Refactoring
Code restructuring and optimization
agent-orchestration-multi-agent-optimize
by ncdevshiv
"Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability."
code-fix
by ryoshimm
code-review の指摘に基づき、コードのリファクタリング・共通化・改善を実施する。
clean-code-principles
by AJ-comp
Enforce clean code principles when writing or reviewing code. Use when writing new functions, refactoring existing code, or reviewing code for readability and maintainability. Covers guard clauses, modularization, naming conventions, and more.
improve-trading-strategies
by robonet-tech
"Iterative refinement, parameter optimization, and ML enhancement of existing trading strategies. Provides 3 tools: refine_strategy (targeted code changes, $0.50-$3.00), optimize_strategy (parameter tuning, $2-$4), enhance_with_allora (ML integration, $1-$2.50). More cost-effective than regenerating from scratch. Use when you have working strategies that need improvement. Always test improvements with test-trading-strategies before deploying."
refine_plan
by HowardKao-1130
Refine the research plan until readiness criteria are met.
git-worktree-feature-flow
by alessandrobologna
Create a feature branch in a Git worktree, work independently, then merge back and clean up safely.
test-driven-development
by hrdtbs
Guidelines and procedures for Test-Driven Development (TDD). Use this when writing new features, fixing bugs, or refactoring code.
tdd
by pmco23
Apply when asked to enforce TDD, practice test-driven development, write test first, or follow Red-Green-Refactor. Enforces the Iron Law — no production code without a failing test first. Covers the full Red-Green-Refactor cycle, when TDD applies, and valid exceptions.
code-principles
by vnord
General coding principles—explicit over implicit, separation of concerns, purity, composability
aeo-escalation
by ivzc07
Human-AI interface for when to interrupt and involve humans. Presents clear options and records decisions.
jb-bgproc
by bjesuiter
Manage and inspect background processes for agents using the bgproc CLI. Use when asked to start, stop, list, clean, check status, or view logs for bgproc-managed processes, or when a task needs a JSON-outputting process manager.
refactor-pass
by carsten-j
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build to verify behavior.
validate-starter-scripts
by karchtho
validation audit quality check startup initialization integrity
stage-plan
by cxyliuy
Convert vague or high-level requests into a concrete engineering plan with goals, constraints, steps, success criteria, and validation. Stop and wait for human confirmation.
refactor-archeology
by ShotaIuchi
Code history and rationale investigation for refactoring. Apply when researching git blame, commit history, code comments, hidden constraints, and historical design decisions.
iterate-skill
by maxoreric
迭代改进 Skill 的 Skill。当评价不通过或需要优化时触发。触发词：迭代、改进、优化、iterate、improve。
continuous-mode
by iulspop
Continuously steers the codebase toward the VISION.md. Reads the vision, assesses current state, picks the highest-impact next action, builds with TDD, commits, and repeats. Never stops. Use when you want autonomous, vision-driven development.
speed-loop
by toomingos
"Systematically optimizes a data processing flow through iterative speed loops. Use when the user wants to improve performance of a data pipeline, query, or processing endpoint. Invoke with the flow to optimize: /speed-loop path/to/file or /speed-loop describe the flow"
safe-refactor-guard
by Envy-7z
Enforce ultra-safe refactoring rules to prevent architecture changes, over-engineering, or unintended side effects.
context-ios
by ShotaIuchi
iOS development context. Apply when working with .swift files, Xcode project, SwiftUI views, async/await, Combine, MVVM patterns.
mode-awareness
by jamelna-apps
When explicitly switching modes or when mode detection shows low confidence. Provides guidance on optimal approach for each detected mode (debugging, performance, feature, refactor, exploration, infrastructure).
refactor
by mguinada
"TDD-based code simplification that preserves behavior through tests. Use Red-Green-Refactor cycles to simplify code one test-verified change at a time. DISTINCT FROM: General code review or AI rewriting—this skill requires existing tests and only proceeds when tests confirm behavior is preserved. PROACTIVE: Auto-invoke when test-covered code has complexity (functions >50 lines, high cyclomatic complexity, duplication) and user wants to simplify it safely. Trigger phrases: 'clean up code', 'make code simpler', 'reduce complexity', 'refactoring help'. NOT FOR: Adding features or fixing bugs—use /tdd skill instead."
full-output-enforcement
by paulbryantbaker-art
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
interactive-task
by AgustinAlbonico
Aclarar y ejecutar tareas de desarrollo no-bug (agregar, cambiar, refactorizar, configurar, optimizar) con preguntas adaptativas via question (opciones + respuesta libre). Usar cuando el pedido llega incompleto o ambiguo y se necesita definir alcance rapido.