agent-orchestration

AI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate dependencies, relay outputs, resolve conflicts, and verify completion. Use only for ongoing multi-agent coordination, not one-off list/detail/send/start/kill actions.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exceptionally tight, well-structured instruction skill: a clear supervised loop, concrete commands, explicit verification checkpoints, and clean sectioning with no wasted tokens. It is a model for instruction-only skills.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept padding; directives like "Run `agent list --json` before each pass; never assume names/statuses" assume Claude's competence and earn every token.	3 / 3
Actionability	Provides concrete executable commands (`agent list --json`, `detail --tail 10`) and specific sibling-skill redirects ($agent-management, $agent-communication, $verify); per scoring notes, absence of code in this instruction-only skill is not penalized since the guidance is actionable.	3 / 3
Workflow Clarity	The Loop is an explicitly numbered sequence (Scan → Assess → Act → Report → Sleep → repeat) with validation checkpoints (`agent list --json` each pass, `$verify` before accepting completion) and an escalation feedback path for repeated failures.	3 / 3
Progressive Disclosure	Under 50 lines with no external bundle files needed; content is cleanly split into Rules, Loop, and Completion sections with one-level sibling-skill references, satisfying the simple-skill exception.	3 / 3
	Total	12 / 12 Passed

Description

85%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly defines a niche and gives explicit when-to-use guidance. Its only weakness is trigger-term naturalness — much of the vocabulary is tool-internal phrasing rather than language a user would naturally say.

Suggestions

Add a few natural user-facing trigger phrases (e.g. "Use when the user asks to coordinate multiple agents" or "keep several agents running in sync") alongside the technical terms.

Soften internal jargon like "repeated passes" and "relay outputs" toward phrasings a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "poll progress, unblock waiting agents, coordinate dependencies, relay outputs, resolve conflicts, and verify completion" — matching the top anchor rather than the single-domain level 2.	3 / 3
Completeness	Explicitly answers what it does (supervise multi-agent workflows through completion) and when to use it ("Use only for ongoing multi-agent coordination, not one-off list/detail/send/start/kill actions"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes relevant terms ("multi-agent workflows", "multi-agent coordination", "agents") but the phrasing leans technical/internal ("repeated passes", "unblock waiting agents", "relay outputs") rather than natural user speech, so it stops short of full natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	Has a clear niche (ongoing multi-agent supervision) and is explicitly distinguished from one-off actions plus points to sibling skills, making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: codeaholicguy/ai-devkit
Path: skills/agent-orchestration/SKILL.md
Commit: 15b09d2

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.