agent-orchestration

agent-orchestration is an Agent task delegation & fan-out skill for AI agents, published by mauricekleine in the mauricekleine.com repository on GitHub. Skillspace rates agent-orchestration D (59/100) and it passed the safety scan; the rating is based on static analysis only.

Doctrine for acting as the orchestrator-and-reviewer over a fleet of sub-agents instead of doing all the work yourself: decompose a job into independent slices, delegate each to a sub-agent in an isolated git worktree that opens a PR, review the diffs (adversarially on anything touching prod), relay feedback until clean, and merge one at a time. Reach for this whenever a task is big enough to split into parallel pieces, involves coordinating several sub-agents or worktrees, fanning work out and reviewing/merging PRs, running a backfill or migration across many items, validating one case before fanning out, de-risking a big change with a spike, or any multi-step build where you should hold the overview while sub-agents execute — even if the user never says the word "orchestrate."

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
23

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.