Loading...
Loading...
Found 1,276 Skills
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.
Clean Code principles adapted for C#/.NET including naming, variables, functions, SOLID, error handling, and async patterns. Use when: (1) reviewing C# code, (2) refactoring for clarity, (3) writing new code, (4) code review feedback.
Detect common code smells and anti-patterns providing feedback on quality issues a senior developer would catch during review. Use when user opens/views code files, asks for code review or quality assessment, mentions code quality/refactoring/improvements, when files contain code smell patterns, or during code review discussions.
This skill should be used when the user wants to invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
Juniors-focused React and TypeScript best practices. Use this skill when writing or reviewing code to enforce clear, consistent, and maintainable patterns across common scopes like React, TypeScript, styling, devtools, assets, and Git.
Requires detailed type annotations for all Python functions, methods, and class members.
Implement a feature or fix based on a Linear issue
Best practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities.
Check if the code you just wrote follows the frontend development guidelines.
Final code review and quality gate — run tests, check coverage, audit security, verify acceptance criteria from spec, and generate ship-ready report. Use when user says "review code", "quality check", "is it ready to ship", "final review", or after /deploy completes. Do NOT use for planning (use /plan) or building (use /build).
Comprehensive code review workflow - parallel specialized reviews → synthesis
Create and manage stacked (dependent) pull requests for complex features