Найдите подходящую возможность для вашего агента.
Expert knowledge for implementing distributed sagas in Composable Rust. Use when coordinating multiple aggregates in distributed transactions, implementing compensation logic or rollback flows, working with EventBus trait or Redpanda integration, designing saga state machines, or questions about eventual consistency and distributed transaction patterns.
Production-ready Supabase database schemas for customers, subscriptions, payments, invoices, and webhook events with comprehensive Row Level Security policies. Use when setting up payment infrastructure, creating subscription tables, implementing secure payment data storage, or configuring RLS policies for multi-tenant payment systems.
Run the full ParserZamaActive validation suite to ensure database schema is synchronized, parser logic matches golden set expectations, and block type classification is accurate. CRITICAL - Use this skill BEFORE committing any code changes to git. Use when you need to: (1) Validate database schema version and table structure, (2) Test parser accuracy against golden set truth data, (3) Verify block type normalization and classification, (4) Ensure system integrity after migrations or parser changes, or (5) Prepare for git commit with confidence that all tests pass
Catalog and analyze prompts in Flow SDK workflows before conversion. Use to identify prompt formats, variables, and conversion requirements.
Convert analysis reports from docs/analysis/ into actionable tasks in the SQLite database
Fix Zod schema import issues in Output SDK workflows. Use when seeing "incompatible schema" errors, type errors at step boundaries, schema validation failures, or when schemas don't match between steps.
Python specialist for Faiston One Platform. Use when writing FastAPI endpoints, Google ADK agents, async patterns, Pydantic models, and Lambda handlers. PROACTIVE for code review and refactoring.
Protecting personal and sensitive data throughout the machine learning lifecycle, from training to inference.
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and production deployment.
Database specialist covering PostgreSQL, MongoDB, Redis, and advanced data patterns for modern applications
Playbook สำหรับ backfill historical data และ reconcile inconsistencies ระหว่าง data sources
Detecting and managing schema changes that can break data pipelines and downstream consumers.
Convert COBOL applications to Java following mainframe modernization best practices. Handles CICS transactions, batch programs, VSAM files, DB2 integration, and data structure migrations. Use when modernizing CardDemo COBOL code to cloud-native Java applications.
Continuous monitoring and diagnostics for ensuring high availability, performance, and stability of database systems.
Parse FAA aviation data sources (NASR, CIFP, d-TPP, DOF) into SQLite databases. Use when processing 28-day subscription data, building automated data pipelines, implementing AIRAC cycle updates, or working with FAA fixed-width file formats. Includes parsers for airports, runways, navaids, fixes, airways, frequencies, procedures (SIDs/STARs/approaches), obstacles, and approach plate manifests.
Comprehensive guide to data retention policies, deletion workflows, and implementing GDPR/CCPA right to erasure across distributed systems.
Farm out AI tasks via Named Pipe to get isolated context. Use when processing large files, batch summarization, or to avoid context pollution. Each call runs in fresh context.
Validate and audit CSV data for quality, consistency, and completeness. Use when you need to check CSV files for data issues, missing values, or format inconsistencies.
Manage Unity Catalog metadata tags for data governance and classification. Use when applying tags to tables and columns, classifying data sensitivity (PII, PHI), marking data quality attributes, or when user mentions Unity Catalog tagging, metadata management, data governance, or compliance workflows.
End-to-end orchestrator for parsing raw workout logs through the complete 4-stage pipeline (ingest, parse, validate, commit) with quality gates and git tracking. Use this skill when: (1) Processing new workout files into structured database records, (2) Running the complete Master Orchestrator pipeline from text to database, (3) Validating workout data before committing to production tables, (4) Testing parser changes against real workout data, or (5) Automating the full workflow from raw text ingestion through atomic database commit with validation checks at each stage
