agent-matrix-optimizer

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

1.40x

Quality

28%

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

Quality

Content

50%Weight 40%Scale 1-3

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 well-sectioned but verbose agent prompt centered on three solid MCP code examples, weakened by redundant capability marketing, an incomplete sandbox example, and no progressive disclosure to separate reference files. Workflows lack validation checkpoints.

Suggestions

Trim the redundant capability bullet lists (Core Capabilities / Advanced Features / Best Practices / Example Workflows overlap heavily) and keep only the concrete MCP tool-call examples and essential guidance.

Make the Flow Nexus sandbox example fully executable by defining or importing create_diagonally_dominant_matrix, analyze_matrix_properties, and os, or label it explicitly as illustrative pseudocode.

Add explicit validation/verification checkpoints to the matrix-optimization pipeline (e.g., verify diagonal dominance and condition number before solving, validate solver convergence), and move detailed API/integration material into referenced files like REFERENCE.md once bundle files are added.

Dimension	Reasoning	Score
Conciseness	The body contains useful MCP code examples but is padded with redundant, marketing-style capability bullets repeated across 'Core Capabilities', 'Advanced Features', 'Best Practices', and 'Example Workflows' that could be cut.	2 / 3
Actionability	Three concrete, copy-pasteable MCP tool-call examples (analyzeMatrix, solve, estimateEntry) are actionable, but the Flow Nexus sandbox example uses undefined helper functions (create_diagonally_dominant_matrix, analyze_matrix_properties) and large portions are vague capability descriptions.	2 / 3
Workflow Clarity	A 5-phase pipeline and numbered best practices provide a sequence, but there are no explicit validation checkpoints or validate-fix-retry feedback loops for large-scale solve operations.	2 / 3
Progressive Disclosure	The ~180-line document is monolithic with clear section headers but no external reference files and no signaled navigation; content such as advanced features, integration details, and examples that should be split out is all inline.	2 / 3
	Total	8 / 12 Passed

Description

7%Weight 40%Scale 1-3

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 terse auto-generated string that names the skill's niche but states no concrete capabilities and offers no usage triggers. It fails to tell a user or Claude when to invoke it or what it concretely does.

Suggestions

Replace the description with concrete actions, e.g. 'Analyze matrix properties (diagonal dominance, condition number, spectral gap), recommend preprocessing, and solve large linear systems with sublinear solvers.'

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

Use natural user-facing terms ('matrix analysis', 'condition number', 'linear system solver') instead of the bare invocation token '$agent-matrix-optimizer'.

Dimension	Reasoning	Score
Specificity	The phrase 'Agent skill for matrix-optimizer' names a domain but lists no concrete actions, matching the vague 'Helps with documents' anchor rather than the multi-action score-3 examples.	1 / 3
Completeness	It gives only a weak 'what' ('Agent skill for matrix-optimizer') and entirely omits any 'Use when...' trigger guidance, so both what and when are weak or missing.	1 / 3
Trigger Term Quality	'matrix-optimizer' and '$agent-matrix-optimizer' are the skill's own name and invocation token, not natural phrases a user would say; no common user terms appear.	1 / 3
Distinctiveness Conflict Risk	It names a specific niche (matrix optimization) that is unlikely to conflict with unrelated skills, but the terse description provides no distinct triggers, so it could overlap with similar math/optimization skills.	2 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-matrix-optimizer/SKILL.md
Commit: 913f9ea

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.