agent-resource-allocator

Agent skill for resource-allocator - invoke with $agent-resource-allocator

5.00x

Quality

26%

Does it follow best practices?

Impact

80%

5.00x

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-resource-allocator/SKILL.md

Quality

Content

35%

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 over-long catalog of non-executable JavaScript class scaffolding interspersed with explanations of familiar ML concepts, organized into sections but lacking any real workflow with validation checkpoints. It would benefit dramatically from trimming, executable examples, and splitting detail into referenced files.

Suggestions

Cut the conceptual padding and reduce each capability to a short overview plus one minimal, executable example instead of full class definitions relying on undefined helpers.

Provide a clear sequenced workflow (analyze -> allocate -> validate -> scale) with explicit validation checkpoints for swarm scaling and other batch operations.

Move the lengthy class implementations and KPI definitions into separate referenced files (e.g. references/ALLOCATOR.md, references/METRICS.md) and keep SKILL.md as a concise overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The ~660-line body is padded with large class definitions and explains ML/optimization concepts Claude already knows (genetic algorithms, Pareto fronts, LSTM, reinforcement learning, DQN), matching 'verbose; explains concepts Claude knows; padded with unnecessary context.'	1 / 3
Actionability	The Operational Commands section offers somewhat concrete `npx claude-flow` invocations, but the bulk of the JavaScript depends on undefined classes and `mcp.`/`this.` methods, making it non-executable scaffolding rather than copy-paste code, matching 'some concrete guidance but incomplete; pseudocode instead of executable code.'	2 / 3
Workflow Clarity	Content is organized into capability sections but presents no sequenced multi-step process and no validation/checkpoint steps for risky batch operations like swarm scaling, matching 'sequence present but checkpoints missing or implicit' rather than the explicit-feedback-loop level.	2 / 3
Progressive Disclosure	The file has section structure but crams extensive implementation detail inline with no references to separate files (no bundle files exist), matching 'content that should be separate is inline' with structure that could be better organized.	2 / 3
	Total	7 / 12 Passed

Description

17%

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 thin, template-like invocation hint that names the domain but states no concrete capabilities and provides no natural trigger terms or 'when to use' guidance. It risks poor discoverability and weak distinction from sibling optimization agents.

Suggestions

Replace the generic framing with concrete capabilities, e.g. 'Adaptively allocates CPU, memory, and agent resources across a swarm and predicts scaling needs.'

Add an explicit 'Use when...' trigger clause using natural terms users would say, such as 'when the user needs to scale a swarm, balance resources, or plan capacity.'

Drop the technical '$agent-resource-allocator' invocation syntax from the description and surface natural keywords (resource allocation, predictive scaling, capacity planning).

Dimension	Reasoning	Score
Specificity	The description names a domain ("resource-allocator") but only implies an action via the noun and an invocation hint; it does not list concrete capabilities, so it matches 'names domain and some actions, but not comprehensive' rather than the multiple-specific-actions level.	2 / 3
Completeness	It gives a weak 'what' ('Agent skill for resource-allocator') and entirely omits any 'when to use' guidance, matching 'missing what OR when, or both very weak'; the missing 'Use when...' clause also caps completeness at 2 per guidelines.	1 / 3
Trigger Term Quality	The only trigger-like phrase is the technical invocation syntax "invoke with $agent-resource-allocator", which is not a natural keyword a user would say, matching 'no natural keywords; technical jargon or overly generic.'	1 / 3
Distinctiveness Conflict Risk	'resource-allocator' provides a somewhat specific niche, but the generic 'Agent skill for...' framing could still overlap with other optimization/scaling agents, matching 'somewhat specific but could still overlap with similar skills.'	2 / 3
	Total	6 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (679 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-resource-allocator/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.