Loading...
Loading...
Found 198 Skills
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing team communication norms, handling plan approvals, or managing team shutdown.
Analyzes and improves LLM prompts and agent instructions for token efficiency, determinism, and clarity. Use when (1) writing a new system prompt, skill, or CLAUDE.md file, (2) reviewing or improving an existing prompt for clarity and efficiency, (3) diagnosing why a prompt produces inconsistent or unexpected results, (4) converting natural language instructions into imperative LLM directives, or (5) evaluating prompt anti-patterns and suggesting fixes. Applies to all LLM platforms (Claude, GPT, Gemini, Llama).
Expert patterns for Godot AutoLoad (singleton) architecture including global state management, scene transitions, signal-based communication, dependency injection, autoload initialization order, and anti-patterns to avoid. Use for game managers, save systems, audio controllers, or cross-scene resources. Trigger keywords: AutoLoad, singleton, GameManager, SceneTransitioner, SaveManager, global_state, autoload_order, signal_bus, dependency_injection.
Core catalog of 8 critical Elixir/Phoenix anti-patterns covering error handling, separation of concerns, Ecto queries, and testing. Trigger: During Elixir code review, refactoring sessions, or when writing Phoenix/Ecto code.
Methodology for debugging non-trivial problems systematically. This skill should be used automatically when investigating bugs, test failures, or unexpected behavior that isn't immediately obvious. Emphasizes hypothesis formation, parallel investigation with subagents, and avoiding common anti-patterns like jumping to conclusions or weakening tests.
Use when clarifying fuzzy boundaries, defining quality criteria, teaching by counterexample, preventing common mistakes, setting design guardrails, disambiguating similar concepts, refining requirements through anti-patterns, creating clear decision criteria, or when user mentions near-miss examples, anti-goals, what not to do, negative examples, counterexamples, or boundary clarification.
WHEN testing React components/hooks/context with React Testing Library; NOT e2e; covers renderHook, providers, forms, and anti-patterns.
Writes behavior-focused tests using Testing Trophy model with real dependencies. Use when writing tests, choosing test types, or avoiding anti-patterns like testing mocks.
Stop your AI agent from generating Tailwind CSS v3 code. Rules for v4 syntax, CSS-first config, modern utility patterns, and common anti-patterns.
Chinese Code Review Communication Reference - Script Templates, Priority Labeling (Must Fix/Suggested Change/For Reference Only), Countermeasures for Common Anti-patterns in Domestic Teams. Only invoke when the user explicitly uses /chinese-code-review, do not trigger automatically based on context.
Turborepo monorepo architecture decisions and anti-patterns. Use when: (1) choosing between monorepo vs polyrepo, (2) deciding when to split packages, (3) debugging cache misses, (4) setting package boundaries, (5) avoiding circular dependencies. NOT for CLI syntax (see turbo --help). Focuses on architectural decisions that prevent monorepo sprawl and maintenance nightmares. Triggers: turborepo, monorepo, package boundaries, when to split packages, turbo cache miss, circular dependency, workspace organization, task dependencies.
React patterns, anti-patterns, and performance optimization. Use when writing React components, reviewing React code, or debugging React issues.