Agent Skills Hub

research-lookup

Intelligent research agent that automatically routes queries between fast web search, deep multi-source synthesis, and academic database lookups.

ring:dev-sre

Gate 2 development cycle skill that validates observability implementation, including structured logging, OpenTelemetry tracing, and instrumentation coverage, without modifying code.

threejs-geometry

Three.js geometry generation: built-in shapes, BufferGeometry, vertex manipulation, custom meshes, and performance-optimized instanced rendering.

skr

A command-line tool for managing, building, and deploying Agent Skills as OCI artifacts within the Agent Skills ecosystem.

paid-ads

Expert skill for planning, launching, and optimizing paid advertising campaigns across Google, Meta, LinkedIn, and more, with focus on performance, ROAS, and lead acquisition.

liquid-il

A high-performance Liquid template engine that compiles templates into optimized Ruby and machine code via an intermediate language (IL).

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

subtitles

Fetch YouTube transcripts and subtitles. Ideal for video summarization, language learning, accessibility, and content analysis. Supports timestamped data and raw text extraction.

design-system-implementation

Enforce strict UI adherence to your project's design system tokens, components, and layout patterns for consistent frontend implementation.

sql-queries

Generate optimized SQL queries from natural language. Supports BigQuery, PostgreSQL, MySQL, and Snowflake. Analyze database schemas, interpret business requirements, and output ready-to-run queries with explanations.

foundry

Foundry development guide for CMTAT RuleEngine contracts, including testing, deployment scripts, and project-specific Solidity patterns.

paper-write

Drafts LaTeX research papers section-by-section using paper plans and research narratives with multi-model reviewer validation.