Essential command-line tools and system utilities.
Manage Supabase database using Orchestrator AI's storage-based sync system. Use when working with Supabase, database snapshots, migrations, agent exports, N8N workflow exports, backups, or storage scripts. CRITICAL: Prevents direct Supabase operations - all operations MUST use storage/scripts/*.sh
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.
Catalog and analyze prompts in Flow SDK workflows before conversion. Use to identify prompt formats, variables, and conversion requirements.
BioBlend and Planemo expertise for Galaxy workflow automation. Galaxy API usage, workflow invocation, status checking, error handling, batch processing, and dataset management. Essential for any Galaxy automation project.
Advanced TanStack Query patterns including useInfiniteQuery, QueryClient operations, and optimistic updates. Use for infinite scroll, optimistic UI, or advanced caching scenarios.
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.
Playbook สำหรับ backfill historical data และ reconcile inconsistencies ระหว่าง data sources
BigQuery integration patterns for CA Lobby lobby data with BLN API schema. Use when working with CA Lobby backend, database queries, or data service. Provides CA-specific BigQuery patterns and Flask integration guidance.
Expert guidance for creating, implementing, and troubleshooting Sync Jobs in the Frappe Tweaks framework. Use when working with Sync Job Types, Sync Job controllers, sync job enqueueing, debugging sync job issues, implementing sync logic, or understanding sync job lifecycle and hooks.
Database operations for BAZINGA orchestration system. This skill should be used when agents need to save or retrieve orchestration state, logs, task groups, token usage, or skill outputs. Replaces file-based storage with concurrent-safe SQLite database. Use instead of writing to bazinga/*.json files or docs/orchestration-log.md.
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.
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
Design and implement automated workflows combining visual logic with custom code. Create multi-step automations, integrate APIs, and build AI-native pipelines. Use when designing automation flows, integrating APIs, building event-driven systems, or creating LangChain-style AI workflows.
Expert knowledge of Claude Code CLI tools (Read, Write, Edit, Bash, Grep, Glob, Task, MCP), features (Skills, Checkpoints, Hooks), and best practices for agentic coding assistance
Documentation for Kubernetes Agent Sandbox - a CRD-based system for managing isolated AI agent execution environments. Use for queries about Sandbox CRDs (Sandbox, SandboxTemplate, SandboxClaim, SandboxWarmPool), Python SDK (SandboxClient, SandboxRouter, ComputerUseExtension), network policies, security configurations, and implementation examples. Keywords kubernetes sandbox, agent sandbox, CRD, python sdk, agentic-sandbox-client, isolated environment, gvisor, network policy.
Terminal session manager for AI coding agents. Use when user mentions "agent-deck", "session", "sub-agent", "MCP attach", or needs to (1) create/start/stop/restart/fork sessions, (2) attach/detach MCPs, (3) manage groups/profiles, (4) get session output, (5) configure agent-deck, (6) troubleshoot issues, or (7) launch sub-agents. Covers CLI commands, TUI shortcuts, config.toml options, and automation.
Context Engineering 101 curriculum slide generation. Use this skill when working on CE101 curriculum to: (1) Generate styled PowerPoint presentations from markdown, (2) Create PNG previews of slides, (3) Update master presentation from curriculum modules
Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parallel with swim lane visualization, event filtering, and live charts. USE WHEN user says 'start observability', 'agent dashboard', 'monitor agents', 'watch agent activity', 'multi-agent monitoring', 'track subagents', or needs to debug multi-agent workflows. **Key Features:** - 🔴 Real-time event streaming via WebSocket - 📊 Agent swim lanes showing parallel execution - 🔍 Event filtering by agent, session, event type - 📈 Live charts for tool usage patterns - 💾 Filesystem-based (no database required) **Inspired by [@indydevdan](https://github.com/indydevdan)**'s work on multi-agent observability. **Our approach:** Filesystem + in-memory streaming vs. indydevdan's SQLite database approach.
Create or refine a VibeDev Studio UnifiedWorkflow graph via tool calls. Use when the user says `$vd-create`, asks the model to “build the workflow graph”, “set up Research/Planning/Execution/Review steps”, or wants the model to collaboratively design prompts/conditions/breakpoints and write them into `unified_workflows` so the UI canvas shows the plan before running `$vd-next`.
Track AI code contributions for auditing and attribution. Use this skill BEFORE writing, editing, creating, or modifying any code files. Enables automatic detection of AI-authored vs human-authored code changes. Required for code attribution compliance.
Integrating AI and LLM capabilities into applications for enhanced functionalities. Use when implementing AI features, processing data with ML models, building generative workflows, or integrating AI APIs.
