Total 52,636 skills, Code Quality has 2382 skills
Showing 12 of 2382 skills
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.
Analyzes existing codebases to understand structure, patterns, and technical debt
Run a final release checklist before shipping. Verifies no TODOs, no debug code, docs updated, tests passing, dependencies justified, and security reviewed.
HarmonyOS code review skill for auditing ArkTS projects against official Huawei development guidelines and security best practices. Use when reviewing HarmonyOS applications for: (1) Security compliance (hardcoded credentials, encryption, input validation), (2) ArkTS language standards (hilog usage, type safety, magic numbers), (3) Component lifecycle management (resource cleanup, event subscription handling), (4) State management (V1/V2 decorator consistency), (5) Database operations (ResultSet handling, transaction management, encryption), (6) Permission management (official permission patterns), (7) Performance issues (async forEach, resource leaks), (8) API version compatibility, (9) Kit usage best practices. Generates comprehensive markdown reports with prioritized fix recommendations.
Review dependency PRs with structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template. USE FOR: dependency update PRs, Renovate/Dependabot PRs, library upgrade reviews, "review this dependency PR", "should we merge this update". DO NOT USE FOR: feature PRs, application code reviews, dependency automation/bot configuration, or unattended merge without confirmation.
Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
deslop a diff, remove AI slop and over-engineering while preserving exact behavior. Triggers: /deslop, remove AI slop, clean AI artifacts, strip over-engineered patterns, simplify code, review changes for bloat. Flags: --staged, --unstaged, --base <branch>.
Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
Specifies best practices, including following RESTful API design principles, implementing responsive design, using Zod for data validation, and regularly updating dependencies. This rule promotes mode