agent-load-balancer

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

1.11x

Quality

25%

Does it follow best practices?

Impact

96%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-load-balancer/SKILL.md

Quality

Content

27%

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 monolithic, verbose catalog of algorithm illustrations rather than lean, executable guidance: it explains concepts Claude already knows and relies on undefined dependencies. It lacks a clear sequenced workflow with validation and makes no use of progressive disclosure.

Suggestions

Cut the tutorial-style explanations of known algorithms (EDF, CFS, circuit breakers) and keep only the load-balancing specifics Claude would not infer.

Replace pseudocode built on undefined classes/objects with minimal executable examples or clearly justify the abstraction, and verify the `claude-flow` commands actually exist.

Add a short numbered workflow with explicit validation checkpoints (e.g. monitor metrics -> detect imbalance -> migrate -> re-verify) instead of presenting a flat capability catalog.

Dimension	Reasoning	Score
Conciseness	The ~430-line body is padded with illustrative implementations of concepts Claude already knows (work-stealing, EDF, CFS, circuit breakers) and restates well-known algorithms, matching the verbose/padded level-1 anchor.	1 / 3
Actionability	Concrete commands and detailed code structures are present, but the JavaScript relies on undefined constructs (PriorityQueue, RedBlackTree, ConstraintSolver, a global `mcp` object) and the `claude-flow` CLI calls are unverifiable, so it is guidance rather than copy-paste-executable code.	2 / 3
Workflow Clarity	The "Operational Commands" section loosely sequences spawn/start/monitor/adjust steps, but there are no validation checkpoints or error-recovery feedback loops, fitting the level-2 anchor of sequence-without-checkpoints.	2 / 3
Progressive Disclosure	With no bundle files present, the entire catalog of algorithms and code lives inline as a monolithic wall of text with no one-level-deep references or navigation to separate materials.	1 / 3
	Total	6 / 12 Passed

Description

22%

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 too vague to function as effective trigger guidance: it names the domain without concrete capabilities and omits any "Use when..." clause. It reads as an invocation hint rather than a capability-and-trigger statement.

Suggestions

Rewrite the description to list concrete actions, e.g. "Distributes tasks across agents, implements work-stealing, and rebalances overloaded queues."

Add an explicit trigger clause such as "Use when coordinating multi-agent workloads, balancing task queues, or relieving overloaded agents."

Replace the invocation syntax ("invoke with $agent-load-balancer") with natural user-facing keywords so the description triggers on what users actually say.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for load-balancer - invoke with $agent-load-balancer" names only a vague domain and no concrete actions, matching the "Helps with documents" anchor rather than the level-2 example that names specific operations.	1 / 3
Completeness	The "what" is only weakly stated ("Agent skill for load-balancer") and there is no "Use when..." clause or equivalent trigger guidance, so both what and when are weak/missing per the level-1 anchor.	1 / 3
Trigger Term Quality	"load-balancer" is a relevant keyword a user might say, but the rest is invocation syntax ("invoke with $agent-load-balancer") rather than natural triggers, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	Load-balancing is a recognizable niche, but the generic phrasing could overlap with other optimization/coordination agents rather than carving a clearly distinct trigger space.	2 / 3
	Total	6 / 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/ruflo
Path: .agents/skills/agent-load-balancer/SKILL.md
Commit: 26c35b5

Reviewed: about 6 hours 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.