Name: agent-matrix-optimizer
Rating: 60.6 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-matrix-optimizer

Agent skill for matrix-optimizer - invoke with $agent-matrix-optimizer

1.40x

Quality

43%

Does it follow best practices?

Impact

87%

1.40x

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-matrix-optimizer/SKILL.md

The canonical home for this skill is agent-matrix-optimizer in ruvnet/claude-flow

Quality

Content

57%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 content is a moderately actionable agent definition with concrete MCP tool examples and clear sectioning, but it is padded with generic capability lists, lacks validation checkpoints in its workflow, and is monolithic with no progressive disclosure to supporting files.

Suggestions

Trim generic bullet sections ('Neural Network Integration', 'Best Practices', 'Advanced Features') to only capabilities with concrete tool calls, reducing token cost.

Add an explicit validation/verification step to the Example Workflows pipeline (e.g. validateTemporalAdvantage or a result-check) with a fix-and-retry loop, since large-scale solving is a batch operation.

Make the Flow Nexus sandbox example executable by defining or removing the placeholder helpers (create_diagonally_dominant_matrix, analyze_matrix_properties).

Dimension	Reasoning	Score
Conciseness	The body provides concrete MCP code examples but is padded with generic capability bullet lists ('Performance Monitoring', 'Neural Network Integration', 'Best Practices') that add little actionable value, matching 'mostly efficient but includes some unnecessary explanation or could be tightened'; not a 2 because the core examples are useful rather than purely verbose.	3 / 5
Actionability	Three usage scenarios give concrete JavaScript calling the MCP tools with real parameters (analyzeMatrix, solve, estimateEntry), which is mostly copy-paste ready; minor gaps exist such as undefined helpers (create_diagonally_dominant_matrix, analyze_matrix_properties) in the Flow Nexus sandbox example, keeping it just below fully executable.	4 / 5
Workflow Clarity	A 5-phase pipeline (Analysis, Preprocessing, Solving, Validation, Optimization) is listed, but the phases are high-level labels with no explicit validation commands or error-recovery feedback loops for large-scale/batch matrix operations, which the rubric caps at 3.	3 / 5
Progressive Disclosure	The ~190-line body is well-sectioned with headers but is a single monolithic file with all capability lists and code inlined and no external references; the simple-skill exception does not apply given its length, so it lands at 'some structure but could be better organized.'	3 / 5
	Total	13 / 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 frontmatter description is a thin, template-like placeholder that names the domain but provides no concrete capabilities or natural use-when triggers, capping completeness and trigger quality low. It is distinguishable only by virtue of its specialized niche, not by what it says.

Suggestions

Replace the placeholder with concrete actions, e.g. 'Analyzes matrix properties (diagonal dominance, condition number, spectral gap) and recommends preprocessing for sublinear solvers.'

Add an explicit 'Use when...' clause with natural user phrasing such as 'Use when you need to analyze matrix properties, estimate condition numbers, or prepare matrices for sublinear solvers.'

Drop the invocation-syntax phrasing ('invoke with $agent-matrix-optimizer') in favor of third-person capability language users would actually say.

Dimension	Reasoning	Score
Specificity	The description names the domain ('matrix-optimizer') but states no concrete actions, only 'Agent skill for matrix-optimizer - invoke with $agent-matrix-optimizer', matching the 'names the domain but actions are minimal or generic' anchor; it is not a 1 because a specific domain is named, and not a 3 because no concrete capabilities are listed.	2 / 5
Completeness	It offers only a vague 'what' ('Agent skill for matrix-optimizer') with no 'when to use' guidance at all, matching the 'vague what and no when' anchor and below 3 where a clear what is present.	2 / 5
Trigger Term Quality	It contains one domain keyword ('matrix-optimizer') but the only phrasing is invocation syntax ('invoke with $agent-matrix-optimizer'), which a user would not naturally say; natural terms like 'analyze matrices' or 'condition number' are absent, so it sits just above the 'only technical jargon' anchor rather than at it.	2 / 5
Distinctiveness Conflict Risk	The 'matrix-optimizer' niche is reasonably specific, but the generic framing ('Agent skill for ...') and absence of explicit triggers leave overlap risk with other matrix/numerical skills, matching the 'somewhat specific but could still overlap' anchor.	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-matrix-optimizer/SKILL.md
Commit: fa13ee4

Reviewed: about 4 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.