agent-queen-coordinator
Agent skill for queen-coordinator - invoke with $agent-queen-coordinator
40
7%
Does it follow best practices?
Impact
97%
2.93xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-queen-coordinator/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a placeholder that provides no useful information about the skill's purpose, capabilities, or when it should be used. It only contains an invocation command, which is insufficient for Claude to make any informed selection decision among multiple skills.
Suggestions
Add a clear statement of what the skill does with specific concrete actions (e.g., 'Coordinates parallel sub-agents to divide and execute complex multi-step tasks').
Add an explicit 'Use when...' clause with natural trigger terms describing the situations where this skill should be selected.
Replace the internal name 'queen-coordinator' with a meaningful description of the domain or workflow this skill addresses to improve distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for queen-coordinator' is entirely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states the invocation command without explaining purpose or trigger conditions. | 1 / 3 |
Trigger Term Quality | No natural keywords a user would say are present. 'queen-coordinator' is internal jargon, and 'invoke with $agent-queen-coordinator' is a technical invocation instruction, not a trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it provides no distinguishing characteristics. Without knowing what the skill does, it could conflict with anything or nothing—Claude has no basis for selection. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily over-themed with 'queen/hive/royal' metaphors that add significant token overhead without improving clarity. While it demonstrates the MCP memory tool call pattern, the actual operational guidance is shallow—most sections are either repetitive store operations or vague bullet lists. Critical coordination concerns like error recovery, agent failure handling, and actual decision-making logic are absent or listed as bullet points without implementation.
Suggestions
Strip all roleplay/thematic language ('sovereign', 'royal decrees', 'coup prevention', 'morale') and replace with direct operational instructions that describe what the coordinator actually does.
Add concrete workflow sequences with validation: e.g., after issuing a directive, how to check agent compliance, what to do if an agent doesn't respond, and how to reassign work.
Consolidate the repetitive mcp__claude-flow__memory_usage blocks into a single pattern/template with a table of key names and their purposes, rather than showing 5+ nearly identical code blocks.
Extract delegation patterns and emergency protocols into separate reference files, keeping SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive roleplay framing ('sovereign intelligence', 'royal decrees', 'coup prevention'). Much of the content is thematic fluff that adds no actionable value. The code blocks are repetitive memory store operations that could be condensed significantly. Claude doesn't need to be told about 'hive loyalty' or 'morale: high'. | 1 / 3 |
Actionability | The code blocks show concrete MCP tool calls with specific JSON structures, which is somewhat actionable. However, the code is presented as JavaScript comments rather than actual executable tool invocations, many sections are just bullet-point lists without concrete implementation (e.g., 'Emergency Protocols' lists concepts with no actual steps), and hardcoded placeholder values like 'coherence_score: 0.95' aren't meaningful. | 2 / 3 |
Workflow Clarity | Despite being a coordination skill involving multi-step processes, there are no clear sequential workflows with validation checkpoints. The 'Command Protocols' section lists abstract 3-step patterns without concrete implementation. There's no error handling, no validation of whether directives were received, and no feedback loops for when agents are non-responsive. | 1 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being complex enough to warrant them. All content is inline including resource allocation tables, delegation patterns, and emergency protocols. No navigation structure or cross-references to related agent skills. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/ruflo
- Commit
398f7c2
- Reviewed
Table of Contents
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.