By eliias
Agent skills for code review and refactoring, built on the Canon-Heuristics-Procedure-Artifacts-Gates framework.
Use when reviewing code structure, design smells, error handling, or test quality at module level.
You MUST use this when actively developing code to enforce disciplined hat-switching between adding function and refactoring.
Use when evaluating code clarity, questioning abstractions, or investigating overengineering concerns.
Use when exploring technical decisions, debating architecture, or stress-testing ideas before committing to an approach.
Meta-skill that auto-invokes great-code skills when relevant. Injected at session start.
A plugin marketplace of agent skills for Claude Code, built on a structured framework.
Install from the marketplace:
/plugin marketplace add eliias/skills
/plugin install great-code
Each skill follows the Canon - Heuristics - Procedure - Artifacts - Gates pattern:
See CONTRIBUTING.md for the full template and guidelines.
Skills activate automatically via a session-start hook. When the plugin loads, the using-great-code meta-skill is injected into the session. It checks each user message against skill triggers and invokes the matching skill without requiring an explicit slash command.
You can still invoke skills manually:
/simplicity-review
/clean-code-review
/refactoring
| Skill | Description |
|---|---|
| simplicity-review | Evaluate code clarity, question abstractions, and investigate overengineering concerns |
| clean-code-review | Review code structure, design smells, error handling, and test quality at module level |
| refactoring | Disciplined two-hat development: alternate between adding function and refactoring |
| using-great-code | Meta-skill that auto-invokes other skills when relevant (injected at session start) |
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub eliias/skills --plugin great-codeCode review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.
Codex-powered code review gate. Creates a review checkpoint that triggers Codex CLI review when Claude exits.
Code review plugin with a standalone reviewer agent and two skill strategies: disposable subagents for one-shot reviews and persistent team members for iterative reviews
Comprehensive guide to clean code, refactoring, SOLID principles, code review techniques, and code smell detection.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions