Skill UI

Defines mandatory contribution guidance for repository work, insisting contributors locate workflow documentation, follow branch/commit/PR templates, and run required linters or tests before submitting changes, without executing forbidden scripts.

A comprehensive meta-skill template designed for developers to scaffold, structure, and define specialized Agent Skills for AI platforms like GitHub Copilot. It guides users through mandatory requirements, including folder naming conventions, YAML frontmatter best practices (name, description), and structuring the skill body with detailed workflows and documentation sections. Use this when building complex, specialized AI capabilities.

A comprehensive academic advisor covering the entire university journey. It guides students through major selection, GPA management, graduate school applications (Chinese and Western systems), study abroad planning, and career transition. Methodology includes Socratic questioning and structured decision-making to help users make informed, autonomous academic choices.

This skill is designed for scenarios requiring complex, multi-step task decomposition. Instead of asking an Agent to perform the task directly, it guides the process of requesting a clear, actionable, sequential execution plan from a stronger Agent. The core function emphasizes that the user must execute the generated plan themselves, ensuring the output is a roadmap, not a final answer.

This skill proactively detects and reports comprehensive system resources, including CPU cores, GPU types (NVIDIA, AMD, Apple Silicon), available memory, and disk space. It generates a detailed JSON report with strategic, context-aware recommendations for optimizing scientific computing workflows, such as recommending parallel processing libraries (Dask, joblib), out-of-core methods (Zarr), or appropriate GPU acceleration backends (Metal, ROCm). Use this before any large-scale data analysis, model training, or computationally intensive simulation to make informed architectural decisions.

LaminDB is an open-source, lineage-native lakehouse specifically designed for complex biological datasets and models. It provides unified capabilities for querying, tracking data lineage, validating schemas, and ensuring FAIR compliance across diverse data types (e.g., AnnData, Parquet, Zarr). Use this skill when managing multi-modal genomic data, tracking computational workflows (like Nextflow/Snakemake), or building robust, reproducible data infrastructure in bioinformatics.

Latch is a robust Python framework designed for building, deploying, and managing complex, scalable bioinformatics workflows as serverless pipelines. It supports integrating multiple analysis tools (like Nextflow/Snakemake) and handles cloud data management (LatchFile/LatchDir) and detailed resource configuration (GPU, CPU, memory). Ideal for running large-scale analyses such as RNA-seq, AlphaFold, and single-cell analysis in a reproducible, production-ready environment.

This guide outlines the rigorous structure and technical requirements for drafting comprehensive 'embodiment descriptions' within patent specifications. It instructs users on how to detail methods, systems, and variations to teach a Person Having Ordinary Skill In The Art (POSITA) how to make and use the invention. Crucially, it emphasizes describing the 'how' (structure and process) and strictly prohibits the inclusion of empirical data, accuracy percentages, or performance test results.

Provides comprehensive integration patterns for Finta fundraising CRM. This skill details how to connect Finta with external services via CSV processing, email APIs (Gmail/Outlook), webhooks (Zapier/Make), and payment gateways. It is essential for automating investor outreach, syncing complex deal data, and building custom fundraising dashboards throughout the investment lifecycle.

This framework shifts the focus from product features to the fundamental 'job' customers need to get done. It helps teams uncover deep customer needs by analyzing functional, emotional, and social dimensions. Use it for product positioning, feature prioritization, and understanding market-product fit by defining the progress customers seek to make in specific life circumstances.

This tool enforces four rigorous coding principles, inspired by Andrej Karpathy's insights on LLM pitfalls. It guides developers to surface assumptions, prioritize simplicity, make surgical changes, and define verifiable goals. Use it when reviewing code, checking diffs, or before committing to ensure high code quality and prevent over-engineering.

This tool enables the real-time transmission of structured Aegis events (such as clip completion or person detection) to any external webhook URL. By posting event data as JSON, it seamlessly integrates Aegis functionality with major automation platforms like Zapier, IFTTT, Make, or custom backend services, allowing users to build complex, event-driven workflows and extend system capabilities.