Can this skill help prevent data races in Go?

Yes, the skill includes specific execution steps for concurrency safety, implementing mutexes, channels, or atomic operations and validating them with Go's race detector.

What documentation does it use to guide implementation?

It primarily reads the project README.md, CONTRIBUTING guides, and the specific GitHub Issue to establish clear acceptance criteria before writing code.

How does this skill handle existing code styles?

It uses grep and Serena MCP to analyze the current project's symbols, naming conventions, and structure to ensure all new code matches the existing implementation style perfectly.

Does it require a specific testing framework?

The skill follows idiomatic Go testing patterns, prioritizing the standard library and table-driven tests as defined in the codegen-test skill guidelines.

Go TDD Feature Generator

Name: Go TDD Feature Generator
Author: nihiyama

bynihiyama

•

API開発

Implements new Go features using Test-Driven Development (TDD) by analyzing requirements and existing code patterns to ensure high-performance, race-free delivery.

The codegen-feature skill automates the end-to-end development of new features within Go projects, specifically optimized for high-concurrency applications like file-based queues. It bridges the gap between GitHub Issues and production code by leveraging TDD principles, semantic code search via Serena MCP, and strict adherence to idiomatic Go patterns. By prioritizing safety and performance—including explicit data race prevention and zero-copy data handling—it allows developers to expand system capabilities while maintaining existing API stability and code consistency.

主な機能

01Semantic code search using Serena MCP for precise, minimal code edits

02Automated performance optimization including slice pre-allocation and zero-copy handling

03Idiomatic Go enforcement through standard library preference and static analysis

04Issue-driven TDD workflow that ensures feature parity with acceptance criteria

05Strict concurrency safety audits to prevent data races in multi-threaded environments

062 GitHub stars

ユースケース

01Implementing feature requests directly from GitHub Issues with automated test-first generation

02Developing new backend logic for high-performance systems like file-based FIFO queues

03Refining Go codebases to handle safe concurrency and high-throughput data processing

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nihiyama/ffq codegen-feature

For use in Claude.ai and ChatGPT

Download Skill