agent-matrix-optimizer

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

1.40x

Quality

35%

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

42%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 reads like a generated agent system prompt rather than a curated skill: solid section structure and a few genuinely concrete MCP tool examples, undermined by heavy abstract padding, a pseudocode sandbox example, workflows without validation checkpoints, and zero use of bundle files for progressive disclosure. It is serviceable as an overview but well below the lean, executable, reference-linked standard the rubric rewards.

Suggestions

Cut the abstract bullet sections (Performance Monitoring, Error Analysis, Neural Network Integration, Integration Guidelines) down to one line each or move them to a reference file — Claude already knows what convergence tracking and error propagation are.

Make the sandbox example executable: import os, define or remove create_diagonally_dominant_matrix and analyze_matrix_properties, or replace with a real scipy snippet.

Move the tool API details and sandbox deployment examples into references/ files (e.g. references/tools.md, references/sandbox.md) and keep SKILL.md as a short overview with clearly signaled links.

Dimension	Reasoning	Score
Conciseness	The ~180-line body is noticeably padded: sections like 'Performance Monitoring' ('Convergence Tracking', 'Memory Usage Optimization') and 'Error Analysis' are abstract bullet lists adding nothing Claude doesn't already know about linear algebra, and the closing line is pure marketing ('serves as the foundation for all matrix-based operations').	2 / 5
Actionability	The three MCP tool examples (analyzeMatrix, solve, estimateEntry) include concrete parameters, but the Flow Nexus sandbox snippet is effectively pseudocode — create_diagonally_dominant_matrix(n) and analyze_matrix_properties(A) are undefined and os is never imported — and much of the body is abstract bullet guidance with no executable substance.	3 / 5
Workflow Clarity	'Complete Matrix Optimization Pipeline' lists a coherent 5-phase sequence (Analysis → Preprocessing → Solving → Validation → Optimization), but each phase is a one-liner with no commands, and no validation checkpoints or error-recovery loops appear anywhere in the workflows.	3 / 5
Progressive Disclosure	The body has clear section headers and no nested-reference problem, but everything — tool catalog, usage scenarios, sandbox code, best practices — is inlined in one ~180-line monolith with no references/ files at all, where the API details and sandbox examples clearly belong in separate files.	3 / 5
	Total	11 / 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 boilerplate: it names the skill's domain and an invocation token but communicates no capabilities and no usage triggers, so a user or Claude has almost nothing to decide relevance from. It falls well below the good examples, which state concrete actions plus an explicit 'Use when' clause. The rich second embedded description block is in the body, not the frontmatter, and does not count here.

Suggestions

Replace the boilerplate with a capability statement such as 'Analyzes matrix properties (diagonal dominance, symmetry, condition numbers) and recommends preprocessing/optimizations for large-scale linear systems.'

Add an explicit trigger clause, e.g. 'Use when analyzing matrix properties, estimating condition numbers, or preparing matrices for sublinear solvers.'

Include natural trigger terms users would actually say — 'matrix', 'diagonal dominance', 'condition number', 'linear system', 'solver' — rather than only the '$agent-matrix-optimizer' invocation token.

Dimension	Reasoning	Score
Specificity	The description only states 'Agent skill for matrix-optimizer - invoke with $agent-matrix-optimizer' — it names the domain but lists no actions whatsoever, sitting between the no-actions anchor 1 and the 1-2-concrete-actions anchor 3.	2 / 5
Completeness	It provides only a vague 'what' ('Agent skill for matrix-optimizer') and contains no 'Use when...' clause or equivalent trigger guidance, matching anchor 2 exactly; the missing-when guideline caps this at 3 at most regardless.	2 / 5
Trigger Term Quality	The only keyword is the technical identifier 'matrix-optimizer' and the invocation token '$agent-matrix-optimizer'; natural phrases a user would say (e.g. 'analyze matrix properties', 'diagonal dominance', 'condition number') are entirely missing.	2 / 5
Distinctiveness Conflict Risk	'matrix-optimizer' is a fairly niche domain with limited overlap risk, but the boilerplate 'Agent skill for X - invoke with $X' template is generic and would pattern-match against every sibling agent skill.	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: 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.