agentsclimarketplace
Sign in

Subagent orchestration

Skill bg-szy/TOP-SKILLS/skills/marketplace/subagent-orchestration

This skill should be used when coordinating multiple subagents, implementing orchestrator patterns, or managing parallel agent workflows. Trigger phrases: "orchestrate agents", "coordinate subagents", "parallel agents", "multi-agent workflow", "delegate to agents", "run agents in parallel", "launch multiple agents".From its SKILL.md

Install
npx -y skills add bg-szy/TOP-SKILLS --skill subagent-orchestration

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.1 KB, 387 tokens by cl100k_base, as published. Nobody here has run it

Orchestrating Subagents

Core Principles

  • Always suggest subagent invocation when task matches their expertise
  • User has final decision on invocation
  • Prefer multiple parallel invocations for independent tasks with strict scopes
  • ALWAYS define: files to modify, files NOT to touch, specific task boundaries

When to Use Parallel Invocation

Invoke multiple subagents in a single message when:

  • Tasks are completely independent
  • Each task has strict, non-overlapping scope
  • No task depends on another's results

Examples:

  • ✓ "Explore authentication flow" + "Review recent auth changes" (parallel)
  • ✗ "Explore auth flow then refactor based on findings" (sequential - second depends on first)

Scope Definition Template

When proposing subagent invocation, use this structure:

Task: [Clear, single-sentence description]

Files to modify: [Explicit list with paths]

Files NOT to touch: [Explicit exclusions - be specific]

Constraints: 
- [Business rules to follow]
- [Patterns to maintain]
- [Technical requirements]

Reference docs: [@AGENTS.md, @docs/architecture.md, etc.]

Decision Framework

Before suggesting subagents, verify:

  1. Is the scope clearly bounded? Can you define exact files and boundaries?
  2. Is it independent? Does it require results from another task first?
  3. Is it delegable? Would a subagent have enough context?

If any answer is "no", handle the task directly or break it down further.

Anti-patterns to Avoid

  • Vague file specifications ("update related files")
  • Missing exclusions (failing to specify what NOT to touch)
  • Sequential tasks disguised as parallel (one depends on the other)
  • Unbounded scopes ("refactor the codebase")
  • Missing context references (no @file references for subagent to read)

What ships with it: 2 files

16.7 KB alongside SKILL.md

Keep looking

Skills are one crate of 625,857. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.