agent-matrix-optimizer

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

1.40x

Quality

Does it follow best practices?

Impact

87%

1.40x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-matrix-optimizer/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an extremely weak description that essentially only provides an invocation command and a tool name. It fails on every dimension: no concrete actions, no trigger terms, no 'what' or 'when' guidance, and no distinguishing details. Claude would have virtually no basis for selecting this skill appropriately from a list of available skills.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Optimizes matrix operations, performs matrix multiplication, computes eigenvalues, solves linear systems.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs matrix computations, linear algebra operations, optimization of matrix expressions, or mentions matrices, eigenvalues, or linear systems.'

Remove the invocation instruction ('invoke with $agent-matrix-optimizer') from the description field, as it wastes space that should be used for capability and trigger information.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for matrix-optimizer' is entirely vague—it doesn't describe what the skill actually does, only names itself.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command, with no explanation of capabilities or usage triggers.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'matrix-optimizer', which is a tool name rather than a natural keyword a user would say. There are no natural language trigger terms like 'matrix', 'optimization', 'linear algebra', etc.	1 / 3
Distinctiveness Conflict Risk	While the tool name 'matrix-optimizer' is somewhat specific, the description is so vague that Claude cannot determine when to select it. It could conflict with any math, optimization, or data processing skill since no clear niche is defined.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill is excessively verbose, mixing vague capability descriptions with partially concrete code examples. Many sections (Swarm Coordination, Neural Network Integration, Performance Monitoring) are abstract bullet points that provide no actionable guidance. The skill would benefit enormously from being trimmed to just the MCP tool signatures with concrete examples, a clear workflow with validation steps, and references to separate files for advanced topics.

Suggestions

Remove all abstract capability descriptions (Swarm Coordination, Neural Network Integration, Performance Monitoring, Error Analysis) and replace with concrete, executable examples or move to separate reference files.

Add explicit validation checkpoints and error recovery steps to the matrix optimization pipeline workflow, e.g., 'If analyzeMatrix shows condition number > X, apply preconditioning before solving'.

Replace placeholder variables (matrixData, sparseValues, create_diagonally_dominant_matrix) with complete, executable code examples that Claude can directly use.

Split advanced integration content (Flow Nexus, other agents) into separate referenced files and keep SKILL.md focused on core matrix analysis workflow with MCP tool usage.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with many sections that describe capabilities Claude already knows or could infer. Sections like 'Swarm Coordination', 'Neural Network Integration', 'Performance Monitoring', and 'Error Analysis' are vague bullet-point lists that add no actionable information. The persona preamble and capability listing waste significant tokens.	1 / 3
Actionability	The code examples for MCP tool calls are somewhat concrete and show specific parameter structures, but many are pseudocode-like (e.g., `create_diagonally_dominant_matrix(n)` is undefined, `matrixData` and `sparseValues` are placeholders). Large sections like 'Advanced Features', 'Best Practices', and 'Integration with Claude Flow' are entirely abstract with no executable guidance.	2 / 3
Workflow Clarity	The 'Complete Matrix Optimization Pipeline' is a vague 5-step list with no concrete commands, validation checkpoints, or error recovery. The pre-solver analysis example hints at a conditional workflow but doesn't provide actual fix/retry steps. No feedback loops exist for what should be a multi-step process involving validation.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files. Everything is inlined regardless of importance, mixing quick-start usage with advanced features, integration patterns, and best practices in one long document with no clear navigation hierarchy.	1 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 01070ed

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.