Найдите подходящую возможность для вашего агента.
Creates STRUCTURED summary.md in each daily folder. Analyzes chat conversations and generates actionable summaries with "Što je uradio" and "Što bi trebao da uradi" sections per person. Use for daily reports and activity tracking.
Create dbt models following FF Analytics Kimball patterns and 2×2 stat model. This skill should be used when creating staging models, core facts/dimensions, or analytical marts. Guides through model creation with proper grain, tests, External Parquet configuration, and per-model YAML documentation using dbt 1.10+ syntax.
Use when working on Acuantia's BigQuery Dataform pipeline (acuantia-gcp-dataform project) - adds Acuantia-specific patterns on top of dataform-engineering-fundamentals: ODS two-arg ref() syntax, looker_ filename prefix, Looker integration (looker_prod/looker_dev), acuantia dataset conventions, coordination with callrail_data_export/dialpad_data_integration/looker projects
Distributed evolutionary memory system using Merkle-DAG branching timelines, holographic erasure coding, and stake-weighted consensus to maintain coherent collective history across thousands of agents despite forking narratives and temporal relativity.
Generate Apache Airflow ETL pipelines for government websites and document sources. Explores websites to find downloadable documents, verifies commercial use licenses, and creates complete Airflow DAG assets with daily scheduling. Use when user wants to create ETL pipelines, scrape government documents, or automate document collection workflows.
PM Airtable data model reference. Use when creating tables, querying structure, or understanding relationships between Domain, Subdomain, Capability, Entity, Requirement, and BacklogItem tables.
Define database models with clear naming, appropriate data types, constraints, relationships, and validation at multiple layers. Use this skill when creating or modifying database model files, ORM classes, schema definitions, or data model relationships. Apply when working with model files (e.g., models.py, models/, ActiveRecord classes, Prisma schema, Sequelize models), defining table structures, setting up foreign keys and relationships, configuring cascade behaviors, implementing model validations, adding timestamps, or working with database constraints (NOT NULL, UNIQUE, foreign keys). Use for any task involving data integrity enforcement, relationship definitions, or model-level data validation.
Validate production batch execution - trigger daily runs and analyze traces for architecture completeness and result quality
Transform BPMN 2.0 process diagrams into professional, editable PowerPoint presentations. Features a 3-tier hierarchical layout with chevrons, rounded boxes, and square task boxes with detailed bullet points.
Designs Redis caching strategies for Braiins API data, optimizing for data freshness vs. API rate limits and response latency.
Expert in retrieving IT masterdata and data lineage from L'Oréal's BTDP infrastructure. **Use this skill when user asks to search, find, or query for any BTDP/L'Oréal resource including: GCP projects, BigQuery datasets, BigQuery tables, Google Groups, applications, repositories, domains, IT organizations, people/users, GCP services, GCP SKUs, or APIs.** Also use for data lineage queries (upstream/downstream dependencies, parents/children). **Trigger keywords:** "search for project", "find the project", "find dataset", "search table", "what is the project", "what is the dataset", "what is the table", "what is the group", "what is the application", "find group", "search application", "show me project", "get project", "list projects", "lineage", "masterdata", "master data", "BTDP", "SDDS" **DO NOT use filesystem commands** (find, grep, ls) to search for BTDP resources. Always use this skill's RAG indices, MCP tools, or BigQuery SQL queries instead.
Complete 5-system healthcare content pipeline for regulated medical content generation. Includes LGPD data extraction (Type B), claims identification (Type A), scientific reference search (Type C), SEO optimization (Type B), and final consolidation (Type D). Validated ROI - 99.4% time reduction, 92.4% cost reduction. Use when implementing healthcare content automation, building regulated medical systems, or optimizing production pipelines.
Generate high-quality synthetic datasets using statistical samplers and Claude's native LLM capabilities. Use when users ask to create synthetic data, generate datasets, create fake/mock data, generate test data, training data, or any data generation task. Supports CSV, JSON, JSONL, Parquet output. Adapted from NVIDIA NeMo DataDesigner (Apache 2.0).
Database schema design and data modeling patterns including normalization principles (1NF-5NF), denormalization trade-offs, entity relationship design, indexing strategies, schema evolution, and domain-driven design patterns. Activates when designing new database schemas, refactoring data models, discussing normalization vs denormalization decisions, planning schema migrations, or modeling complex domain entities. Use when creating new tables/collections, redesigning existing schemas, evaluating relationship patterns, or making data integrity decisions.
Generate comprehensive dbt test suites following FF Analytics data quality standards and dbt 1.10+ syntax. This skill should be used when creating tests for new dbt models, adding tests to existing models, standardizing test coverage, or implementing data quality gates. Covers grain uniqueness, FK relationships, enum validation, and freshness tests.
Expert in creating database diagrams and visual representations. Use when generating ERDs, schema diagrams, or visualizing database relationships with Mermaid.js.
Execute SQL queries against Databricks using the DBSQL MCP server. Use when querying Unity Catalog tables, running SQL analytics, exploring Databricks data, or when user mentions Databricks queries, SQL execution, Unity Catalog, or data warehouse operations. Handles query execution, result formatting, and error handling.
Kailash DataFlow - zero-config database framework with automatic model-to-node generation. Use when asking about 'database operations', 'DataFlow', 'database models', 'CRUD operations', 'bulk operations', 'database queries', 'database migrations', 'multi-tenancy', 'multi-instance', 'database transactions', 'PostgreSQL', 'MySQL', 'SQLite', 'MongoDB', 'pgvector', 'vector search', 'document database', 'RAG', 'semantic search', 'existing database', 'database performance', 'database deployment', 'database testing', or 'TDD with databases'. DataFlow is NOT an ORM - it generates 11 workflow nodes per SQL model, 8 nodes for MongoDB, and 3 nodes for vector operations.
