agent-load-balancer

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

1.11x

Quality

27%

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

26%Weight 40%Scale 1-5

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

The body is an oversized catalog of generic scheduling-algorithm pseudocode rather than an actionable skill: it duplicates frontmatter, inlines material that belongs in reference files, and offers no sequenced workflow or validation. A user would gain little executable guidance from it.

Suggestions

Replace the algorithm catalog with a sequenced workflow (collect metrics -> detect imbalance -> migrate tasks -> verify distribution) with explicit validation checkpoints before and after task migration.

Move the full algorithm implementations (EDF, CFS, circuit breaker, genetic allocator) into reference files and keep only a lean overview with one-level-deep links in SKILL.md.

Make code executable or trim it: either define the assumed PriorityQueue/RedBlackTree/mcp dependencies or cut the snippets to the minimal working core, and remove the duplicated frontmatter block and Agent Profile padding.

Dimension	Reasoning	Score
Conciseness	The ~435-line body re-implements standard algorithms Claude already knows (work-stealing, EDF, CFS, circuit breaker, WFQ) and pads with an 'Agent Profile' bullet list, KPI lists, and a stray duplicated frontmatter block. This is 'noticeably verbose; several unnecessary explanations or padded sections' — not 1, since the code sections are not didactic prose explaining basics, but well below 3.	2 / 5
Actionability	The JavaScript snippets are not executable — they depend on undefined PriorityQueue, RedBlackTree, ConstraintSolver, WeightedRoundRobinQueue, and an undefined mcp object — matching 'pseudocode instead of executable code; missing key details'. The npx claude-flow commands are concrete, lifting it above 2, but unverifiable flags and placeholders keep it below 4.	3 / 5
Workflow Clarity	The body is a capability catalog with no step sequence anywhere — nothing tells the agent what to do first, next, or how to verify results, and no validation checkpoints exist for the batch task-migration operations it describes. This matches 'Steps missing or incoherent; no sequence; no validation'.	1 / 5
Progressive Disclosure	Section headers exist (so not an unstructured monolith), but 400+ lines of full algorithm implementations that clearly belong in separate reference files are inlined, and no references/, scripts/, or assets/ files exist to offload them. 'Minimal structure; content that clearly belongs in separate files is inlined' is the best fit.	2 / 5
	Total	8 / 20 Passed

Description

28%Weight 40%Scale 1-5

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 stub: it identifies the skill's domain and how to invoke it, but tells neither what it concretely does nor when it should be used. It would rarely be selected by a user's natural request and reads as auto-generated boilerplate.

Suggestions

Rewrite the description in third person to list concrete actions, e.g. 'Distributes tasks across agents using work-stealing, monitors agent load, and rebalances overloaded swarms'.

Add an explicit trigger clause: 'Use when load is unevenly distributed across agents, when tasks queue behind idle workers, or when the user mentions load balancing or work stealing'.

Include natural trigger terms and synonyms ("load balancing", "balance load", "distribute tasks", "work stealing") instead of only the hyphenated internal skill name.

Dimension	Reasoning	Score
Specificity	"Agent skill for load-balancer" names the domain but lists no concrete actions whatsoever, matching the anchor 'Names the domain but actions are minimal or generic'. It is above 1 because the domain itself is specific rather than entirely vague, but below 3 because no action (like 'distribute tasks' or 'monitor agent load') is stated.	2 / 5
Completeness	The 'what' is vague ("Agent skill for load-balancer") and the 'when' is completely missing — no 'Use when...' clause or equivalent. This is exactly anchor 2; it cannot be 3 because the 'what' itself is only weakly implied, and the missing trigger clause caps completeness at 3 anyway.	2 / 5
Trigger Term Quality	The only keyword is the hyphenated technical name "load-balancer"; natural phrases a user would actually say ("load balancing", "balance the load", "distribute tasks across agents") and synonyms are absent. This fits 'one or two generic keywords; missing the natural phrases users say' rather than 3, which requires the relevant natural keyword to be present.	2 / 5
Distinctiveness Conflict Risk	Load balancing is a fairly specific niche, so it is distinguishable from unrelated skills, but the description provides no distinct triggers and could overlap with other agent/swarm coordination or performance-optimization skills. 'Somewhat specific but could still overlap with similar skills' is the best fit — not 4, since nothing in the description distinguishes it from sibling optimization agents.	3 / 5
	Total	9 / 20 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: b14c79e

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.