Skill UI

This skill forces the AI to operate in a non-inferential mode, ensuring every claim—factual, legal, or numerical—is strictly anchored to user-provided materials or verified online sources. It eliminates assumptions, gap-filling, and background knowledge reliance, making it essential for legal research, evidence review, citation checking, and high-stakes document analysis where evidential fidelity is paramount.

This skill provides a rigorous, multi-step methodology for verifying and citing legal documents related to the Special Tribunal for Lebanon (STL). It guides users through complex international criminal cases (e.g., Ayyash et al., 2011 Decision) by establishing strict citation standards. The process requires verifying sources against dedicated legal archives (stl-tsl.org, legal-tools.org) and defining citation levels (existence, content, paragraph), ensuring academic and legal accuracy for international justice research.

This skill guides the extraction of structured data from multiple documents (PDF, DOCX) into a comprehensive, cited Excel matrix. It is ideal for legal, contractual, or research review processes where users need to compare specific clauses, provisions, or pieces of information across numerous source files, ensuring every extracted data point includes a citation (page number and context quote) for verifiable accuracy.

Helps users stuck in repetitive failures or facing hard choices by applying lateral thinking personas (hacker, researcher, simplifier, architect, contrarian). Runs solo or as a debate to synthesize multiple perspectives and converge on one actionable recommendation.

This skill queries the NCATS Translator ARAX API for biomedical knowledge-graph relationships. It supports one-hop and two-hop lookups with Biolink constraints, entity normalization, and provider federation. Users can inspect provenance and edge bindings. It is designed for public research queries only, requiring Python 3.10+ and HTTPS access. Do not use for clinical guidance or sensitive data.

This skill enables users to discover, compare, and research autonomous AI agents using the AgentFolio directory. It helps map the landscape of agent frameworks and tools, identify market gaps, and gather benchmarks before building new agents. Ideal for evaluating existing solutions, understanding integration surfaces, and tracking emerging trends in agent architectures and deployments.

Researches uncertain questions via user-approved web search or ChatGPT consultation, presents concise options with sources, and waits for explicit approval before writing code.

This skill enables autonomous multi-step research using Google's Gemini Deep Research Agent. Users can initiate queries, monitor progress, and collect cited reports for market analysis, literature reviews, or competitive scans. It requires a Gemini API key and Python environment. Ideal for tasks needing structured, source-grounded reports beyond simple web searches.

This skill enables AI assistants to interact with the Hugging Face Hub via Model Context Protocol (MCP). Users can search for models, datasets, and papers, retrieve repository details, fetch documentation, and execute compute jobs on GPU or CPU. It also allows leveraging Gradio Spaces as functional AI tools. Ideal for developers and researchers needing direct access to the HF ecosystem for model discovery, training, and deployment workflows.

This skill helps security researchers identify HTML injection vulnerabilities in web applications. It provides techniques for detecting unescaped user input, escalating to XSS, and proving impact with unique canaries. Recommended for authorized penetration testing and bug bounty engagements.

idea-os is a comprehensive, five-phase pipeline designed to transform a raw, abstract idea into a fully structured, build-ready plan. It guides users through Triage, Clarification, Deep Research, detailed PRD creation (including non-goals and metrics), and finally, a phased execution plan. The system adapts its complexity and vocabulary to the user's sophistication level, providing everything from foundational market analysis to actionable technical stack recommendations.

A powerful tool for deterministic and reproducible retrieval of evidence from specialized academic and policy corpora. It supports searching arXiv (preprints), PubMed/PMC (biomedical literature), and US policy documents. Users can check corpus freshness, retrieve stable metadata, and fetch full-document Markdown for high-reliability research tasks.