You need consistent ways to measure LLM quality and regressions. This skill provides metrics, human review guidance, and testing frameworks for reliable AI assessment.

Content creators struggle to find trending topics that resonate with audiences. This skill fetches real-time hot list data from TopHub and uses Claude to identify high-potential topics and generate content suggestions.

Prevents AI models from treating search results as infallible truth. Establishes structured protocols for external evidence gathering, source tiering, and verification sprawl prevention.

Get current information beyond AI training data by searching the web instantly. Perfect for research, fact-checking, and staying updated with latest developments.

Enhance your AI agents with real-time web search and content extraction capabilities. This skill provides access to Tavily and Exa APIs through inference.sh CLI for research, fact-checking, and RAG pipelines.

Shallow code reviews lead to misunderstandings and bugs. This skill enforces rigorous, evidence-based investigation of codebases through structured multi-turn analysis.

An uncompromising Academic Research Engineer that applies scientific rigor, objective criticism, and zero fluff to engineering challenges. Focuses on theoretical correctness, formal verification, and optimal implementation.

Improve LLM outputs with proven prompt engineering techniques. This skill provides patterns for chain-of-thought reasoning, few-shot learning, and template systems that make AI interactions more reliable and controllable.

Stop the copy-paste dance between your browser and editor. This skill lets Claude Code chat directly with Google NotebookLM for source-grounded answers that cite your uploaded documents.

Stay current with fast-moving AI trends without drowning in noise. This skill surfaces what people are actually upvoting and discussing right now, then writes copy-paste prompts tailored to your target tool.

Deep research requires comprehensive information from multiple sources. This skill orchestrates 10 AI agents to work in parallel, gathering and synthesizing research faster than sequential methods.

Finding relevant information online is time-consuming with traditional keyword search. This skill enables semantic search using AI embeddings to discover similar content and conduct structured research through the Exa API.

Manual research is time-consuming and often incomplete. This skill automates multi-step research using Google Gemini Deep Research Agent to deliver comprehensive, cited reports in minutes.

This skill helps developers design and implement dynamic context management systems for AI applications, including vector databases, knowledge graphs, and intelligent memory architectures that provide the right information to AI systems at the right time.

Language models exhibit predictable performance degradation as context length increases. This skill helps diagnose lost-in-middle, poisoning, distraction, and clash patterns to build more reliable AI systems.

Stop relying on outdated documentation in your AI training data. This skill connects Claude Code to the Context7 API for real-time access to current library and framework documentation.

This skill helps users analyze their competitive environment using proven business frameworks. It provides structured methodologies like Porter's Five Forces and Blue Ocean Strategy to identify market positioning opportunities.

Researchers face overwhelming literature and complex data analysis challenges. This skill provides structured methodologies for literature review, experimental design, and statistical analysis to accelerate scientific discovery.

Get fast, LLM-optimized web search results with Qryma API. This skill provides structured search responses in Markdown, JSON, or Brave-style formats for seamless integration into your AI workflows.

AI agents lose performance as conversations grow longer. This skill diagnoses lost-in-middle problems, context poisoning, and attention failures to restore optimal agent performance. It provides patterns for recognizing and mitigating context degradation.