (routes, state, DB, jobs, UI), then run a codebase_search with a natural language query describing similar features. Extract reusable patterns, integration points, and tests, then write an implementation plan that matches the repository.

What should I search for in a codebase before implementing a feature?▼

Search for existing implementations similar to your feature, including endpoints, data models, background tasks, and tests. Also look for config and feature-flag conventions so the new code follows established patterns.

When should I use codebase research instead of coding directly?▼

Use it when a feature spans multiple modules or services, when similar features may already exist, or when you need to identify API boundaries and data models. For small single-file changes, direct implementation is usually sufficient.

Does codebase search work with natural language queries?▼

Yes, this workflow relies on natural language questions or descriptions passed to codebase_search. A template query like asking for similar implementations with endpoints, data models, and tests produces the most useful results.

What are the limitations of pattern-based feature research?▼

Results depend on the quality of the search tool's indexing and the clarity of your query. It surfaces existing patterns but cannot judge whether those patterns are still best practice, so review findings before reusing them.

Related Skills

Explore More Software Engineering Skills→
ElliotJLTElliotJLT
60

zero-in

Define search scope, expected results, and aliases before codebase exploration.

Community
Basic
jhlee0409jhlee0409
7

afc:test

Plan and write tests for specified code targets using the AAA pattern.

Community
Advanced
adamfilliadamfilli
11

update-claudemd

Review recent git changes and update CLAUDE.md with significant codebase modifications.

Community
Basic
uhyouhyo
88

docs-consistency

Align documentation files with codebase changes to prevent drift.

Community
Intermediate