Skill UI

A comprehensive guide covering patterns and architectures for automating code execution using LLMs. It spans simple sequential pipelines (e.g., daily dev scripts) to advanced, RFC-driven multi-agent Directed Acyclic Graph (DAG) orchestration. Ideal for building CI/CD style continuous development pipelines, managing complex state, and automating quality gates without human intervention.

This skill is intended to analyze and improve the quality of codebases, ensuring adherence to best practices and coding standards. Note: This specific file is a translation placeholder, and the core functionality description should refer to the original skill file for details.

Explains when to call the code-reviewer subagent, how to collect SHAs, fill the template, and act on its feedback so every task, feature, or merge meets quality expectations.

Guides execution of implementation plans by dispatching isolated subagents per task, enforcing a spec-first then quality review loop, and preserving overall coordination context for faster, high-quality iterations.

Guides product and growth teams through evaluating whether to scale, test, or kill acquisition channels using unit economics (CAC, LTV, payback), customer quality (retention, NRR), and scalability indicators for data-driven go-to-market budgeting.

Helps product managers diagnose whether AI workflows rely on indiscriminate context stuffing or deliberate context engineering, then apply bounded domains, retrieval, and Research→Plan→Reset→Implement practices to improve reliability and output quality.

This skill provides comprehensive techniques for optimizing prompts used with any Large Language Model (LLM). It teaches proven methodologies—including Role definition (R), Context setting (S), Constraints (C), Instructions (I), and Templates (T)—to transform vague inputs into precision-engineered instructions. Users can reliably achieve structured JSON output, implement Chain-of-Thought reasoning, reduce hallucinations, and minimize token usage, ensuring consistent and high-quality results across different AI platforms.

A comprehensive guide to building production-grade evaluation systems for Large Language Models (LLMs). This skill covers advanced methodologies, including Direct Scoring and Pairwise Comparison, alongside critical techniques for mitigating systematic biases (e.g., Position Bias, Length Bias). Learn how to select appropriate metrics and structure prompts to ensure reliable, consistent, and objective quality assessment across various AI applications.

This model provides an engineering operational framework for teams that leverage AI agents to generate large volumes of code. It shifts the focus from simple syntax to process quality, robust architecture design, rigorous testing, and systematic risk control, ensuring the development of highly stable and reliable systems in AI-assisted environments.

This skill enforces a rigorous, opinionated baseline for UI development, ensuring consistency across spacing, hierarchy, typography, and layout. It helps maintain high code quality by fixing structural and stylistic inconsistencies, particularly useful for polishing AI-generated or quickly developed interfaces to meet professional standards and accessibility requirements.

This skill simulates a senior engineer's final, deep audit of an entire codebase before committing or pushing to a remote repository. It systematically checks for junk files, dead code, security vulnerabilities (secrets, injection flaws), and performance bottlenecks (N+1 queries). Use this pre-flight check before any major release or public deployment to ensure maximum code quality and production readiness.

This pattern defines a robust, continuous loop structure for autonomous agents. It integrates crucial components like quality gates, evaluation harnesses, and explicit recovery controls. It guides complex workflows by defining decision paths (e.g., PR control, RFC decomposition) and includes strategies to mitigate common failure modes such as infinite loop churn or cost drift, ensuring measurable progress in autonomous systems.