Total 43,459 skills, Code Quality has 2026 skills
Showing 12 of 2026 skills
Pyright fast Python type checker from Microsoft with VS Code integration and strict type checking modes
Skill for defining coding rules and conventions. Ensures consistent code style and specifies coding standards for AI collaboration. Use proactively when starting a new project or when coding standards are needed. Triggers: convention, coding style, naming rules, 컨벤션, コンベンション, 编码风格, convención, estilo de código, reglas de nombrado, convention, style de codage, règles de nommage, Konvention, Coding-Stil, Namensregeln, convenzione, stile di codice, regole di denominazione Do NOT use for: existing projects with established conventions, deployment, or testing.
Static analysis skill for C/C++ codebases. Use when hardening code quality, triaging noisy builds, running clang-tidy, cppcheck, or scan-build, interpreting check categories, suppressing false positives, or integrating static analysis into CI. Activates on queries about clang-tidy checks, cppcheck, scan-build, compile_commands.json, code hardening, or static analysis warnings.
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
Adopt Funkcia in TypeScript codebases using Option, Result, OptionAsync, ResultAsync, and module utilities such as Brand, SafeJSON, SafeURI, SafeURL, and TaggedError patterns. Use when migrating from null/throw/promise-rejection flows, designing typed error boundaries, or implementing domain-safe parsing and validation.
Use Slopwatch to detect LLM reward hacking in .NET code changes. Run after every code modification to catch disabled tests, suppressed warnings, empty catch blocks, and other shortcuts that mask real problems.
Research-driven code review and validation at multiple levels of abstraction. Two modes: (1) Session review — after making changes, review and verify work using parallel reviewers that research-validate every assumption; (2) Full codebase audit — deep end-to-end evaluation using parallel teams of subagent-spawning reviewers. Use when reviewing changes, verifying work quality, auditing a codebase, validating correctness, checking assumptions, finding defects, reducing complexity. NOT for writing new code, explaining code, or benchmarking.
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.
Linting workflows with neostandard and ESLint v9 flat config
L3 Worker. Builds module dependency graph, detects transitive cycles (DFS), validates boundary rules (forbidden/allowed/required), calculates coupling metrics (Ca/Ce/I, CCD/NCCD). Adaptive architecture detection: custom rules > docs > auto-detect. Supports hybrid architectures.
Expert blueprint for signal-driven architecture using "Signal Up, Call Down" pattern for loose coupling. Covers typed signals, signal chains, one-shot connections, and AutoLoad event buses. Use when implementing event systems OR decoupling nodes. Keywords signal, emit, connect, CONNECT_ONE_SHOT, CONNECT_REFERENCE_COUNTED, event bus, AutoLoad, decoupling.
Manage software complexity through deep modules, information hiding, and strategic programming. Use when the user mentions "module design", "API too complex", "shallow class", "complexity budget", or "strategic vs tactical". Covers deep vs shallow modules, red flags for complexity, and comments as design documentation. For code quality, see clean-code. For boundaries, see clean-architecture.