skills.rest
anukkrit149
anukkrit149COMMUNITY
Explore all skills by this author →
Website𝕏@anukkritGitHub

deep-agents-orchestration

Orchestrate Deep Agent workflows with subagent delegation, todo tracking, and human approval gates.

Updated May 26, 2026
Search Tags:#agent orchestration#task planning#human-in-the-loop#deep agents#subagent delegation#workflow interrupts#todo middleware
One-click install
npx skills add https://github.com/anukkrit149/anukkrit-skills --skill deep-agents-orchestration-anukkrit149
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-agents-orchestration
Source: https://github.com/anukkrit149/anukkrit-skills/tree/main/cloud/skills/deep-agents-orchestration
Command: npx skills add https://github.com/anukkrit149/anukkrit-skills --skill deep-agents-orchestration-anukkrit149

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep Agents need reliable orchestration to delegate sub-tasks, break down complex work into plans, and pause for human approval on sensitive steps.

Core Features & Use Cases

  • SubAgentMiddleware (Task Delegation): Delegate work to specialized subagents via the task tool for isolated, tool-focused execution.
  • TodoListMiddleware (Task Planning): Automatically create and track multi-step plans using write_todos, including statuses like pending and in_progress.
  • HumanInTheLoopMiddleware (Approval Workflows): Require approval before executing sensitive actions (e.g., writes or risky operations), using interrupt/resume semantics.

Use this for multi-step agent workflows such as coordinating research subagents, generating incremental deliverables, or gating high-stakes operations behind explicit approvals.

Quick Start

Invoke a Deep Agent for a complex project with planning, then approve any paused sensitive actions before resuming execution.

Frequently Asked Questions about deep-agents-orchestration

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

FAQPage Schema
How do I add human-in-the-loop approval to my agent workflow?▼

Human-in-the-loop approval requires configuring HumanInTheLoopMiddleware with interrupt_on flags and a checkpointer to pause sensitive agent actions before resuming execution.

What is the best way to delegate sub-tasks to specialized agents?▼

Delegating sub-tasks to specialized agents requires SubAgentMiddleware, which provides a task tool for isolated, tool-focused execution within deep agent workflows.

How does task planning work for multi-step agent execution?▼

Task planning for multi-step execution uses TodoListMiddleware to automatically create and track plans with write_todos, assigning statuses like pending and in_progress to coordinate complex workflows.

Can I gate risky tool calls behind explicit approval in production workflows?▼

Yes, you can gate risky tool calls behind explicit approval by using interrupt and resume semantics to pause high-stakes operations until a human reviews and authorizes the action.

Do I need a checkpointer to use interrupt and resume coordination?▼

Yes, a checkpointer is required to enable interrupt and resume coordination, ensuring paused agent workflows can safely resume execution after human approval is granted.

Related Skills

Explore More Software Engineering Skills→
dotlab-hqdotlab-hq

langchain-middleware

Configure human-in-the-loop approval for LangChain tool calls with per-tool policies.

Official
Advanced
dotlab-hqdotlab-hq

deep-agents-orchestration

Orchestrate subagent task delegation, persistent todo planning, and human approval interrupts.

Official
Advanced
caio-moliveiracaio-moliveira
36

deep-agents-orchestration

Coordinate subagents, plan tasks, and enforce human approval in AI workflows.

Community
Advanced
tivon-xtivon-x

langchain-middleware

Add human approval and custom middleware to LangChain agent tool calls.

Community
Advanced