skills.rest
yersonargotev
yersonargotevCOMMUNITY
Explore all skills by this author →
GitHub

orchestrate

Coordinates multiple agents on large-scope tasks with parallel delegation.

1|Updated Jul 5, 2026
Search Tags:#parallel agents#delegation#multi-agent#orchestration#task coordination#reasoning effort
One-click install
npx skills add https://github.com/yersonargotev/packy --skill orchestrate-yersonargotev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: orchestrate
Source: https://github.com/yersonargotev/packy/tree/main/bundle/skills/orchestrate
Command: npx skills add https://github.com/yersonargotev/packy --skill orchestrate-yersonargotev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Large-scope tasks overwhelm a single agent, leading to slow progress, tangled context, and missed details. This Skill breaks substantial work into focused assignments and coordinates multiple agents so the user stays in control while work proceeds in parallel. ## Core Features & Use Cases - Parallel scouting: Runs narrow, read-only scout agents concurrently with low reasoning effort to gather information quickly. - Tiered reasoning effort: Assigns medium effort to routine implementation and high effort to difficult work, matching cost to complexity. - Clear ownership boundaries: Gives each agent distinct, non-overlapping assignments and prevents leaf workers from delegating further. - Use Case: When refactoring a large codebase across multiple modules, use this Skill to dispatch focused agents per module, then integrate their results while keeping final approvals with the user. ## Quick Start Use the orchestrate skill to split this large task across focused agents and coordinate their work.

Frequently Asked Questions about orchestrate

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

FAQPage Schema
How do I coordinate multiple AI agents on a large task?▼

Delegate substantive work to focused agents with distinct, non-overlapping ownership. Run narrow read-only scouts in parallel with low reasoning effort, then integrate their results while keeping final approvals with the user.

When should I use multi-agent orchestration instead of a single agent?▼

Use orchestration whenever the work is substantial and spans multiple independent areas. Trivial or single-focus tasks do not require this skill and are handled faster by one agent directly.

What reasoning effort should each delegated agent use?▼

Use low reasoning effort for narrow read-only scouts, medium for routine implementation, and high for difficult work. Matching effort to task difficulty balances speed and quality.

How do I prevent agents from duplicating each other's work?▼

Give each agent distinct ownership with non-overlapping assignments before dispatching. Instruct leaf workers not to delegate further, so responsibility stays flat and traceable.

Who approves the final results from delegated agents?▼

Approvals stay with the user. The orchestrator integrates agent results and remains available to the user, but does not approve changes autonomously.

Related Skills

Explore More Software Engineering Skills→
cablatecablate
66

baton-dispatch

Govern multi-agent task delegation with dispatch brakes and centralized verification.

Community
Advanced
arpitnatharpitnath
86

code-review

Automate pre-commit code reviews with structured feedback and blocking commits.

Community
Advanced
MatiasComercioMatiasComercio
31

agent-orchestrator-manager

Delegate tasks to spawned subagents and track progress in UUID-based output directories.

Community
Advanced
CasaPerksCasaPerks

sdd

Execute implementation plan tasks via isolated subagents with spec-first review.

Official
Advanced