메뉴
Clean up AI-generated or over-engineered code while preserving behavior. Use when: refactoring noisy code, removing dead code, simplifying abstractions, or making code more idiomatic without changing the public API.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Review AI-generated code changes for unintended consequences, logic errors, UI inconsistencies, and context-specific issues. Use when: code has just been modified, flag potential bugs, verify UI consistency, check implementation correctness against project patterns.
Turn a feature request, issue, or rough spec into a safe implementation plan for an existing codebase. Use when: planning a new feature, scoping impacted files, evaluating trade-offs, or deciding rollout steps before coding.
Turn small ideas into fully-fledged projects through structured discovery, research, and specification. Use when: starting a new project from a rough idea, need to validate feasibility, want to create comprehensive project documentation, exploring feature requirements and design patterns. Conversational, adaptive workflow.
Audit the quality and robustness of an implementation by inventorying the code, understanding how it works, then researching reference examples and community standards online to identify gaps. Use when: checking if a DSP routine is correct, validating a JUCE component follows best practices, reviewing an entire module for structural weaknesses, or verifying a feature is not just "working" but properly implemented.
Initialize or bootstrap a Ralph workspace. Use when starting a repo, preparing the workspace for first use, creating or seeding the `.ralph` folder, filling the first project understanding / journal entries, and documenting setup blockers before substantive work begins.
Find the actual cause of bugs, failures, flaky tests, build errors, and regressions before proposing a fix. Use when: debugging runtime errors, CI failures, broken features, inconsistent behavior, JUCE/CMake build errors, or production incidents.
| name | agent-code-deslop |
| description | Clean up AI-generated or over-engineered code while preserving behavior. Use when: refactoring noisy code, removing dead code, simplifying abstractions, or making code more idiomatic without changing the public API. |
| argument-hint | Describe the code, file, or refactor target to clean up |
| user-invocable | true |
| disable-model-invocation | false |
Prefer small, focused refactorings that preserve behavior, public APIs, and project constraints. Remove unnecessary complexity first, then tighten the code toward idiomatic patterns for the target language.
Do not invent dependencies, config, or environment requirements unless explicitly asked.
/agent-code-deslop -> "Clean up this over-engineered Kotlin service without changing its API"/agent-code-deslop -> "Refactor this Python helper module to remove dead code and make it idiomatic"/agent-code-deslop -> "Simplify this React component tree and remove AI-generated noise"See EXAMPLES.md for detailed before/after examples in Python, JavaScript/TypeScript, and Go, demonstrating de-slopping patterns across languages.