agent-v3-queen-coordinator

Agent skill for v3-queen-coordinator - invoke with $agent-v3-queen-coordinator

6.25x

Quality

—

Does it follow best practices?

Impact

100%

6.25x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

20%

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

The body reads as a project vision document rather than an actionable skill: it is padded with over-claimed metrics, timelines, and a redundant config blob, and provides no executable instructions or validation-backed workflow. Only its clean sectioning and self-contained structure keep it above the floor on workflow clarity and progressive disclosure.

Suggestions

Replace the aspirational metrics and 14-week phase schedule with concrete, executable instructions or commands Claude can run to perform the coordination task.

Move the inline YAML hooks/config block into a separate referenced file or a clearly delimited config section so the overview stays lean.

Add validation checkpoints or feedback loops (e.g., verify agent handoff status before proceeding) to any multi-step coordination workflow, and relocate version/date-sensitive details to a deprecated or changelog section.

Dimension	Reasoning	Score
Conciseness	The body is padded with aspirational project-management content (performance targets like '2.49x-7.47x', a 14-week timeline, emoji headers, an ASCII topology diagram) and a redundant inline YAML config blob, plus time-sensitive version/date info ('3.0.0-alpha', '2026-01-04') outside any deprecated section.	1 / 3
Actionability	There is no executable guidance for accomplishing the skill's purpose; the only runnable code is bash hook boilerplate inside the YAML blob, while the phases merely assign work ('Agent #7: Memory unification') rather than instructing Claude how to do anything.	1 / 3
Workflow Clarity	The 'Implementation Phases' section provides a sequenced plan (Phase 1-4 across 14 weeks), but it is a project schedule rather than an operational workflow and lacks any validation checkpoints or feedback loops.	2 / 3
Progressive Disclosure	Content is self-contained with clear sections and no nested references, but the inline YAML hooks/config block is content that could live in a separate file and is not clearly signaled as separable, keeping organization short of a 3.	2 / 3
	Total	6 / 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 circular, templated label that fails to communicate any capability or usage trigger, relying on an internal invocation token instead of natural language. It scores at the floor on specificity, triggers, and completeness, with only the distinctive internal name lifting conflict risk slightly.

Suggestions

Replace the circular phrasing with concrete actions the skill performs (e.g., 'Orchestrates a 15-agent swarm, assigns GitHub issues, and coordinates cross-agent handoffs').

Add an explicit 'Use when...' clause naming natural triggers a user would say (e.g., 'Use when coordinating multi-agent work, distributing issues across agents, or managing swarm handoffs').

Drop the internal invocation syntax '$agent-v3-queen-coordinator' from the description and describe the skill in third-person capability terms instead.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for v3-queen-coordinator - invoke with $agent-v3-queen-coordinator' names a domain but states no concrete actions, only circularly referring to itself; it does not reach the 'names domain and some actions' bar of a 2.	1 / 3
Completeness	It answers neither 'what does this do' (the capability is undefined, only 'agent skill for X') nor 'when should Claude use it' (no 'Use when...' clause or equivalent trigger guidance).	1 / 3
Trigger Term Quality	The only terms are the internal token 'v3-queen-coordinator' and the invocation syntax '$agent-v3-queen-coordinator', which are technical jargon a user would not naturally say rather than natural trigger keywords.	1 / 3
Distinctiveness Conflict Risk	The specific internal name 'v3-queen-coordinator' gives it a niche identity that limits accidental triggering, but the templated 'Agent skill for X - invoke with $X' form offers no functional distinction and could overlap with similarly-named skills.	2 / 3
	Total	5 / 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.