CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-matrix-optimizer

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

42

1.40x

Quality

13%

Does it follow best practices?

Impact

87%

1.40x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Evaluation results

76%

15%

Matrix Solver Readiness Analysis Tool

Matrix property analysis workflow

Criteria
Without context
With context

Diagonal dominance check

100%

100%

Symmetry check

100%

100%

Condition number estimation

100%

100%

Spectral gap computation

30%

70%

Dominance failure recommendation

41%

100%

Analysis-before-solve ordering

100%

100%

Structured JSON report

80%

100%

Preprocessing phase present

10%

60%

Validation phase present

0%

12%

Error handling

40%

0%

Without context: $0.3832 · 1m 37s · 20 turns · 25 in / 6,168 out tokens

With context: $0.8339 · 3m 16s · 33 turns · 39 in / 12,716 out tokens

86%

41%

Large-Scale Sparse Linear System Solver

Sparse solver method and convergence parameters

Criteria
Without context
With context

COO format structure

50%

100%

Neumann series method

0%

100%

Epsilon 1e-8

0%

100%

MaxIterations 1000

0%

100%

Pre-solve dominance check

100%

100%

Preprocessing for non-dominant

20%

30%

Solution report output

100%

100%

Error handling

62%

62%

Analysis before solve ordering

100%

100%

Validation phase

50%

50%

Without context: $0.4393 · 1m 50s · 25 turns · 31 in / 6,157 out tokens

With context: $0.6508 · 2m 45s · 27 turns · 436 in / 9,548 out tokens

100%

19%

Sublinear Solution Entry Estimator

Targeted entry estimation parameters

Criteria
Without context
With context

Random-walk method

66%

100%

Epsilon 1e-6

16%

100%

Confidence 0.95

100%

100%

Pre-estimation matrix analysis

100%

100%

Diagonal dominance check

100%

100%

Condition number estimation

100%

100%

Entry-specific targeting

100%

100%

Estimation report output

100%

100%

Error handling

50%

100%

Analysis-before-estimation ordering

100%

100%

Without context: $0.4364 · 2m 19s · 17 turns · 20 in / 8,709 out tokens

With context: $0.7714 · 3m 38s · 32 turns · 288 in / 10,722 out tokens

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.