agent-queen-coordinator

Agent skill for queen-coordinator - invoke with $agent-queen-coordinator

2.93x

Quality

—

Does it follow best practices?

Impact

97%

2.93x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

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

The body is a themed orchestration skill with concrete memory-store examples and reasonable section organization, but it is padded with decorative language, lacks real control-flow/retrieval logic, and omits validation checkpoints for its coordinated operations.

Suggestions

Trim ceremonial prose (sovereign/royal/hive-loyalty framing) and reduce the verbose mock-JSON status blobs to minimal representative examples to improve token efficiency.

Add the missing half of the control flow — show how to retrieve and act on stored directives/health, including validation and error-recovery feedback loops for risky swarm operations, to lift workflow_clarity and actionability.

Split the API/command detail (governance modes, delegation patterns, integration points) into a one-level-deep reference file referenced from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly code, but it is padded with ceremonial prose ("sovereign presence", "royal decrees", "hive loyalty") and verbose inline JSON blobs of mock status data that could be tightened; it is not a score-3 lean example nor a score-1 concept-explaining wall of text.	2 / 3
Actionability	It provides concrete mcp__claude-flow__memory_usage store calls with keys and values, but these only write mock status/directive data — no retrieval, branching, or real orchestration logic is shown, leaving the guidance incomplete rather than copy-paste-ready executable control flow.	2 / 3
Workflow Clarity	Responsibilities and a high-level "issue → monitor → evaluate" protocol are listed, but there are no explicit validation checkpoints or error-recovery feedback loops for risky coordinated swarm operations, capping this at 2 per the rubric's batch-operation guidance.	2 / 3
Progressive Disclosure	Content is a single ~150-line monolithic SKILL.md with all material inline and no bundle/reference files to split into; sections are somewhat organized but there is no one-level-deep reference structure to reward a 3.	2 / 3
	Total	8 / 12 Passed

Description

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

The description is a placeholder-style invocation label that conveys nothing about the skill's capabilities or when to use it. It fails every dimension by stating only that the skill exists.

Suggestions

Rewrite the description in third person to name concrete actions, e.g. "Orchestrates hierarchical multi-agent swarm operations: allocates resources, issues directives, and monitors hive coherence via shared memory."

Add an explicit "Use when..." clause listing natural trigger terms users would say (e.g. coordinating multiple agents, swarm orchestration, allocating agent tasks).

Drop the boilerplate "Agent skill for ... - invoke with $..." framing, which adds no information and wastes the description budget.

Dimension	Reasoning	Score
Specificity	The phrase "Agent skill for queen-coordinator" names only the skill's domain and states it is a skill; it lists no concrete actions whatsoever, matching the score-1 anchor of vague/abstract language with no actions.	1 / 3
Completeness	It answers neither "what does this do" nor "when should Claude use it" — there is no capability description and no "Use when..." clause, so both required elements are missing.	1 / 3
Trigger Term Quality	"invoke with $agent-queen-coordinator" is a technical invocation token rather than natural language a user would say, and no natural trigger keywords are present.	1 / 3
Distinctiveness Conflict Risk	The generic "Agent skill for X - invoke with $X" framing provides no distinguishing triggers beyond the name and would not differentiate this skill from any other agent skill.	1 / 3
	Total	4 / 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: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 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.