agent-load-balancer

Agent skill for load-balancer - invoke with $agent-load-balancer

1.11x

Quality

Does it follow best practices?

Impact

96%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-load-balancer/SKILL.md

Quality

Discovery

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 critically deficient across all dimensions. It provides no concrete actions, no trigger terms, no 'when to use' guidance, and no distinguishing characteristics. It reads as a placeholder label rather than a functional skill description that Claude could use to select the right skill.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Configures load balancer rules, manages backend pools, monitors health checks, distributes traffic across servers.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about load balancing, traffic distribution, backend health checks, server pools, or routing configuration.'

Remove the invocation syntax ('invoke with $agent-load-balancer') from the description and replace it with domain-specific keywords that help Claude distinguish this skill from other infrastructure or networking skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for load-balancer' is entirely vague and does not describe what the skill actually does—no verbs, no operations, no domain-specific capabilities.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause, no explanation of capabilities, and no explicit trigger guidance.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'load-balancer', but there are no natural user keywords like 'traffic distribution', 'routing', 'health checks', 'scaling', or any variations a user might naturally say. The invocation syntax '$agent-load-balancer' is not a natural trigger term.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides almost no distinguishing information. 'Agent skill for load-balancer' could overlap with networking, infrastructure, DevOps, or any number of related skills without any way to differentiate.	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 an extensive reference document of load balancing algorithms and patterns rather than an actionable skill for Claude. It suffers from extreme verbosity, explaining well-known CS concepts Claude already understands, while lacking a clear workflow for when and how to actually perform load balancing. The code examples reference undefined dependencies and fictional APIs, reducing practical actionability.

Suggestions

Reduce content to under 100 lines by removing well-known algorithm implementations (CFS, EDF, circuit breaker) and focusing only on project-specific configuration and invocation steps.

Add a clear sequential workflow: when to invoke the load balancer, what inputs it needs, how to validate results, and how to recover from failures.

Move detailed algorithm implementations and benchmarking code to separate reference files (e.g., ALGORITHMS.md, BENCHMARKS.md) and link to them from a concise overview.

Replace pseudocode-like examples that depend on undefined classes with either truly executable code or specific CLI commands that actually work with the claude-flow tool.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~350+ lines. Contains extensive code examples for well-known algorithms (work-stealing, CFS, EDF, circuit breaker) that Claude already knows. The 'Agent Profile' section, integration points descriptions, and concluding summary sentence are all unnecessary padding.	1 / 3
Actionability	The operational commands section provides concrete CLI commands, and code examples are syntactically complete. However, the code relies on undefined classes (PriorityQueue, RedBlackTree, ConstraintSolver, WeightedRoundRobinQueue) and fictional MCP methods, making it not truly executable or copy-paste ready.	2 / 3
Workflow Clarity	There is no clear multi-step workflow or sequenced process for actually using this agent. The content presents isolated code snippets and concepts without explaining when or how to invoke them in sequence, and there are no validation checkpoints or error recovery steps for load balancing operations.	1 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content—algorithms, MCP integration, scheduling, benchmarking, circuit breakers—is dumped inline with no navigation structure or separation into focused documents.	1 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Commit: ccb062f

Reviewed: 3 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.