重构
代码重组与优化
marketplace-liquidity
liqiongyu
"Diagnose and improve marketplace liquidity (match rate/fill rate, time-to-match, reliability) by segment. Produces a Marketplace Liquidity Management Pack: liquidity definition + metric tree, fragmentation map, segment scorecard, supply/demand bottleneck diagnosis, experiment backlog, measurement plan, and operating cadence. Use for Growth teams running two-sided marketplaces."
managing-tech-debt
liqiongyu
"Manage technical debt by producing a Tech Debt Management Pack (debt register, scoring/prioritization, refactor vs rewrite decision memo, incremental paydown plan, migration/rollback plan, metrics, and stakeholder cadence). Use for tech debt, refactoring, legacy modernization, and migrations."
matt-pocock
ajoslin
Routes software work through Matt Pocock planning and execution philosophy. Use when the user mentions Matt Pocock, PRD-first planning, PRD-to-issues decomposition, vertical slices, Ralph loop, behavior-first TDD, interface options, or refactor planning.
testing-strategy
block
Guidelines for writing effective tests in this project
moai-lang-rust
Ven0m0
Rust specialist for async services, safe systems programming, and production tooling with Tokio, Axum, SQLx, and clippy-driven quality checks. Use when building or refactoring Rust code.
orchestrate-subagents
shhac
Activate orchestrator mode for complex multi-task work using subagents. Use when you need to coordinate multiple independent Task subagents to accomplish work while keeping the main context window clean.
beautiful-prose
EricGrill
A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.
refactor
corca-ai
"Multi-mode code and skill review for controlling drift as capability surface grows. Quick scan all plugins, commit-based tidying, contract-driven codebase quick scan, deep-review a single skill, holistic cross-plugin analysis, or docs consistency check. Triggers: \"cwf:refactor\", \"/refactor\", \"tidy\", \"review skill\", \"cleanup code\", \"check docs consistency\""
candid-validate-standards
ron-myers
Validate Technical.md for vague rules, linter overlaps, and effectiveness issues
code-simplifier
ArjenSchwarz
Review and simplify code to reduce complexity and improve maintainability
code-simplify
PaulRBerg
This skill should be used when the user asks to "simplify code", "clean up code", "refactor for clarity", "reduce complexity", "improve readability", "make this easier to maintain", or asks to simplify recently modified code.
fixture-boundary-skill-name-padded-to-sixty-four-characters-long
daishiman
Boundaries
refactor
v1-io
Use when refactoring code for simplicity, removing duplication, or applying KISS/DRY/SOLID/YAGNI. Triggers on "refactor", "clean up code", "apply DRY".
deslop
v1-io
Use when removing AI-generated slop, cleaning up verbose code, or removing unnecessary defensive checks. Triggers on "remove slop", "clean up AI code", "deslop".
performance-profiling
lv416e
"Use when investigating performance issues, before attempting any optimization - four-phase methodology (baseline measurement, bottleneck profiling, complexity analysis, targeted optimization) that ensures data-driven decisions over gut-feel tuning パフォーマンスの問題を調査する際、最適化を試みる前に使用 - 4フェーズ手法（ベースライン測定、ボトルネックプロファイリング、計算量分析、的を絞った最適化）により、直感的なチューニングではなくデータに基づく判断を保証"
decision-framework
majesticlabs-dev
Walk through decisions using a 3-part framework (first-principles, cost/benefit, second-order effects). Use when choosing between options, evaluating trade-offs, or making high-stakes decisions.
first-principles
majesticlabs-dev
Apply first-principles thinking to break down complex problems into fundamental truths and rebuild solutions from the ground up. Use when solving strategic decisions, breaking through blockers, or challenging assumptions. Triggers on first principles, Elon Musk methodology, fundamental truths, strip assumptions, physics of the problem, rebuild from scratch.
code-polish
PaulRBerg
This skill should be used when the user asks to "polish code", "simplify and review", "clean up and review code", "full code polish", "simplify then review", "refactor and review", "simplify and fix", "clean up and fix", or wants a combined simplification and review workflow on recently changed code.
sdlc
booch
Software development lifecycle guidance. This skill should be used when planning development work, conducting code reviews, or establishing development workflows. Use proactively when reviewing code, preparing commits, creating pull requests, refactoring, or discussing development process and best practices. (user)
testing
booch
Testing philosophy and practices. This skill should be used when writing tests, designing test strategies, or reviewing test code. Use proactively when discussing TDD, red-green-refactor, test doubles, mocks, stubs, fakes, RSpec, Jest, pytest, unit tests, integration tests, test coverage, or test-first development. (user)
bdd-practices
ssiumha
Writes behavior specifications in Gherkin format. Use when defining features from user perspective or creating acceptance tests.
tdd-practices
ssiumha
Applies TDD workflow to development. Use when writing tests before code, implementing features test-first, fixing bugs via failing test, or refactoring with test coverage. Detects AI anti-patterns.
prompt-optimizer
Aznatkoiny
Optimize prompts for Claude 4.x models using Anthropic's official best practices. Use when users want to improve, refine, or create effective prompts for Claude. Triggers include requests to optimize prompts, make prompts more effective, fix underperforming prompts, create system prompts, improve instruction following, reduce verbosity, control output formatting, or enhance agentic/tool-use behaviors. Also use when users report Claude is being too verbose, not following instructions, not using tools properly, or producing generic outputs.
building-apple-platform-products
kylehughes
Builds, tests, and archives Swift packages and Xcode projects for Apple platforms. Use when running xcodebuild, swift build, or swift test commands, discovering schemes and targets, or selecting simulator destinations for iOS, macOS, tvOS, watchOS, or visionOS.