sparc-refinement

SPARC Refinement phase specialist for iterative improvement through TDD, code optimization, refactoring, performance tuning, and quality improvement

5 stars

byvamseeachanta

View on GitHub Installation ↓

Best use case

sparc-refinement is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

SPARC Refinement phase specialist for iterative improvement through TDD, code optimization, refactoring, performance tuning, and quality improvement

Teams using sparc-refinement should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/sparc-refinement/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/development/sparc/sparc-refinement/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/sparc-refinement/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How sparc-refinement Compares

Feature / Agent	sparc-refinement	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

SPARC Refinement phase specialist for iterative improvement through TDD, code optimization, refactoring, performance tuning, and quality improvement

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

SKILL.md Source

# Sparc Refinement

## Quick Start

```bash
# Invoke SPARC Refinement/TDD phase

# Or directly in Codex
# "Use SPARC refinement to implement login with TDD approach"
```

## When to Use

- Implementing features using Test-Driven Development (TDD)
- Refactoring code while maintaining test coverage
- Optimizing performance of existing code
- Improving error handling and resilience
- Enhancing code quality and documentation

## Prerequisites

- Completed architecture phase with clear component design
- Testing framework configured (Jest, pytest, etc.)
- Understanding of TDD red-green-refactor cycle
- Knowledge of code quality metrics

## References

- [Test-Driven Development](https://martinfowler.com/bliki/TestDrivenDevelopment.html)
- [Refactoring Guru](https://refactoring.guru/)
- [Jest Documentation](https://jestjs.io/docs/getting-started)

## Version History

- **1.0.0** (2026-01-02): Initial release - converted from agent to skill format

## Sub-Skills

- [Configuration](configuration/SKILL.md)
- [Example 1: Performance Optimization (+2)](example-1-performance-optimization/SKILL.md)
- [Example 4: Complexity Reduction](example-4-complexity-reduction/SKILL.md)
- [Best Practices](best-practices/SKILL.md)

## Sub-Skills

- [Execution Checklist](execution-checklist/SKILL.md)
- [Error Handling](error-handling/SKILL.md)

## Sub-Skills

- [SPARC Refinement Phase (+1)](sparc-refinement-phase/SKILL.md)
- [Red Phase - Write Failing Tests (+2)](red-phase-write-failing-tests/SKILL.md)
- [Metrics & Success Criteria](metrics-success-criteria/SKILL.md)
- [MCP Tools (+2)](mcp-tools/SKILL.md)