Skill UI

Automate Crowdin tasks by discovering current tool schemas via Rube MCP before managing connections and executing workflows through Composio’s toolkit for reliable localization operations.

This skill details best practices for handling and structuring Evernote data. It covers designing local database schemas (SQL), advanced ENML content processing (to Markdown/HTML), managing attachments, and implementing reliable incremental synchronization using Update Sequence Numbers (USN). Ideal for developers building robust applications requiring deep, local data access and integrity checks for Evernote content.

Outlines guarantees valid JSON/XML/code outputs by applying CFG/FSM-constrained token filtering, Pydantic schemas, and grammar-level sampling while supporting local Transformers, llama.cpp, and vLLM backends for fast inference.

Automate the entire Supabase development lifecycle within CI/CD pipelines using GitHub Actions. This tool links projects, validates database migrations, deploys Edge Functions, generates TypeScript types, and runs comprehensive tests against local Supabase instances. Essential for maintaining robust code quality and ensuring schema consistency before deployment.

Comprehensive SEO analysis for websites and businesses, including audits, technical checks, schema, content quality, Core Web Vitals, sitemap review, local and ecommerce SEO, and AI search visibility planning.

This skill provides methods for reliably extracting typed, validated, and structured data from Large Language Models (LLMs), moving beyond simple text parsing. It covers best practices across major APIs (OpenAI's response_format, Anthropic's tool_use, Google's responseSchema) and local models. Key workflows include defining schemas (Pydantic/Zod), implementing constrained decoding, and building robust retry loops for production-grade data pipelines.

The HypoGeniC skill facilitates the iterative proposal and scoring of textual hypotheses from labeled datasets using LLMs. It provides tools for generating candidate hypothesis banks and task-prediction statistics. Crucially, it mandates a rigorous, local review workflow, emphasizing dataset auditing (checksums, schemas), configuration validation, and explicitly separating candidate results from definitive scientific conclusions.

LaminDB is an open-source, lineage-native lakehouse designed for managing complex biological datasets and computational workflows. It makes diverse scientific data (like scRNA-seq, AnnData) queryable, traceable, and compliant with FAIR principles. Core capabilities include robust data lineage tracking, schema validation, ontology-backed annotation (Bionty), and unified querying across multiple cloud/local storage systems. It is essential for bioinformatics research and building reproducible data infrastructure.

Provides a comprehensive setup guide for running ClickHouse locally using Docker Compose. This includes defining the database schema, seeding mock data, and setting up robust integration tests (using vitest). Ideal for developers building OLAP systems or performing local data analysis to ensure schema and query reliability.

This workflow provides a complete, end-to-end solution for building and deploying robust web scrapers using Crawlee on the Apify platform. It guides users through every stage: defining input schemas, setting up the Actor with a sophisticated router pattern, extracting structured data (e.g., product details), saving results to datasets, and managing the full lifecycle from local testing to cloud deployment via apify-cli.

This skill pulls the latest GEO-SEO components, including skills, agents, scripts, and schema templates, from the official upstream repository. It performs a detailed comparison (diff) to show all changes—new, modified, or removed—before applying the update. It ensures local customizations are preserved while keeping the toolkit current. Use this whenever you suspect your local setup might be outdated.

Analyze local SEO performance for Google Business Profile, NAP consistency, citations, reviews, local schema, location pages, and multi-location sites. Useful for brick-and-mortar, service area, or hybrid businesses targeting map pack visibility.