自動化

Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when: (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.

Control event flow from EventSources to triggers. Master filtering, transformation, and multi-action capabilities for sophisticated event-driven automation.

Compile visual workflow canvas to Google ADK Python code. Use when generating executable agent code from WorkflowCanvas data structures. Supports all ADK workflow patterns.

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.

Test-driven development with Result types. Red-green-refactor cycles using vitest-mock-extended, explicit deps mocking, and Result assertions.

Эксперт по data annotation. Используй для ML labeling, annotation workflows и quality control.

Comprehensive guide to Claude Code's extensibility features including subagents, skills, plugins, commands, hooks, MCP servers, permissions, and automation. Use when the user asks about Claude Code features, capabilities, customization, extensibility, how to extend Claude Code, or automation workflows.

Two-phase workflow that generates explicit YAML plan before execution, with approval gates and checkpointing. Use for complex multi-file changes, refactoring, bug fixes with dependencies, or any task where mistakes are costly. Achieves 90% first-pass success rate vs ad-hoc changes. Provides audit trail, rollback capability, and explicit approval points. Triggers on "refactor", "multi-step", "plan then execute", "complex changes", "safe refactoring".

Creates Claude Code hooks for automation and workflow customization.Guides through hook events, configuration, and script creation.Use when user wants to create a hook, automate Claude Code, or asks about hook events.

Use when the user asks to create, build, implement, write, design, plan, generate, draft, make, add a feature, or develop. Provides tiered and anchored development preventing over-engineering and scope creep. The workspace and externalized traces drive tether's workflow.

Complete knowledge domain for Cloudflare Workflows - durable execution frameworkfor building multi-step applications on Workers that automatically retry, persiststate, and run for hours or days.Use when: creating long-running workflows, implementing retry logic, buildingevent-driven processes, scheduling multi-step tasks, coordinating between APIs,or encountering "NonRetryableError", "I/O context", "workflow execution failed","serialization error", or "WorkflowEvent not found" errors.Keywords: cloudflare workflows, workflows workers, durable execution, workflow step,WorkflowEntrypoint, step.do, step.sleep, workflow retries, NonRetryableError,workflow state, wrangler workflows, workflow events, long-running tasks, step.sleepUntil,step.waitForEvent, workflow bindings

Orchestrates the complete task planning workflow including codebase exploration, requirements gathering, and technical plan creation. Use when the user provides a new feature request, bug fix, or refactoring task that needs planning before implementation.

Manage emotion detection, LED responses, and mood-based automations for Ezra. Use when working on emotional regulation features, smart home responses, or the Chaos Orb.

Guided workflow for creating new Claude Code Skills with proper structure, documentation, templates, subagents, and hooks. Use this when the user wants to create a new skill or asks you to build tooling/automation. Ensures skills follow official conventions and are production-ready.

Store and retrieve documents using ChromaDB for RAG workflows. Use for persistent memory, research storage, and semantic search.

Load when working on documentation systems, README files, API docs, orimplementing documentation workflows. Contains best practices for treatingdocumentation as code with version control, automation, and CI/CD integration.

PolicyEngine-US tax and benefit microsimulation patterns, situation creation, and common workflows

This skill should be used when TODO: describe the sequential workflow this skill orchestrates and the triggers that should activate it.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Designing Slash Commands for Claude Code. Create and optimize slash commands with proper argument parsing, tool permissions, and agent orchestration. Use when building workflow entry points, automation commands, or user-facing shortcuts.