skills.rest
AskTinNguyen
AskTinNguyenCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

dispatch

Coordinate parallel agent workers using a shared task ledger and dependencies.

1|Updated Jan 26, 2026
Search Tags:#workflow#dependencies#runtime#dispatch#adapter#task-coordination#mult-agent
One-click install
npx skills add https://github.com/AskTinNguyen/vesper-team-skills --skill dispatch-asktinnguyen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dispatch
Source: https://github.com/AskTinNguyen/vesper-team-skills/tree/main/dispatch
Command: npx skills add https://github.com/AskTinNguyen/vesper-team-skills --skill dispatch-asktinnguyen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Coordinates complex work across multiple agents by using a shared task ledger and explicit dependencies to coordinate decomposition, ownership, monitoring, and recovery.

Core Features & Use Cases

  • Universal, runtime-agnostic workflow for decomposing work, tracking dependencies, and coordinating parallel execution.
  • Adapter-aware runtime support with hooks for archiving progress and enabling safe recovery after failures.
  • Use cases include large feature work broken into 3-10 tasks with explicit blockers and ownership, across native task tools, shared workspaces, or manual boards.

Quick Start

Start Claude Code with a shared task list, decompose a request into tasks, then spawn workers against the plan.

Frequently Asked Questions about dispatch

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

FAQPage Schema
How do I coordinate tasks across parallel agents with explicit dependencies?▼

You coordinate parallel agents by using a shared task ledger that tracks task primitives, ownership, and blockers. This approach decomposes requests into 3-10 tasks and spawns workers against the plan to manage execution.

What is a shared task ledger for multi-agent workflow coordination?▼

A shared task ledger is a portable protocol structure that tracks task primitives, dependencies, and worker ownership. It enables runtime-agnostic coordination by recording progress and enabling safe recovery after failures.

Can I use this workflow coordination adapter with native task systems or manual boards?▼

Yes, the adapter-aware runtime support includes hooks for archiving progress and enabling recovery. It adapts to native task systems, shared workspaces, or manual boards to fit your existing environment.

What is the best way to break down large feature work for parallel execution?▼

The best way is decomposing the request into 3-10 tasks with explicit blockers and ownership. You then spawn workers against the plan using the shared ledger to monitor progress and manage dependencies.

How does dependency tracking handle recovery when a parallel worker fails?▼

Dependency tracking handles recovery through adapter hooks that archive progress within the shared ledger. This allows the system to safely resume or reassign tasks from the last recorded state after a failure.

Do I need a specific runtime to support multi-agent task decomposition?▼

No specific runtime is required because the workflow is runtime-agnostic. It uses a portable protocol with adapters that support various runtimes, allowing you to coordinate tasks across different execution environments.

Related Skills

Explore More Software Engineering Skills→
parcadeiparcadei
3.9k

onboard

Analyze a brownfield codebase and create a continuity ledger.

Community
Advanced
MatrixFounderMatrixFounder
4

skill-parallel-orchestration

Orchestrate parallel execution of decomposed tasks by spawning asynchronous sub-agents.

Community
Intermediate
mupengi-botmupengi-bot
11

mupeng-collab

Coordinate multi-agent projects with shared workspaces, progress tracking, and conflict detection.

Community
Advanced
thanhquan3010thanhquan3010

orchestrator

Plan and coordinate multi-agent tasks with parallel worker agents.

Community
Advanced