Skill UI

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.

Implements and audits GA4/GTM analytics plans, event taxonomy, conversion tracking, and data quality so customer actions are captured accurately for confident decision-making.

A comprehensive guide detailing best practices for building high-quality, native-feeling applications using Expo Router. It covers advanced topics like component usage, advanced styling (flexbox, gradients), responsiveness, navigation patterns, and critical decisions on whether to use Expo Go or custom native builds.

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.

Defines a continuous autonomous agent loop pattern with quality gates, evaluations, and recovery actions, orchestrating CI/PR controls, RFC breakdown, and assessment cycles to keep release branches stable.

This skill provides deep technical expertise regarding the DWARF debugging format (v3-v5) and the DWARF standard. It assists in analyzing, parsing, verifying, and generating debug information from compiled binaries. Use cases include answering questions about the DWARF specification, writing code that interacts with DWARF data, and utilizing tools like `dwarfdump` or `readelf` for structural validation and quality metric extraction.

This assistant streamlines the workflow for managing GitHub issues using the GitHub CLI. It guides users through structured processes to create, list, and view issues. When creating, it prompts for detailed information (including issue type, reproduction steps, and expected vs. actual behavior for bugs), ensuring high-quality issue reports. It also allows filtering and listing of existing issues.

A comprehensive skill for advanced text and typography handling within the Makepad framework. It provides robust mechanisms for font configuration, text layout management (Layouter), and high-quality GPU-based text rendering using Signed Distance Fields (SDF). Use this skill when needing to implement rich text displays, manage complex font styles, or ensure crisp, scalable typography across different resolutions.

This comprehensive reference guide for Makepad provides essential materials for developers. It covers common errors, debugging tips, API documentation, and advanced techniques for adaptive and high-quality layouts. Use this resource when troubleshooting, looking up specific API details, or ensuring code robustness across different platforms.