agent-execution-redux

Manage AI agent execution state with a four-layer Redux architecture.

2|1|Updated Aug 24, 2024
One-click install
npx skills add https://github.com/armanisadeghi/ai-matrx --skill agent-execution-redux
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-execution-redux
Source: https://github.com/armanisadeghi/ai-matrx/tree/main/.cursor/skills/agent-execution-redux
Command: npx skills add https://github.com/armanisadeghi/ai-matrx --skill agent-execution-redux

SYSTEM DOCUMENTATION & REQUIREMENTS

State management architecture for the AI agent execution system AND the rules for triggering agent shortcuts from product code. Covers the four-layer Redux structure (agent source, app context, execution instances, request lifecycle), slice ownership, body assembly, NDJSON streaming, the rules for extending instance slices, and the consumption-side rules for engaging shortcuts (trigger APIs, registry, warm-up, direct vs non-direct display modes, scope/mapping contract, cleanup). Use when working on any file in features/agents/redux/, building agent UI components, creating execution instances, wiring selectors for agent state, adding new per-instance capabilities, OR when firing/engaging/triggering an agent shortcut from any surface (button, context menu, mounted component, programmatic). Triggers on: instanceId, agentDefinition, executionInstances, instanceUIState, instanceModelOverrides, instanceVariableValues, instanceResources, instanceContext, instanceUserInput, instanceClientTools, activeRequests, instanceConversationHistory, assembleRequest, executeInstance, createManualInstance, createInstanceFromShortcut, launchAgentExecution, useShortcutTrigger, useShortcut, triggerShortcut, launchShortcut, useAgentLauncher, getSystemShortcut, SYSTEM_SHORTCUTS, ensureShortcutLoaded, applicationScope, scopeMappings, UnifiedAgentContextMenu, AgentGenerator, displayMode, "trigger shortcut", "fire shortcut", "engage shortcut", "run a shortcut", "use a shortcut".

Frequently Asked Questions about agent-execution-redux

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage AI agent execution state with Redux?

AI agent execution state is managed using a four-layer Redux architecture covering agent definitions, app context, execution instances, and request lifecycle to ensure predictable cleanup and stable state.

What is the best way to trigger AI agent shortcuts from product code?

Triggering AI agent shortcuts requires using trigger APIs, a shortcut registry, and warm-up routines, choosing between direct and non-direct display modes while adhering to scope mapping contracts for proper execution.

How does NDJSON streaming work for AI agent execution instances?

NDJSON streaming handles the request lifecycle within execution instances, managing body assembly and data flow to support real-time updates during AI agent execution orchestration.

When do I need snapshot isolation in AI agent state management?

Snapshot isolation is needed during execution instance lifecycle rules to ensure predictable cleanup and maintain stable state when extending per-instance slices or managing active requests.

Can I extend instance slices for custom per-instance capabilities in Redux?

Extending instance slices allows adding new per-instance capabilities by wiring selectors for agent state, managing instance variable values, resources, and context within the defined Redux architecture.

Does this Redux agent execution architecture support context menus and programmatic launches?

The architecture supports launching agent execution from various surfaces including context menus, mounted components, and programmatic triggers via useShortcut, triggerShortcut, and useAgentLauncher hooks.